| Title: | Species Sensitivity Distributions |
| Version: | 2.5.0 |
| Description: | Species sensitivity distributions are cumulative probability distributions which are fitted to toxicity concentrations for different species as described by Posthuma et al.(2001) <isbn:9781566705783>. The ssdtools package uses Maximum Likelihood to fit distributions such as the gamma, log-logistic, log-normal and log-normal log-normal mixture. Multiple distributions can be averaged using Akaike Information Criteria. Confidence intervals on hazard concentrations and proportions are produced by bootstrapping. |
| License: | Apache License (== 2.0) | file LICENSE |
| URL: | https://github.com/bcgov/ssdtools,https://bcgov.github.io/ssdtools/ |
| BugReports: | https://github.com/bcgov/ssdtools/issues |
| Depends: | R (≥ 4.1) |
| Imports: | abind, chk, furrr, generics, ggplot2, ggtext, glue, goftest,graphics, grid, lifecycle, parallel, plyr, purrr, Rcpp, readr,rlang, scales, ssddata, stats, stringr, tibble, TMB,universals, utils |
| Suggests: | actuar, covr, dplyr, EnvStats, extraDistr, fitdistrplus,grDevices, knitr, latex2exp, magrittr, mle.tools, patchwork,reshape2, rmarkdown, testthat (≥ 3.0.0), tidyr, tidyselect,tinytex, VGAM, withr |
| LinkingTo: | Rcpp, RcppEigen, TMB |
| VignetteBuilder: | knitr |
| Config/testthat/edition: | 3 |
| Encoding: | UTF-8 |
| Language: | en-US |
| LazyData: | true |
| RoxygenNote: | 7.3.3.9000 |
| NeedsCompilation: | yes |
| Packaged: | 2025-11-30 18:24:14 UTC; joe |
| Author: | Joe Thorley [aut, cre], Rebecca Fisher [aut], David Fox [aut], Carl Schwarz [aut], Angeline Tillmanns [ctb], Seb Dalgarno [ctb], Kathleen McTavish [ctb], Heather Thompson [ctb], Doug Spry [ctb], Rick van Dam [ctb], Graham Batley [ctb], Ali Azizishirazi [ctb], Nadine Hussein [ctb], Sarah Lyons [ctb], Duncan Kennedy [ctb], Stephanie Hazlitt [ctb], Hadley Wickham [ctb], Sergio Ibarra Espinosa [ctb], Andy Teucher [ctb], Emilie Doussantousse [ctb], Nan-Hung Hsieh [ctb], Florencia D'Andrea [ctb], Eduard Szöcs [ctb], Province of British Columbia [fnd, cph], Environment and Climate Change Canada [fnd, cph], Australian Government Department of Climate Change, Energy, the Environment and Water [fnd, cph] |
| Maintainer: | Joe Thorley <joe@poissonconsulting.ca> |
| Repository: | CRAN |
| Date/Publication: | 2025-12-01 06:10:17 UTC |
ssdtools: Species Sensitivity Distributions
Description
Species sensitivity distributions are cumulative probability distributions which are fitted to toxicity concentrations for different species as described by Posthuma et al.(2001) <isbn:9781566705783>. The ssdtools package uses Maximum Likelihood to fit distributions such as the gamma, log-logistic, log-normal and log-normal log-normal mixture. Multiple distributions can be averaged using Akaike Information Criteria. Confidence intervals on hazard concentrations and proportions are produced by bootstrapping.
Author(s)
Maintainer: Joe Thorleyjoe@poissonconsulting.ca (ORCID)
Authors:
Rebecca FisherR.Fisher@aims.gov.au
David Foxdavid.fox@environmetrics.net.au
Carl Schwarz
Other contributors:
Angeline Tillmanns [contributor]
Seb Dalgarnoseb@poissonconsulting.ca (ORCID) [contributor]
Kathleen McTavish [contributor]
Heather Thompson [contributor]
Doug Spry [contributor]
Rick van Dam [contributor]
Graham Batley [contributor]
Ali Azizishirazi [contributor]
Nadine Husseinnadine@poissonconsulting.ca (ORCID) [contributor]
Sarah Lyonssarah@poissonconsulting.ca (ORCID) [contributor]
Duncan Kennedyduncan@poissonconsulting.ca (ORCID) [contributor]
Stephanie Hazlitt [contributor]
Hadley Wickham [contributor]
Sergio Ibarra Espinosa [contributor]
Andy Teucher [contributor]
Emilie Doussantousse [contributor]
Nan-Hung Hsieh [contributor]
Florencia D'Andrea [contributor]
Eduard Szöcs (ORCID) [contributor]
Province of British Columbia [funder, copyright holder]
Environment and Climate Change Canada [funder, copyright holder]
Australian Government Department of Climate Change, Energy, the Environment and Water [funder, copyright holder]
See Also
Useful links:
Report bugs athttps://github.com/bcgov/ssdtools/issues
Augmented Data from fitdists Object
Description
Get a tibble of the original data with augmentation.
Usage
## S3 method for class 'fitdists'augment(x, ...)Arguments
x | The object. |
... | Unused. |
Value
A tibble of the agumented data.
See Also
Other generics:glance.fitdists(),tidy.fitdists()
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)augment(fits)Plot a fitdists Object
Description
A wrapper onssd_plot_cdf().
Usage
## S3 method for class 'fitdists'autoplot(object, ...)Arguments
object | The object. |
... | Unused. |
Value
A ggplot object.
See Also
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)autoplot(fits)Model Averaged Predictions for CCME Boron Data
Description
A data frame of the predictions based on 1,000 bootstrap iterations.
Usage
boron_predFormat
An object of classtbl_df (inherits fromtbl,data.frame) with 99 rows and 15 columns.
Details
- proportion
The proportion of species affected (int).
- est
The estimated concentration (dbl).
- se
The standard error of the estimate (dbl).
- lcl
The lower confidence limit (dbl).
- se
The upper confidence limit (dbl).
- dist
The distribution (chr).
Examples
## Not run: fits <- ssd_fit_dists(ssddata::ccme_boron)withr::with_seed(50, { boron_pred <- predict(fits, ci = TRUE)})head(boron_pred)## End(Not run)Turn a fitdists Object into a Tidy Tibble
Description
A wrapper ontidy.fitdists().
Usage
## S3 method for class 'fitdists'coef(object, ...)Arguments
object | The object. |
... | Unused. |
See Also
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)coef(fits)Comma and Significance Formatter![[Deprecated]](/image.pl?url=http%3a%2f%2fcran.rstudio.com%2fweb%2fpackages%2fRcpp%2f..%2flidR%2f..%2fglue%2f..%2frlang%2f..%2fssdtools%2frefman%2f.%2ffigures%2flifecycle-deprecated.svg&f=jpg&w=240)
Description
Deprecated forssd_label_comma()
Usage
comma_signif(x, digits = 3, ..., big.mark = ",")Arguments
x | A numeric vector to format. |
digits | A whole number specifying the number of significant figures. |
... | Unused. |
big.mark | A string specifying the thousands separator. |
Value
A character vector.
See Also
Examples
## Not run: comma_signif(c(0.1, 1, 10, 1000, 10000))## End(Not run)Gompertz Probability Density
Description
Gompertz Probability Density
Usage
dgompertz(x, llocation = 0, lshape = 0, log = FALSE)Arguments
x | A numeric vector of values. |
llocation | location parameter on the log scale. |
lshape | shape parameter on the log scale. |
log | logical; if TRUE, probabilities p are given as log(p). |
Value
A numeric vector.
Distribution Data
Description
A data frame of information on the implemented distributions.
Usage
dist_dataFormat
An object of classtbl_df (inherits fromtbl,data.frame) with 10 rows and 6 columns.
Details
- dist
The distribution (chr).
- bcanz
Whether the distribution belongs to the set of distributions approved by BC, Canada, Australia and New Zealand for official guidelines (flag).
- tails
Whether the distribution has both tails (flag).
- npars
The number of parameters (int).
- valid
Whether the distribution has a valid likelihood that allows it to be fit with other distributions for modeling averaging (flag).
- bound
Whether one or more parameters have boundaries (flag).
See Also
Other dists:ssd_dists(),ssd_dists_all(),ssd_dists_shiny()
Examples
dist_dataLog-Gumbel (Inverse Weibull) Probability Density
Description
Log-Gumbel (Inverse Weibull) Probability Density
Usage
dlgumbel(x, locationlog = 0, scalelog = 1, log = FALSE)Arguments
x | A numeric vector of values. |
locationlog | location on the log scale parameter. |
scalelog | scale on log scale parameter. |
log | logical; if TRUE, probabilities p are given as log(p). |
Value
A numeric vector.
Estimates for fitdists Object
Description
Gets a named list of the estimated weights and parameters.
Usage
## S3 method for class 'fitdists'estimates(x, all_estimates = FALSE, ...)Arguments
x | The object. |
all_estimates | A flag specifying whether to calculate estimates for all implemented distributions. |
... | Unused. |
Value
A named list of the estimates.
See Also
tidy.fitdists(),ssd_match_moments(),ssd_hc() andssd_plot_cdf()
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)estimates(fits)Species Sensitivity Hazard Concentration Intersection
Description
Plots the intersection between eachxintercept andyintercept value.
Usage
geom_hcintersect( mapping = NULL, data = NULL, ..., xintercept, yintercept, na.rm = FALSE, show.legend = NA)Arguments
mapping | Set of aesthetic mappings created by |
data | The data to be displayed in this layer. There are threeoptions: If A A |
... | Other arguments passed on to
|
xintercept | The x-value for the intersect. |
yintercept | The y-value for the intersect. |
na.rm | If |
show.legend | logical. Should this layer be included in the legends? |
See Also
Other ggplot:geom_ssdpoint(),geom_ssdsegment(),geom_xribbon(),scale_colour_ssd(),ssd_pal()
Examples
ggplot2::ggplot(ssddata::ccme_boron, ggplot2::aes(x = Conc)) + geom_ssdpoint() + geom_hcintersect(xintercept = 1.5, yintercept = 0.05)Species Sensitivity Data Points
Description
Deprecated forgeom_ssdpoint().
Usage
geom_ssd( mapping = NULL, data = NULL, stat = "ssdpoint", position = "identity", ..., na.rm = FALSE, show.legend = NA, inherit.aes = TRUE)Arguments
mapping | Set of aesthetic mappings created by |
data | The data to be displayed in this layer. There are threeoptions: If A A |
stat | The statistical transformation to use on the data for this layer.When using a
|
position | A position adjustment to use on the data for this layer. Thiscan be used in various ways, including to prevent overplotting andimproving the display. The
|
... | Other arguments passed on to
|
na.rm | If |
show.legend | logical. Should this layer be included in the legends? |
inherit.aes | If |
Species Sensitivity Data Points
Description
Uses the empirical cumulative distribution to create scatterplot of pointsx.
Usage
geom_ssdpoint( mapping = NULL, data = NULL, stat = "ssdpoint", position = "identity", ..., na.rm = FALSE, show.legend = NA, inherit.aes = TRUE)Arguments
mapping | Set of aesthetic mappings created by |
data | The data to be displayed in this layer. There are threeoptions: If A A |
stat | The statistical transformation to use on the data for this layer.When using a
|
position | A position adjustment to use on the data for this layer. Thiscan be used in various ways, including to prevent overplotting andimproving the display. The
|
... | Other arguments passed on to
|
na.rm | If |
show.legend | logical. Should this layer be included in the legends? |
inherit.aes | If |
See Also
Other ggplot:geom_hcintersect(),geom_ssdsegment(),geom_xribbon(),scale_colour_ssd(),ssd_pal()
Examples
ggplot2::ggplot(ssddata::ccme_boron, ggplot2::aes(x = Conc)) + geom_ssdpoint()Species Sensitivity Censored Segments
Description
Uses the empirical cumulative distribution to draw lines between pointsx andxend.
Usage
geom_ssdsegment( mapping = NULL, data = NULL, stat = "ssdsegment", position = "identity", ..., arrow = NULL, arrow.fill = NULL, lineend = "butt", linejoin = "round", na.rm = FALSE, show.legend = NA, inherit.aes = TRUE)Arguments
mapping | Set of aesthetic mappings created by |
data | The data to be displayed in this layer. There are threeoptions: If A A |
stat | The statistical transformation to use on the data for this layer.When using a
|
position | A position adjustment to use on the data for this layer. Thiscan be used in various ways, including to prevent overplotting andimproving the display. The
|
... | Other arguments passed on to
|
arrow | specification for arrow heads, as created by |
arrow.fill | fill colour to use for the arrow head (if closed). |
lineend | Line end style (round, butt, square). |
linejoin | Line join style (round, mitre, bevel). |
na.rm | If |
show.legend | logical. Should this layer be included in the legends? |
inherit.aes | If |
See Also
Other ggplot:geom_hcintersect(),geom_ssdpoint(),geom_xribbon(),scale_colour_ssd(),ssd_pal()
Examples
ggplot2::ggplot(ssddata::ccme_boron, ggplot2::aes(x = Conc, xend = Conc * 2)) + geom_ssdsegment()Ribbon on X-Axis
Description
Plots thex interval defined byxmin andxmax.
Usage
geom_xribbon( mapping = NULL, data = NULL, stat = "identity", position = "identity", ..., na.rm = FALSE, show.legend = NA, inherit.aes = TRUE)Arguments
mapping | Set of aesthetic mappings created by |
data | The data to be displayed in this layer. There are threeoptions: If A A |
stat | The statistical transformation to use on the data for this layer.When using a
|
position | A position adjustment to use on the data for this layer. Thiscan be used in various ways, including to prevent overplotting andimproving the display. The
|
... | Other arguments passed on to
|
na.rm | If |
show.legend | logical. Should this layer be included in the legends? |
inherit.aes | If |
See Also
Other ggplot:geom_hcintersect(),geom_ssdpoint(),geom_ssdsegment(),scale_colour_ssd(),ssd_pal()
Examples
gp <- ggplot2::ggplot(boron_pred) + geom_xribbon(ggplot2::aes(xmin = lcl, xmax = ucl, y = proportion))Get a tibble summarizing each distribution
Description
Gets a tibble with a single row for each distribution.
Usage
## S3 method for class 'fitdists'glance(x, ..., wt = FALSE)Arguments
x | The object. |
... | Unused. |
wt | A flag specifying whether to return the Akaike weight as "wt" instead of "weight". |
Value
A tidy tibble of the distributions.
See Also
Other generics:augment.fitdists(),tidy.fitdists()
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)glance(fits, wt = TRUE)Is fitdists Object
Description
Tests whether x is a fitdists Object.
Usage
is.fitdists(x)Arguments
x | The object. |
Value
A flag specifying whether x is a fitdists Object.
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)is.fitdists(fits)Is Censored
Description
Deprecated forssd_is_censored().
Usage
is_censored(x)Arguments
x | A fitdists object. |
Value
A flag indicating if the data is censored.
See Also
Parameter Descriptions for ssdtools Functions
Description
Parameter Descriptions for ssdtools Functions
Arguments
... | Unused. |
add_x | The value to add to the label x values (before multiplying by |
all | A flag specifying whether to also return transformed parameters. |
all_dists | A flag specifying whether all the named distributions must fit successfully. |
all_estimates | A flag specifying whether to calculate estimates for all implemented distributions. |
at_boundary_ok | A flag specifying whether a model with one or moreparameters at the boundary should be considered to have converged (default = TRUE). |
average | A flag specifying whether to provide model averaged values as opposed to a value for each distribution. |
bcanz | A flag or NULL specifying whether to only include distributions in the set that is approved by BC, Canada, Australia and New Zealand for official guidelines. |
big.mark | A string specifying the thousands separator. |
breaks | A character vector |
bounds | A named non-negative numeric vector of the left and right bounds foruncensored missing (0 and Inf) data in terms of the orders of magnituderelative to the extremes for non-missing values. |
chk | A flag specifying whether to check the arguments. |
ci | A flag specifying whether to estimate confidence intervals (by bootstrapping). |
ci_method | A string specifying which method to use for estimatingthe standard error and confidence limits from the bootstrap samples.The default and recommended value is still |
censoring | A numeric vector of the left and right censoring values. |
color | A string of the column in data for the color aesthetic. |
computable | A flag specifying whether to only return fits with numerically computable standard errors. |
conc | A numeric vector of concentrations to calculate the hazard proportions for. |
control | A list of control parameters passed to |
data | A data frame. |
decimal.mark | A string specifying the numeric decimal point. |
delta | A non-negative number specifying the maximum absolute AIC difference cutoff.Distributions with an absolute AIC difference greater than delta are excluded from the calculations. |
digits | A whole number specifying the number of significant figures. |
dists | A character vector of the distribution names. |
est_method | A string specifying whether to estimate directly fromthe model-averaged cumulative distribution function ( |
fitdists | An object of class fitdists. |
hc | A value between 0 and 1 indicating the proportion hazard concentration (or NULL). |
hc_value | A number of the hazard concentration value to offset. |
label | A string of the column in data with the labels. |
label_size | A number for the size of the labels. |
left | A string of the column in data with the concentrations. |
level | A number between 0 and 1 of the confidence level of the interval. |
linecolor | A string of the column in pred to use for the line color. |
linetype | A string of the column in pred to use for the linetype. |
llocation | location parameter on the log scale. |
location | location parameter. |
locationlog | location on the log scale parameter. |
locationlog1 | locationlog1 parameter. |
locationlog2 | locationlog2 parameter. |
log | logical; if TRUE, probabilities p are given as log(p). |
log.p | logical; if TRUE, probabilities p are given as log(p). |
lscale | scale parameter on the log scale. |
lshape | shape parameter on the log scale. |
lshape1 | shape1 parameter on the log scale. |
lshape2 | shape2 parameter on the log scale. |
lower.tail | logical; if TRUE (default), probabilities are |
meanlog | mean on log scale parameter. |
meanlog1 | mean on log scale parameter. |
meanlog2 | mean on log scale parameter. |
min_pboot | A number between 0 and 1 of the minimumproportion of bootstrap samples that must successfully fit (return a likelihood)to report the confidence intervals. |
min_pmix | A number between 0 and 0.5 specifying the minimum proportion in mixture models. |
npars | A whole numeric vector specifying which distributions to include based on the number of parameters. |
multi_est | A flag specifying whether to estimate directly fromthe model-averaged cumulative distribution function ( |
na.rm | A flag specifying whether to silently remove missing values orremove them with a warning. |
n | positive number of observations. |
nboot | A count of the number of bootstrap samples to use to estimate the confidence limits. A value of 10,000 is recommended for official guidelines. |
nrow | A positive whole number of the minimum number of non-missing rows. |
nsim | A positive whole number of the number of simulations to generate. |
object | The object. |
parametric | A flag specifying whether to perform parametric bootstrapping as opposed to non-parametrically resampling the original data with replacement. |
p | vector of probabilities. |
percent | A numeric vector of percent values to estimate hazard concentrations for. Deprecated for |
pmix | Proportion mixture parameter. |
proportion | A numeric vector of proportion values to estimate hazard concentrations for. |
pvalue | A flag specifying whether to return p-values or the statistics (default) for the various tests. |
pred | A data frame of the predictions. |
q | vector of quantiles. |
range_shape1 | A numeric vector of length two of the lower and upper bounds for the shape1 parameter. |
range_shape2 | shape2 parameter. |
reweight | A flag specifying whether to reweight weights by dividing by the largest weight. |
rescale | A flag specifying whether to leave the values unchanged (FALSE) or to rescale concentration values by dividing by the geometric mean of the minimum and maximum positive finite values (TRUE) or a string specifying whether to leave the values unchanged ("no") or to rescale concentration values by dividing by the geometric mean of the minimum and maximum positive finite values ("geomean") or to logistically transform ("odds"). |
ribbon | A flag indicating whether to plot the confidence interval as a grey ribbon as opposed to green solid lines. |
right | A string of the column in data with the right concentration values. |
save_to | NULL or a string specifying a directory to save where the bootstrap datasets and parameter estimates (when successfully converged) to. |
samples | A flag specfying whether to include a numeric vector of the bootstrap samples as a list column in the output. |
scale | scale parameter. |
scalelog1 | scalelog1 parameter. |
scalelog2 | scalelog2 parameter. |
scalelog | scale on log scale parameter. |
sdlog | standard deviation on log scale parameter. |
sdlog1 | standard deviation on log scale parameter. |
sdlog2 | standard deviation on log scale parameter. |
select | A character vector of the distributions to select. |
shape | shape parameter. |
shape1 | shape1 parameter. |
shape2 | shape2 parameter. |
shift_x | The value to multiply the label x values by (after adding |
silent | A flag indicating whether fits should fail silently. |
size | A number for the size of the labels. Deprecated for |
strict | A flag indicating whether all elements of select must be present. |
suffix | Additional text to display after the number on the y-axis. |
tails | A flag or NULL specifying whether to only include distributions with both tails. |
text_size | A number for the text size. |
theme_classic | A flag specifying whether to use the classic theme or the default. |
trans | A string of which transformation to use. Accepted values include |
valid | A flag or NULL specifying whether to include distributions with valid likelihoods that allows them to be fit with other distributions for modeling averaging. |
weight | A string of the numeric column in data with positive weights less than or equal to 1,000 or NULL. |
odds_max | A number specifying the upper left value when |
wt | A flag specifying whether to return the Akaike weight as "wt" instead of "weight". |
x | The object. |
xbreaks | The x-axis breaks as one of:
|
xlimits | The x-axis limits as one of:
|
xintercept | The x-value for the intersect. |
xlab | A string of the x-axis label. |
yintercept | The y-value for the intersect. |
ylab | A string of the x-axis label. |
burrIII3.weight | weight parameter for the Burr III distribution. |
burrIII3.shape1 | shape1 parameter for the Burr III distribution. |
burrIII3.shape2 | shape2 parameter for the Burr III distribution. |
burrIII3.scale | scale parameter for the Burr III distribution. |
gamma.weight | weight parameter for the gamma distribution. |
gamma.shape | shape parameter for the gamma distribution. |
gamma.scale | scale parameter for the gamma distribution. |
gompertz.weight | weight parameter for the Gompertz distribution. |
gompertz.location | location parameter for the Gompertz distribution. |
gompertz.shape | shape parameter for the Gompertz distribution. |
invpareto.weight | weight parameter for the inverse Pareto distribution. |
invpareto.shape | shape parameter for the inverse Pareto distribution. |
invpareto.scale | scale parameter for the inverse Pareto distribution. |
lgumbel.weight | weight parameter for the log-Gumbel distribution. |
lgumbel.locationlog | location parameter for the log-Gumbel distribution. |
lgumbel.scalelog | scale parameter for the log-Gumbel distribution. |
llogis.weight | weight parameter for the log-logistic distribution. |
llogis.locationlog | location parameter for the log-logistic distribution. |
llogis.scalelog | scale parameter for the log-logistic distribution. |
llogis_llogis.weight | weight parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.locationlog1 | locationlog1 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.scalelog1 | scalelog1 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.locationlog2 | locationlog2 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.scalelog2 | scalelog2 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.pmix | pmix parameter for the log-logistic log-logistic mixture distribution. |
lnorm.weight | weight parameter for the log-normal distribution. |
lnorm.meanlog | meanlog parameter for the log-normal distribution. |
lnorm.sdlog | sdlog parameter for the log-normal distribution. |
lnorm_lnorm.weight | weight parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.meanlog1 | meanlog1 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.sdlog1 | sdlog1 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.meanlog2 | meanlog2 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.sdlog2 | sdlog2 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.pmix | pmix parameter for the log-normal log-normal mixture distribution. |
weibull.weight | weight parameter for the Weibull distribution. |
weibull.shape | shape parameter for the Weibull distribution. |
weibull.scale | scale parameter for the Weibull distribution. |
Cumulative Distribution Function for Gompertz Distribution
Description
Deprecated forssd_pgompertz().
Usage
pgompertz(q, llocation = 0, lshape = 0, lower.tail = TRUE, log.p = FALSE)Arguments
q | vector of quantiles. |
llocation | location parameter on the log scale. |
lshape | shape parameter on the log scale. |
lower.tail | logical; if TRUE (default), probabilities are |
log.p | logical; if TRUE, probabilities p are given as log(p). |
Cumulative Distribution Function for Log-Gumbel Distribution
Description
Deprecated forssd_plgumbel().
Usage
plgumbel(q, locationlog = 0, scalelog = 1, lower.tail = TRUE, log.p = FALSE)Arguments
q | vector of quantiles. |
locationlog | location on the log scale parameter. |
scalelog | scale on log scale parameter. |
lower.tail | logical; if TRUE (default), probabilities are |
log.p | logical; if TRUE, probabilities p are given as log(p). |
Predict Hazard Concentrations of fitburrlioz Object
Description
A wrapper onssd_hc() that by default calculatesall hazard concentrations from 1 to 99%.
Usage
## S3 method for class 'fitburrlioz'predict( object, percent, proportion = 1:99/100, ..., ci = FALSE, level = 0.95, nboot = 1000, min_pboot = 0.95, parametric = TRUE)Arguments
object | The object. |
percent | A numeric vector of percent values to estimate hazard concentrations for. Deprecated for |
proportion | A numeric vector of proportion values to estimate hazard concentrations for. |
... | Unused. |
ci | A flag specifying whether to estimate confidence intervals (by bootstrapping). |
level | A number between 0 and 1 of the confidence level of the interval. |
nboot | A count of the number of bootstrap samples to use to estimate the confidence limits. A value of 10,000 is recommended for official guidelines. |
min_pboot | A number between 0 and 1 of the minimumproportion of bootstrap samples that must successfully fit (return a likelihood)to report the confidence intervals. |
parametric | A flag specifying whether to perform parametric bootstrapping as opposed to non-parametrically resampling the original data with replacement. |
Details
It is useful for plotting purposes.
See Also
Examples
fits <- ssd_fit_burrlioz(ssddata::ccme_boron)predict(fits)Predict Hazard Concentrations of fitdists Object
Description
A wrapper onssd_hc() that by default calculatesall hazard concentrations from 1 to 99%.
Usage
## S3 method for class 'fitdists'predict( object, percent, proportion = 1:99/100, ..., average = TRUE, ci = FALSE, level = 0.95, nboot = 1000, min_pboot = 0.95, est_method = "multi", ci_method = "weighted_samples", parametric = TRUE, delta = 9.21, control = NULL)Arguments
object | The object. |
percent | A numeric vector of percent values to estimate hazard concentrations for. Deprecated for |
proportion | A numeric vector of proportion values to estimate hazard concentrations for. |
... | Unused. |
average | A flag specifying whether to provide model averaged values as opposed to a value for each distribution. |
ci | A flag specifying whether to estimate confidence intervals (by bootstrapping). |
level | A number between 0 and 1 of the confidence level of the interval. |
nboot | A count of the number of bootstrap samples to use to estimate the confidence limits. A value of 10,000 is recommended for official guidelines. |
min_pboot | A number between 0 and 1 of the minimumproportion of bootstrap samples that must successfully fit (return a likelihood)to report the confidence intervals. |
est_method | A string specifying whether to estimate directly fromthe model-averaged cumulative distribution function ( |
ci_method | A string specifying which method to use for estimatingthe standard error and confidence limits from the bootstrap samples.The default and recommended value is still |
parametric | A flag specifying whether to perform parametric bootstrapping as opposed to non-parametrically resampling the original data with replacement. |
delta | A non-negative number specifying the maximum absolute AIC difference cutoff.Distributions with an absolute AIC difference greater than delta are excluded from the calculations. |
control | A list of control parameters passed to |
Details
It is useful for plotting purposes.
See Also
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)predict(fits)Quantile Function for Gompertz Distribution
Description
Deprecated forssd_qgompertz().
Usage
qgompertz(p, llocation = 0, lshape = 0, lower.tail = TRUE, log.p = FALSE)Arguments
p | vector of probabilities. |
llocation | location parameter on the log scale. |
lshape | shape parameter on the log scale. |
lower.tail | logical; if TRUE (default), probabilities are |
log.p | logical; if TRUE, probabilities p are given as log(p). |
Quantile Function for Log-Gumbel Distribution
Description
Deprecated forssd_qlgumbel().
Usage
qlgumbel(p, locationlog = 0, scalelog = 1, lower.tail = TRUE, log.p = FALSE)Arguments
p | vector of probabilities. |
locationlog | location on the log scale parameter. |
scalelog | scale on log scale parameter. |
lower.tail | logical; if TRUE (default), probabilities are |
log.p | logical; if TRUE, probabilities p are given as log(p). |
Objects exported from other packages
Description
These objects are imported from other packages. Follow the linksbelow to see their documentation.
- generics
- ggplot2
- graphics
- stats
- universals
Random Generation for Gompertz Distribution
Description
Deprecated forssd_rgompertz().
Usage
rgompertz(n, llocation = 0, lshape = 0)Arguments
n | positive number of observations. |
llocation | location parameter on the log scale. |
lshape | shape parameter on the log scale. |
Random Generation for log-Gumbel Distribution
Description
Deprecated forssd_rlgumbel().
Usage
rlgumbel(n, locationlog = 0, scalelog = 1)Arguments
n | positive number of observations. |
locationlog | location on the log scale parameter. |
scalelog | scale on log scale parameter. |
Details
Discrete color-blind scale for SSD Plots
Description
The functions were designed for coloring different groups in a plot of SSD data.
Usage
scale_colour_ssd(...)scale_color_ssd(...)scale_fill_ssd(...)Arguments
... | Arguments passed to |
Functions
scale_color_ssd(): Discrete color-blind scale for SSD Plotsscale_fill_ssd(): Discrete color-blind scale for SSD Plots
See Also
Other ggplot:geom_hcintersect(),geom_ssdpoint(),geom_ssdsegment(),geom_xribbon(),ssd_pal()
Examples
# Use the color-blind palette for a SSD plotssd_plot(ssddata::ccme_boron, boron_pred, shape = "Group", color = "Group") + scale_colour_ssd()# Use the color-blind palette for a histogram of concentrationsggplot2::ggplot(ssddata::ccme_boron, ggplot2::aes(x = Species, y = Conc, fill = Group)) + ggplot2::geom_col() + scale_fill_ssd() + ggplot2::theme(axis.text.x = ggplot2::element_text(angle = 90, vjust = 0.5, hjust = 1))Is At Boundary
Description
Generic function to test if one or more parameters is at boundary.
Usage
ssd_at_boundary(x, ...)## S3 method for class 'tmbfit'ssd_at_boundary(x, ...)## S3 method for class 'fitdists'ssd_at_boundary(x, ...)Arguments
x | The object. |
... | Unused. |
Value
A flag for each distribution indicating if one or more parameters at boundary.
A flag indicating if one or more parameters at boundary.
A logical vector for each distribution indicating if one or more parameters at boundary.
Methods (by class)
ssd_at_boundary(tmbfit): Is At Boundary for tmbfit Objectssd_at_boundary(fitdists): Is At Boundary for fitdists Object
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron, dists = c("lnorm", "lnorm_lnorm", "burrIII3"))ssd_at_boundary(fits$lnorm)ssd_at_boundary(fits$lnorm_lnorm)ssd_at_boundary(fits$burrIII3)fits <- ssd_fit_dists(ssddata::ccme_boron, dists = c("lnorm", "lnorm_lnorm", "burrIII3"))ssd_at_boundary(fits)Censor Data
Description
Censors data to a specified range based on thecensoring argument.The function is useful for creating test data sets.
Usage
ssd_censor_data(data, left = "Conc", ..., right = left, censoring = c(0, Inf))Arguments
data | A data frame. |
left | A string of the column in data with the concentrations. |
... | Unused. |
right | A string of the column in data with the right concentration values. |
censoring | A numeric vector of the left and right censoring values. |
Value
A tibble of the censored data.
Examples
ssd_censor_data(ssddata::ccme_boron, censoring = c(2.5, Inf))Confidence Interval Methods for SSDs
Description
Returns a character vector of the available non-deprecatedmethods for getting the model averaged confidence limits for two or moredistributions.
Usage
ssd_ci_methods()Value
A character vector of the available methods.
Examples
ssd_ci_methods()Is Computable Standard Errors
Description
Generic function to test if all parameters have numerically computable standard errors.
Usage
ssd_computable(x, ...)## S3 method for class 'tmbfit'ssd_computable(x, ...)## S3 method for class 'fitdists'ssd_computable(x, ...)Arguments
x | The object. |
... | Unused. |
Value
A flag for each distribution indicating if all parameters have numerically computable standard errors.
A flag indicating if all parameters have numerically computable standard errors.
A logical vector for each distribution indicating if all parameters have numerically computable standard errors.
Methods (by class)
ssd_computable(tmbfit): Is Computable Standard for tmbfit Objectssd_computable(fitdists): Is At Boundary for fitdists Object
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron, dists = c("lnorm", "lnorm_lnorm", "burrIII3"))ssd_computable(fits$lnorm)ssd_computable(fits$lnorm_lnorm)ssd_computable(fits$burrIII3)fits <- ssd_fit_dists(ssddata::ccme_boron, dists = c("lnorm", "lnorm_lnorm", "burrIII3"))ssd_computable(fits)Data from fitdists Object
Description
Get a tibble of the original data.
Usage
ssd_data(x)Arguments
x | The object. |
Value
A tibble of the original data.
See Also
augment.fitdists(),ssd_ecd_data() andssd_sort_data()
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)ssd_data(fits)Species Sensitivity Distributions
Description
Gets a character vector of the names of the available distributions.
Usage
ssd_dists(bcanz = NULL, ..., tails = NULL, npars = 2:5, valid = TRUE)Arguments
bcanz | A flag or NULL specifying whether to only include distributions in the set that is approved by BC, Canada, Australia and New Zealand for official guidelines. |
... | Unused. |
tails | A flag or NULL specifying whether to only include distributions with both tails. |
npars | A whole numeric vector specifying which distributions to include based on the number of parameters. |
valid | A flag or NULL specifying whether to include distributions with valid likelihoods that allows them to be fit with other distributions for modeling averaging. |
Value
A unique, sorted character vector of the distributions.
See Also
Other dists:dist_data,ssd_dists_all(),ssd_dists_shiny()
Examples
ssd_dists()ssd_dists(bcanz = TRUE)ssd_dists(tails = FALSE)ssd_dists(npars = 5)All Species Sensitivity Distributions
Description
Gets a character vector of the names of all the available distributions.
Usage
ssd_dists_all(valid = TRUE)Arguments
valid | A flag or NULL specifying whether to include distributions with valid likelihoods that allows them to be fit with other distributions for modeling averaging. |
Value
A unique, sorted character vector of the distributions.
See Also
Other dists:dist_data,ssd_dists(),ssd_dists_shiny()
Examples
ssd_dists_all()BCANZ Distributions
Description
Gets a character vector of the names of the distributionsadopted by BC, Canada, Australia and New Zealand for official guidelines.
Usage
ssd_dists_bcanz(npars = c(2L, 5L))Arguments
npars | A whole numeric vector specifying which distributions to include based on the number of parameters. |
Value
A unique, sorted character vector of the distributions.
See Also
Examples
ssd_dists_bcanz()ssd_dists_bcanz(npars = 2)All Shiny Species Sensitivity Distributions
Description
Gets a character vector of the names of all the available distributionsin the shinyssdtools.
Usage
ssd_dists_shiny()Value
A unique, sorted character vector of the distributions.
See Also
Other dists:dist_data,ssd_dists(),ssd_dists_all()
Examples
ssd_dists_shiny()Default Parameter Estimates
Description
Default Parameter Estimates
Usage
ssd_eburrIII3()ssd_egamma()ssd_egompertz()ssd_einvpareto()ssd_elgumbel()ssd_elgumbel()ssd_ellogis_llogis()ssd_ellogis()ssd_elnorm_lnorm()ssd_elnorm()ssd_emulti()ssd_eweibull()Functions
ssd_eburrIII3(): Default Parameter Values for BurrIII Distributionssd_egamma(): Default Parameter Values for Gamma Distributionssd_egompertz(): Default Parameter Values for Gompertz Distributionssd_einvpareto(): Default Parameter Values for Inverse Pareto Distributionssd_elgumbel(): Default Parameter Values for Log-Gumbel Distributionssd_elgumbel(): Default Parameter Values for log-Gumbel Distributionssd_ellogis_llogis(): Default Parameter Values for Log-Logistic/Log-Logistic Mixture Distributionssd_ellogis(): Default Parameter Values for Log-Logistic Distributionssd_elnorm_lnorm(): Default Parameter Values for Log-Normal/Log-Normal Mixture Distributionssd_elnorm(): Default Parameter Values for Log-Normal Distributionssd_emulti(): Default Parameter Values for Multiple Distributionsssd_eweibull(): Default Parameter Values for Log-Normal Distribution
See Also
Examples
ssd_eburrIII3()ssd_egamma()ssd_egompertz()ssd_einvpareto()ssd_einvpareto()ssd_elgumbel()ssd_ellogis_llogis()ssd_ellogis()ssd_elnorm_lnorm()ssd_elnorm()ssd_emulti()ssd_eweibull()Empirical Cumulative Density
Description
Empirical Cumulative Density
Usage
ssd_ecd(x, ties.method = "first")Arguments
x | a numeric, complex, character or logical vector. |
ties.method | a character string specifying how ties are treated,see ‘Details’; can be abbreviated. |
Value
A numeric vector of the empirical cumulative density.
Examples
ssd_ecd(1:10)Empirical Cumulative Density for Species Sensitivity Data
Description
Empirical Cumulative Density for Species Sensitivity Data
Usage
ssd_ecd_data( data, left = "Conc", right = left, ..., bounds = c(left = 1, right = 1))Arguments
data | A data frame. |
left | A string of the column in data with the concentrations. |
right | A string of the column in data with the right concentration values. |
... | Unused. |
bounds | A named non-negative numeric vector of the left and right bounds foruncensored missing (0 and Inf) data in terms of the orders of magnituderelative to the extremes for non-missing values. |
Value
A numeric vector of the empirical cumulative density for the rowsin data.
See Also
Examples
ssd_ecd_data(ssddata::ccme_boron)Estimate Methods for SSDs
Description
Returns a character vector of the available non-deprecatedmethods for getting the model averaged estimates for two or moredistributions.
Usage
ssd_est_methods()Value
A character vector of the available methods.
Examples
ssd_est_methods()Proportion Exposure
Description
Calculates average proportion exposed based on log-normal distribution of concentrations.
Usage
ssd_exposure(x, meanlog = 0, sdlog = 1, ..., nboot = 1000)Arguments
x | The object. |
meanlog | The mean of the exposure concentrations on the log scale. |
sdlog | The standard deviation of the exposure concentrations on the log scale. |
... | Unused. |
nboot | The number of samples to use to calculate the exposure. |
Value
The proportion exposed.
Examples
## Not run: fits <- ssd_fit_dists(ssddata::ccme_boron, dists = "lnorm")withr::with_seed(50, { ssd_exposure(fits) ssd_exposure(fits, meanlog = 1) ssd_exposure(fits, meanlog = 1, sdlog = 1)})## End(Not run)Fit BCANZ Distributions
Description
Fits distributions using settings adopted byBC, Canada, Australia and New Zealand for official guidelines.
Usage
ssd_fit_bcanz(data, left = "Conc", ..., dists = ssd_dists_bcanz())Arguments
data | A data frame. |
left | A string of the column in data with the concentrations. |
... | Unused. |
dists | A character vector of the distribution names. |
Value
An object of class fitdists.
See Also
Other BCANZ:ssd_hc_bcanz(),ssd_hp_bcanz()
Examples
ssd_fit_bcanz(ssddata::ccme_boron)Fit Burrlioz Distributions
Description
Fits 'burrIII3' distribution.If shape1 parameter is at boundary returns 'lgumbel' (which is equivalent to inverse Weibull).Else if shape2 parameter is at a boundary returns 'invpareto'.Otherwise returns 'burrIII3'
Usage
ssd_fit_burrlioz( data, left = "Conc", ..., rescale = FALSE, control = list(), silent = FALSE)Arguments
data | A data frame. |
left | A string of the column in data with the concentrations. |
... | Unused. |
rescale | A flag specifying whether to leave the values unchanged (FALSE) or to rescale concentration values by dividing by the geometric mean of the minimum and maximum positive finite values (TRUE) or a string specifying whether to leave the values unchanged ("no") or to rescale concentration values by dividing by the geometric mean of the minimum and maximum positive finite values ("geomean") or to logistically transform ("odds"). |
control | A list of control parameters passed to |
silent | A flag indicating whether fits should fail silently. |
Value
An object of class fitdists.
See Also
Examples
ssd_fit_burrlioz(ssddata::ccme_boron)Fit Distributions
Description
Fits one or more distributions to species sensitivity data.
Usage
ssd_fit_dists( data, left = "Conc", ..., right = left, weight = NULL, dists = ssd_dists_bcanz(), nrow = 6L, rescale = FALSE, odds_max = 0.999, reweight = FALSE, computable = FALSE, at_boundary_ok = TRUE, all_dists = FALSE, min_pmix = ssd_min_pmix(nrow(data)), range_shape1 = c(0.05, 20), range_shape2 = range_shape1, control = list(), silent = FALSE)Arguments
data | A data frame. |
left | A string of the column in data with the concentrations. |
... | Unused. |
right | A string of the column in data with the right concentration values. |
weight | A string of the numeric column in data with positive weights less than or equal to 1,000 or NULL. |
dists | A character vector of the distribution names. |
nrow | A positive whole number of the minimum number of non-missing rows. |
rescale | A flag specifying whether to leave the values unchanged (FALSE) or to rescale concentration values by dividing by the geometric mean of the minimum and maximum positive finite values (TRUE) or a string specifying whether to leave the values unchanged ("no") or to rescale concentration values by dividing by the geometric mean of the minimum and maximum positive finite values ("geomean") or to logistically transform ("odds"). |
odds_max | A number specifying the upper left value when |
reweight | A flag specifying whether to reweight weights by dividing by the largest weight. |
computable | A flag specifying whether to only return fits with numerically computable standard errors. |
at_boundary_ok | A flag specifying whether a model with one or moreparameters at the boundary should be considered to have converged (default = TRUE). |
all_dists | A flag specifying whether all the named distributions must fit successfully. |
min_pmix | A number between 0 and 0.5 specifying the minimum proportion in mixture models. |
range_shape1 | A numeric vector of length two of the lower and upper bounds for the shape1 parameter. |
range_shape2 | shape2 parameter. |
control | A list of control parameters passed to |
silent | A flag indicating whether fits should fail silently. |
Details
By default the 'gamma', 'lgumbel', 'llogis', 'lnorm', 'lnorm_lnorm' and'weibull' distributions are fitted to the data.For a complete list of the distributions that are currently implemented inssdtools seessd_dists_all().
If weight specifies a column in the data frame with positive numbers,weighted estimation occurs.However, currently only the resultant parameter estimates are available.
If theright argument is different to theleft argumentthen the data are considered to be censored.
Value
An object of class fitdists.
See Also
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)fitsssd_plot_cdf(fits)ssd_hc(fits)Goodness of Fit
Description
Returns a tbl data frame with the following columns
- dist
The distribution name (chr)
- aic
Akaike's Information Criterion (dbl)
- bic
Bayesian Information Criterion (dbl)
- at_bound
Parameter(s) at boundary (lgl)
- computable
All parameter have computable standard errors (lgl)
and if the data are non-censored
- aicc
Akaike's Information Criterion corrected for sample size (dbl)
and if there are 8 or more samples
- ad
Anderson-Darling statistic (dbl)
- ks
Kolmogorov-Smirnov statistic (dbl)
- cvm
Cramer-von Mises statistic (dbl)
In the case of an object of class fitdists the function also returns
- delta
The Information Criterion differences (dbl)
- wt
The Information Criterion weights (dbl)
wheredelta andwt are based onaic for censored dataandaicc for non-censored data.
Usage
ssd_gof(x, ...)## S3 method for class 'fitdists'ssd_gof(x, ..., pvalue = FALSE, wt = FALSE)Arguments
x | The object. |
... | Unused. |
pvalue | A flag specifying whether to return p-values or the statistics (default) for the various tests. |
wt | A flag specifying whether to return the Akaike weight as "wt" instead of "weight". |
Value
A tbl data frame of the gof statistics.
Methods (by class)
ssd_gof(fitdists): Goodness of Fit
See Also
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)ssd_gof(fits, wt = TRUE)ssd_gof(fits, pvalue = TRUE, wt = TRUE)Hazard Concentrations for Species Sensitivity Distributions
Description
Calculates concentration(s) with bootstrap confidence intervalsthat protect specified proportion(s) of species forindividual or model-averaged distributionsusing parametric or non-parametric bootstrapping.
Usage
ssd_hc(x, ...)## S3 method for class 'list'ssd_hc(x, percent, proportion = 0.05, ...)## S3 method for class 'fitdists'ssd_hc( x, percent = deprecated(), proportion = 0.05, ..., average = TRUE, ci = FALSE, level = 0.95, nboot = 1000, min_pboot = 0.95, multi_est = deprecated(), est_method = "multi", ci_method = "weighted_samples", parametric = TRUE, delta = 9.21, samples = FALSE, save_to = NULL, control = NULL)## S3 method for class 'fitburrlioz'ssd_hc( x, percent, proportion = 0.05, ..., ci = FALSE, level = 0.95, nboot = 1000, min_pboot = 0.95, parametric = FALSE, samples = FALSE, save_to = NULL)Arguments
x | The object. |
... | Unused. |
percent | A numeric vector of percent values to estimate hazard concentrations for. Deprecated for |
proportion | A numeric vector of proportion values to estimate hazard concentrations for. |
average | A flag specifying whether to provide model averaged values as opposed to a value for each distribution. |
ci | A flag specifying whether to estimate confidence intervals (by bootstrapping). |
level | A number between 0 and 1 of the confidence level of the interval. |
nboot | A count of the number of bootstrap samples to use to estimate the confidence limits. A value of 10,000 is recommended for official guidelines. |
min_pboot | A number between 0 and 1 of the minimumproportion of bootstrap samples that must successfully fit (return a likelihood)to report the confidence intervals. |
multi_est | A flag specifying whether to estimate directly fromthe model-averaged cumulative distribution function ( |
est_method | A string specifying whether to estimate directly fromthe model-averaged cumulative distribution function ( |
ci_method | A string specifying which method to use for estimatingthe standard error and confidence limits from the bootstrap samples.The default and recommended value is still |
parametric | A flag specifying whether to perform parametric bootstrapping as opposed to non-parametrically resampling the original data with replacement. |
delta | A non-negative number specifying the maximum absolute AIC difference cutoff.Distributions with an absolute AIC difference greater than delta are excluded from the calculations. |
samples | A flag specfying whether to include a numeric vector of the bootstrap samples as a list column in the output. |
save_to | NULL or a string specifying a directory to save where the bootstrap datasets and parameter estimates (when successfully converged) to. |
control | A list of control parameters passed to |
Details
Model-averaged estimates and/or confidence intervals (including standard error)can be calculated by treating the distributions asconstituting a single mixture distributionversus 'taking the mean'.When calculating the model averaged estimates treating thedistributions as constituting a single mixture distributionensures thatssd_hc() is the inverse ofssd_hp().
Distributions with an absolute AIC difference greaterthan a delta of by default 7 have considerably less support (wt < 0.01)and are excludedprior to calculation of the hazard concentrations to reduce the run time.
Value
A tibble of corresponding hazard concentrations.
Methods (by class)
ssd_hc(list): Hazard Concentrations for Distributional Estimatesssd_hc(fitdists): Hazard Concentrations for fitdists Objectssd_hc(fitburrlioz): Hazard Concentrations for fitburrlioz Object
References
Burnham, K.P., and Anderson, D.R. 2002. Model Selection and Multimodel Inference. Springer New York, New York, NY. doi:10.1007/b97636.
See Also
predict.fitdists() andssd_hp().
Examples
ssd_hc(ssd_match_moments())fits <- ssd_fit_dists(ssddata::ccme_boron)ssd_hc(fits)fit <- ssd_fit_burrlioz(ssddata::ccme_boron)ssd_hc(fit)BCANZ Hazard Concentrations
Description
Gets hazard concentrations with confidence intervals that protect1, 5, 10 and 20% of species using settings adopted byBC, Canada, Australia and New Zealand for official guidelines.This function can take several minutes to run with recommended 10,000 iterations.
Usage
ssd_hc_bcanz(x, ..., nboot = 10000, min_pboot = 0.95)Arguments
x | The object. |
... | Unused. |
nboot | A count of the number of bootstrap samples to use to estimate the confidence limits. A value of 10,000 is recommended for official guidelines. |
min_pboot | A number between 0 and 1 of the minimumproportion of bootstrap samples that must successfully fit (return a likelihood)to report the confidence intervals. |
Value
A tibble of corresponding hazard concentrations.
See Also
Other BCANZ:ssd_fit_bcanz(),ssd_hp_bcanz()
Examples
fits <- ssd_fit_bcanz(ssddata::ccme_boron)ssd_hc_bcanz(fits, nboot = 100)Hazard Concentrations for Burrlioz Fit
Description
Deprecated forssd_hc().
Usage
ssd_hc_burrlioz( x, percent, proportion = 0.05, ci = FALSE, level = 0.95, nboot = 1000, min_pboot = 0.95, parametric = FALSE)Arguments
x | The object. |
percent | A numeric vector of percent values to estimate hazard concentrations for. Deprecated for |
proportion | A numeric vector of proportion values to estimate hazard concentrations for. |
ci | A flag specifying whether to estimate confidence intervals (by bootstrapping). |
level | A number between 0 and 1 of the confidence level of the interval. |
nboot | A count of the number of bootstrap samples to use to estimate the confidence limits. A value of 10,000 is recommended for official guidelines. |
min_pboot | A number between 0 and 1 of the minimumproportion of bootstrap samples that must successfully fit (return a likelihood)to report the confidence intervals. |
parametric | A flag specifying whether to perform parametric bootstrapping as opposed to non-parametrically resampling the original data with replacement. |
Value
A tibble of corresponding hazard concentrations.
Hazard Proportion
Description
Calculates proportion of species affected at specified concentration(s)with quantile based bootstrap confidence intervals forindividual or model-averaged distributionsusing parametric or non-parametric bootstrapping.For more information see the inverse functionssd_hc().
Usage
ssd_hp(x, ...)## S3 method for class 'fitdists'ssd_hp( x, conc = 1, ..., average = TRUE, ci = FALSE, level = 0.95, nboot = 1000, min_pboot = 0.95, multi_est = deprecated(), est_method = "multi", ci_method = "weighted_samples", parametric = TRUE, delta = 9.21, proportion = FALSE, samples = FALSE, save_to = NULL, control = NULL)## S3 method for class 'fitburrlioz'ssd_hp( x, conc = 1, ..., ci = FALSE, level = 0.95, nboot = 1000, min_pboot = 0.95, parametric = FALSE, proportion = FALSE, samples = FALSE, save_to = NULL)Arguments
x | The object. |
... | Unused. |
conc | A numeric vector of concentrations to calculate the hazard proportions for. |
average | A flag specifying whether to provide model averaged values as opposed to a value for each distribution. |
ci | A flag specifying whether to estimate confidence intervals (by bootstrapping). |
level | A number between 0 and 1 of the confidence level of the interval. |
nboot | A count of the number of bootstrap samples to use to estimate the confidence limits. A value of 10,000 is recommended for official guidelines. |
min_pboot | A number between 0 and 1 of the minimumproportion of bootstrap samples that must successfully fit (return a likelihood)to report the confidence intervals. |
multi_est | A flag specifying whether to estimate directly fromthe model-averaged cumulative distribution function ( |
est_method | A string specifying whether to estimate directly fromthe model-averaged cumulative distribution function ( |
ci_method | A string specifying which method to use for estimatingthe standard error and confidence limits from the bootstrap samples.The default and recommended value is still |
parametric | A flag specifying whether to perform parametric bootstrapping as opposed to non-parametrically resampling the original data with replacement. |
delta | A non-negative number specifying the maximum absolute AIC difference cutoff.Distributions with an absolute AIC difference greater than delta are excluded from the calculations. |
proportion | A flag specifying whether to return hazard proportions( |
samples | A flag specfying whether to include a numeric vector of the bootstrap samples as a list column in the output. |
save_to | NULL or a string specifying a directory to save where the bootstrap datasets and parameter estimates (when successfully converged) to. |
control | A list of control parameters passed to |
Value
A tibble of corresponding hazard proportions.
Methods (by class)
ssd_hp(fitdists): Hazard Proportions for fitdists Objectssd_hp(fitburrlioz): Hazard Proportions for fitburrlioz Object
See Also
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)ssd_hp(fits, conc = 1)fit <- ssd_fit_burrlioz(ssddata::ccme_boron)ssd_hp(fit)BCANZ Hazard Proportion
Description
Gets proportion of species affected at specified concentration(s)using settings adopted by BC, Canada, Australia and New Zealand for official guidelines.This function can take several minutes to run with recommended 10,000 iterations.
Usage
ssd_hp_bcanz( x, conc = 1, ..., nboot = 10000, min_pboot = 0.95, proportion = FALSE)Arguments
x | The object. |
conc | A numeric vector of concentrations to calculate the hazard proportions for. |
... | Unused. |
nboot | A count of the number of bootstrap samples to use to estimate the confidence limits. A value of 10,000 is recommended for official guidelines. |
min_pboot | A number between 0 and 1 of the minimumproportion of bootstrap samples that must successfully fit (return a likelihood)to report the confidence intervals. |
proportion | A numeric vector of proportion values to estimate hazard concentrations for. |
Value
A tibble of corresponding hazard concentrations.
See Also
Other BCANZ:ssd_fit_bcanz(),ssd_hc_bcanz()
Examples
fits <- ssd_fit_bcanz(ssddata::ccme_boron)ssd_hp_bcanz(fits, nboot = 100)Is Censored
Description
Tests if an object has censored data.
Test if a data frame is censored.
Test if a fitdists object is censored.
Usage
ssd_is_censored(x, ...)## S3 method for class 'data.frame'ssd_is_censored(x, left = "Conc", right = left, ...)## S3 method for class 'fitdists'ssd_is_censored(x, ...)Arguments
x | The object. |
... | Unused. |
left | A string of the column in data with the concentrations. |
right | A string of the column in data with the right concentration values. |
Value
A flag indicating whether an object is censored.
Examples
ssd_is_censored(ssddata::ccme_boron)ssd_is_censored(data.frame(Conc = 1, right = 2), right = "right")fits <- ssd_fit_dists(ssddata::ccme_boron)ssd_is_censored(fits)Label numbers with significant digits and comma
Description
Label numbers with significant digits and comma
Usage
ssd_label_comma( digits = 3, ..., big.mark = ",", decimal.mark = getOption("OutDec", "."))Arguments
digits | A whole number specifying the number of significant figures. |
... | Unused. |
big.mark | A string specifying the thousands separator. |
decimal.mark | A string specifying the numeric decimal point. |
Value
A "labelling" function that takes a vector x andreturns a character vector oflength(x) giving a label for each input value.
See Also
Examples
ggplot2::ggplot(data = ssddata::anon_e, ggplot2::aes(x = Conc / 10)) + geom_ssdpoint() + ggplot2::scale_x_log10(labels = ssd_label_comma())Label numbers with significant digits and comma.Ifhc_value is present in breaks, put on new line and make bold.
Description
Label numbers with significant digits and comma.Ifhc_value is present in breaks, put on new line and make bold.
Usage
ssd_label_comma_hc( hc_value, digits = 3, ..., big.mark = ",", decimal.mark = getOption("OutDec", "."))Arguments
hc_value | A number of the hazard concentration value to offset. |
digits | A whole number specifying the number of significant figures. |
... | Unused. |
big.mark | A string specifying the thousands separator. |
decimal.mark | A string specifying the numeric decimal point. |
Value
A "labelling" function that takes a vector x andreturns a character vector oflength(x) giving a label for each input value.
See Also
Examples
ggplot2::ggplot(data = ssddata::anon_e, ggplot2::aes(x = Conc / 10)) + geom_ssdpoint() + ggplot2::scale_x_log10(labels = ssd_label_comma_hc(1.26))Licensing Markdown
Description
A string of markdown code indicating the licensing of the codeand documentation
Usage
ssd_licensing_md()Examples
ssd_licensing_md()Match Moments
Description
Gets a named list of the values that producethe moment values (meanlog and sdlog) by distribution and term.
Usage
ssd_match_moments( dists = ssd_dists_bcanz(), meanlog = 1, sdlog = 1, ..., nsim = 1e+05)Arguments
dists | A character vector of the distribution names. |
meanlog | The mean on the log scale. |
sdlog | The standard deviation on the log scale. |
... | Unused. |
nsim | A positive whole number of the number of simulations to generate. |
Value
a named list of the values that produce the moment values by distribution and term.
See Also
estimates.fitdists(),ssd_hc() andssd_plot_cdf()
Examples
moments <- ssd_match_moments()print(moments)ssd_hc(moments)ssd_plot_cdf(moments)Calculate Minimum Proportion in Mixture Models
Description
Calculate Minimum Proportion in Mixture Models
Usage
ssd_min_pmix(n)Arguments
n | positive number of observations. |
Value
A number between 0 and 0.5 of the minimum proportion in mixture models.
See Also
Examples
ssd_min_pmix(6)ssd_min_pmix(50)Color-blind Palette for SSD Plots
Description
Color-blind Palette for SSD Plots
Usage
ssd_pal()Value
A character vector of a color blind palette with 8 colors.
See Also
Other ggplot:geom_hcintersect(),geom_ssdpoint(),geom_ssdsegment(),geom_xribbon(),scale_colour_ssd()
Examples
ssd_pal()Cumulative Distribution Function
Description
Cumulative Distribution Function
Usage
ssd_pburrIII3( q, shape1 = 1, shape2 = 1, scale = 1, lower.tail = TRUE, log.p = FALSE)ssd_pgamma(q, shape = 1, scale = 1, lower.tail = TRUE, log.p = FALSE)ssd_pgompertz(q, location = 1, shape = 1, lower.tail = TRUE, log.p = FALSE)ssd_pinvpareto(q, shape = 3, scale = 1, lower.tail = TRUE, log.p = FALSE)ssd_plgumbel( q, locationlog = 0, scalelog = 1, lower.tail = TRUE, log.p = FALSE)ssd_pllogis_llogis( q, locationlog1 = 0, scalelog1 = 1, locationlog2 = 1, scalelog2 = 1, pmix = 0.5, lower.tail = TRUE, log.p = FALSE)ssd_pllogis(q, locationlog = 0, scalelog = 1, lower.tail = TRUE, log.p = FALSE)ssd_plnorm_lnorm( q, meanlog1 = 0, sdlog1 = 1, meanlog2 = 1, sdlog2 = 1, pmix = 0.5, lower.tail = TRUE, log.p = FALSE)ssd_plnorm(q, meanlog = 0, sdlog = 1, lower.tail = TRUE, log.p = FALSE)ssd_pmulti( q, burrIII3.weight = 0, burrIII3.shape1 = 1, burrIII3.shape2 = 1, burrIII3.scale = 1, gamma.weight = 0, gamma.shape = 1, gamma.scale = 1, gompertz.weight = 0, gompertz.location = 1, gompertz.shape = 1, lgumbel.weight = 0, lgumbel.locationlog = 0, lgumbel.scalelog = 1, llogis.weight = 0, llogis.locationlog = 0, llogis.scalelog = 1, llogis_llogis.weight = 0, llogis_llogis.locationlog1 = 0, llogis_llogis.scalelog1 = 1, llogis_llogis.locationlog2 = 1, llogis_llogis.scalelog2 = 1, llogis_llogis.pmix = 0.5, lnorm.weight = 0, lnorm.meanlog = 0, lnorm.sdlog = 1, lnorm_lnorm.weight = 0, lnorm_lnorm.meanlog1 = 0, lnorm_lnorm.sdlog1 = 1, lnorm_lnorm.meanlog2 = 1, lnorm_lnorm.sdlog2 = 1, lnorm_lnorm.pmix = 0.5, weibull.weight = 0, weibull.shape = 1, weibull.scale = 1, lower.tail = TRUE, log.p = FALSE)ssd_pmulti_fitdists(q, fitdists, lower.tail = TRUE, log.p = FALSE)ssd_pweibull(q, shape = 1, scale = 1, lower.tail = TRUE, log.p = FALSE)Arguments
q | vector of quantiles. |
shape1 | shape1 parameter. |
shape2 | shape2 parameter. |
scale | scale parameter. |
lower.tail | logical; if TRUE (default), probabilities are |
log.p | logical; if TRUE, probabilities p are given as log(p). |
shape | shape parameter. |
location | location parameter. |
locationlog | location on the log scale parameter. |
scalelog | scale on log scale parameter. |
locationlog1 | locationlog1 parameter. |
scalelog1 | scalelog1 parameter. |
locationlog2 | locationlog2 parameter. |
scalelog2 | scalelog2 parameter. |
pmix | Proportion mixture parameter. |
meanlog1 | mean on log scale parameter. |
sdlog1 | standard deviation on log scale parameter. |
meanlog2 | mean on log scale parameter. |
sdlog2 | standard deviation on log scale parameter. |
meanlog | mean on log scale parameter. |
sdlog | standard deviation on log scale parameter. |
burrIII3.weight | weight parameter for the Burr III distribution. |
burrIII3.shape1 | shape1 parameter for the Burr III distribution. |
burrIII3.shape2 | shape2 parameter for the Burr III distribution. |
burrIII3.scale | scale parameter for the Burr III distribution. |
gamma.weight | weight parameter for the gamma distribution. |
gamma.shape | shape parameter for the gamma distribution. |
gamma.scale | scale parameter for the gamma distribution. |
gompertz.weight | weight parameter for the Gompertz distribution. |
gompertz.location | location parameter for the Gompertz distribution. |
gompertz.shape | shape parameter for the Gompertz distribution. |
lgumbel.weight | weight parameter for the log-Gumbel distribution. |
lgumbel.locationlog | location parameter for the log-Gumbel distribution. |
lgumbel.scalelog | scale parameter for the log-Gumbel distribution. |
llogis.weight | weight parameter for the log-logistic distribution. |
llogis.locationlog | location parameter for the log-logistic distribution. |
llogis.scalelog | scale parameter for the log-logistic distribution. |
llogis_llogis.weight | weight parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.locationlog1 | locationlog1 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.scalelog1 | scalelog1 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.locationlog2 | locationlog2 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.scalelog2 | scalelog2 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.pmix | pmix parameter for the log-logistic log-logistic mixture distribution. |
lnorm.weight | weight parameter for the log-normal distribution. |
lnorm.meanlog | meanlog parameter for the log-normal distribution. |
lnorm.sdlog | sdlog parameter for the log-normal distribution. |
lnorm_lnorm.weight | weight parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.meanlog1 | meanlog1 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.sdlog1 | sdlog1 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.meanlog2 | meanlog2 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.sdlog2 | sdlog2 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.pmix | pmix parameter for the log-normal log-normal mixture distribution. |
weibull.weight | weight parameter for the Weibull distribution. |
weibull.shape | shape parameter for the Weibull distribution. |
weibull.scale | scale parameter for the Weibull distribution. |
fitdists | An object of class fitdists. |
Functions
ssd_pburrIII3(): Cumulative Distribution Function for BurrIII Distributionssd_pgamma(): Cumulative Distribution Function for Gamma Distributionssd_pgompertz(): Cumulative Distribution Function for Gompertz Distributionssd_pinvpareto(): Cumulative Distribution Function for Inverse Pareto Distributionssd_plgumbel(): Cumulative Distribution Function for Log-Gumbel Distributionssd_pllogis_llogis(): Cumulative Distribution Function for Log-Logistic/Log-Logistic Mixture Distributionssd_pllogis(): Cumulative Distribution Function for Log-Logistic Distributionssd_plnorm_lnorm(): Cumulative Distribution Function for Log-Normal/Log-Normal Mixture Distributionssd_plnorm(): Cumulative Distribution Function for Log-Normal Distributionssd_pmulti(): Cumulative Distribution Function for Multiple Distributionsssd_pmulti_fitdists(): Cumulative Distribution Function for Multiple Distributionsssd_pweibull(): Cumulative Distribution Function for Weibull Distribution
See Also
Examples
ssd_pburrIII3(1)ssd_pgamma(1)ssd_pgompertz(1)ssd_pinvpareto(1)ssd_plgumbel(1)ssd_pllogis_llogis(1)ssd_pllogis(1)ssd_plnorm_lnorm(1)ssd_plnorm(1)# multissd_pmulti(1, gamma.weight = 0.5, lnorm.weight = 0.5)# multi fitdistsfit <- ssd_fit_dists(ssddata::ccme_boron)ssd_pmulti_fitdists(1, fit)ssd_pweibull(1)Plot Species Sensitivity Data and Distributions
Description
Plots species sensitivity data and distributions.
Usage
ssd_plot( data, pred, left = "Conc", right = left, ..., label = NULL, shape = NULL, color = NULL, size, linetype = NULL, linecolor = NULL, xlab = "Concentration", ylab = "Species Affected", ci = TRUE, ribbon = TRUE, hc = 0.05, shift_x = 3, add_x = 0, bounds = c(left = 1, right = 1), big.mark = ",", decimal.mark = getOption("OutDec", "."), suffix = "%", trans = "log10", xbreaks = waiver(), xlimits = NULL, text_size = 11, label_size = 2.5, theme_classic = FALSE)Arguments
data | A data frame. |
pred | A data frame of the predictions. |
left | A string of the column in data with the concentrations. |
right | A string of the column in data with the right concentration values. |
... | Unused. |
label | A string of the column in data with the labels. |
shape | A string of the column in data for the shape aesthetic. |
color | A string of the column in data for the color aesthetic. |
size | A number for the size of the labels. Deprecated for |
linetype | A string of the column in pred to use for the linetype. |
linecolor | A string of the column in pred to use for the line color. |
xlab | A string of the x-axis label. |
ylab | A string of the x-axis label. |
ci | A flag specifying whether to estimate confidence intervals (by bootstrapping). |
ribbon | A flag indicating whether to plot the confidence interval as a grey ribbon as opposed to green solid lines. |
hc | A value between 0 and 1 indicating the proportion hazard concentration (or NULL). |
shift_x | The value to multiply the label x values by (after adding |
add_x | The value to add to the label x values (before multiplying by |
bounds | A named non-negative numeric vector of the left and right bounds foruncensored missing (0 and Inf) data in terms of the orders of magnituderelative to the extremes for non-missing values. |
big.mark | A string specifying the thousands separator. |
decimal.mark | A string specifying the numeric decimal point. |
suffix | Additional text to display after the number on the y-axis. |
trans | A string of which transformation to use. Accepted values include |
xbreaks | The x-axis breaks as one of:
|
xlimits | The x-axis limits as one of:
|
text_size | A number for the text size. |
label_size | A number for the size of the labels. |
theme_classic | A flag specifying whether to use the classic theme or the default. |
See Also
ssd_plot_cdf() andgeom_ssdpoint()
Examples
ssd_plot(ssddata::ccme_boron, boron_pred, label = "Species", shape = "Group")Plot Cumulative Distribution Function (CDF)
Description
Generic function to plots the cumulative distribution function (CDF).
Usage
ssd_plot_cdf(x, ...)## S3 method for class 'fitdists'ssd_plot_cdf(x, average = FALSE, delta = 9.21, ...)## S3 method for class 'list'ssd_plot_cdf(x, ...)Arguments
x | The object. |
... | Additional arguments passed to |
average | A flag specifying whether to provide model averaged values as opposed to a value for each distribution or if NA provides model averaged and individual values. |
delta | A non-negative number specifying the maximum absolute AIC difference cutoff.Distributions with an absolute AIC difference greater than delta are excluded from the calculations. |
Methods (by class)
ssd_plot_cdf(fitdists): Plot CDF for fitdists objectssd_plot_cdf(list): Plot CDF for named list of distributional parameter values
See Also
estimates.fitdists() andssd_match_moments()
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)ssd_plot_cdf(fits)ssd_plot_cdf(fits, average = NA)ssd_plot_cdf(list( llogis = c(locationlog = 2, scalelog = 1), lnorm = c(meanlog = 2, sdlog = 2)))Cullen and Frey Plot
Description
Plots a Cullen and Frey graph of the skewness and kurtosisfor non-censored data.
Usage
ssd_plot_cf(data, left = "Conc")Arguments
data | A data frame. |
left | A string of the column in data with the concentrations. |
Details
Deprecated forfitdistrplus::descdist().
Plot Species Sensitivity Data
Description
Plots species sensitivity data.
Usage
ssd_plot_data( data, left = "Conc", right = left, ..., label = NULL, shape = NULL, color = NULL, size = 2.5, xlab = "Concentration", ylab = "Species Affected", shift_x = 3, add_x = 0, big.mark = ",", decimal.mark = getOption("OutDec", "."), suffix = "%", bounds = c(left = 1, right = 1), trans = "log10", xbreaks = waiver())Arguments
data | A data frame. |
left | A string of the column in data with the concentrations. |
right | A string of the column in data with the right concentration values. |
... | Unused. |
label | A string of the column in data with the labels. |
shape | A string of the column in data for the shape aesthetic. |
color | A string of the column in data for the color aesthetic. |
size | A number for the size of the labels. Deprecated for |
xlab | A string of the x-axis label. |
ylab | A string of the x-axis label. |
shift_x | The value to multiply the label x values by (after adding |
add_x | The value to add to the label x values (before multiplying by |
big.mark | A string specifying the thousands separator. |
decimal.mark | A string specifying the numeric decimal point. |
suffix | Additional text to display after the number on the y-axis. |
bounds | A named non-negative numeric vector of the left and right bounds foruncensored missing (0 and Inf) data in terms of the orders of magnituderelative to the extremes for non-missing values. |
trans | A string of which transformation to use. Accepted values include |
xbreaks | The x-axis breaks as one of:
|
See Also
Examples
ssd_plot_data(ssddata::ccme_boron, label = "Species", shape = "Group")Quantile Function
Description
Quantile Function
Usage
ssd_qburrIII3( p, shape1 = 1, shape2 = 1, scale = 1, lower.tail = TRUE, log.p = FALSE)ssd_qgamma(p, shape = 1, scale = 1, lower.tail = TRUE, log.p = FALSE)ssd_qgompertz(p, location = 1, shape = 1, lower.tail = TRUE, log.p = FALSE)ssd_qinvpareto(p, shape = 3, scale = 1, lower.tail = TRUE, log.p = FALSE)ssd_qlgumbel( p, locationlog = 0, scalelog = 1, lower.tail = TRUE, log.p = FALSE)ssd_qllogis_llogis( p, locationlog1 = 0, scalelog1 = 1, locationlog2 = 1, scalelog2 = 1, pmix = 0.5, lower.tail = TRUE, log.p = FALSE)ssd_qllogis(p, locationlog = 0, scalelog = 1, lower.tail = TRUE, log.p = FALSE)ssd_qlnorm_lnorm( p, meanlog1 = 0, sdlog1 = 1, meanlog2 = 1, sdlog2 = 1, pmix = 0.5, lower.tail = TRUE, log.p = FALSE)ssd_qlnorm(p, meanlog = 0, sdlog = 1, lower.tail = TRUE, log.p = FALSE)ssd_qmulti( p, burrIII3.weight = 0, burrIII3.shape1 = 1, burrIII3.shape2 = 1, burrIII3.scale = 1, gamma.weight = 0, gamma.shape = 1, gamma.scale = 1, gompertz.weight = 0, gompertz.location = 1, gompertz.shape = 1, lgumbel.weight = 0, lgumbel.locationlog = 0, lgumbel.scalelog = 1, llogis.weight = 0, llogis.locationlog = 0, llogis.scalelog = 1, llogis_llogis.weight = 0, llogis_llogis.locationlog1 = 0, llogis_llogis.scalelog1 = 1, llogis_llogis.locationlog2 = 1, llogis_llogis.scalelog2 = 1, llogis_llogis.pmix = 0.5, lnorm.weight = 0, lnorm.meanlog = 0, lnorm.sdlog = 1, lnorm_lnorm.weight = 0, lnorm_lnorm.meanlog1 = 0, lnorm_lnorm.sdlog1 = 1, lnorm_lnorm.meanlog2 = 1, lnorm_lnorm.sdlog2 = 1, lnorm_lnorm.pmix = 0.5, weibull.weight = 0, weibull.shape = 1, weibull.scale = 1, lower.tail = TRUE, log.p = FALSE)ssd_qmulti_fitdists(p, fitdists, lower.tail = TRUE, log.p = FALSE)ssd_qweibull(p, shape = 1, scale = 1, lower.tail = TRUE, log.p = FALSE)Arguments
p | vector of probabilities. |
shape1 | shape1 parameter. |
shape2 | shape2 parameter. |
scale | scale parameter. |
lower.tail | logical; if TRUE (default), probabilities are |
log.p | logical; if TRUE, probabilities p are given as log(p). |
shape | shape parameter. |
location | location parameter. |
locationlog | location on the log scale parameter. |
scalelog | scale on log scale parameter. |
locationlog1 | locationlog1 parameter. |
scalelog1 | scalelog1 parameter. |
locationlog2 | locationlog2 parameter. |
scalelog2 | scalelog2 parameter. |
pmix | Proportion mixture parameter. |
meanlog1 | mean on log scale parameter. |
sdlog1 | standard deviation on log scale parameter. |
meanlog2 | mean on log scale parameter. |
sdlog2 | standard deviation on log scale parameter. |
meanlog | mean on log scale parameter. |
sdlog | standard deviation on log scale parameter. |
burrIII3.weight | weight parameter for the Burr III distribution. |
burrIII3.shape1 | shape1 parameter for the Burr III distribution. |
burrIII3.shape2 | shape2 parameter for the Burr III distribution. |
burrIII3.scale | scale parameter for the Burr III distribution. |
gamma.weight | weight parameter for the gamma distribution. |
gamma.shape | shape parameter for the gamma distribution. |
gamma.scale | scale parameter for the gamma distribution. |
gompertz.weight | weight parameter for the Gompertz distribution. |
gompertz.location | location parameter for the Gompertz distribution. |
gompertz.shape | shape parameter for the Gompertz distribution. |
lgumbel.weight | weight parameter for the log-Gumbel distribution. |
lgumbel.locationlog | location parameter for the log-Gumbel distribution. |
lgumbel.scalelog | scale parameter for the log-Gumbel distribution. |
llogis.weight | weight parameter for the log-logistic distribution. |
llogis.locationlog | location parameter for the log-logistic distribution. |
llogis.scalelog | scale parameter for the log-logistic distribution. |
llogis_llogis.weight | weight parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.locationlog1 | locationlog1 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.scalelog1 | scalelog1 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.locationlog2 | locationlog2 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.scalelog2 | scalelog2 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.pmix | pmix parameter for the log-logistic log-logistic mixture distribution. |
lnorm.weight | weight parameter for the log-normal distribution. |
lnorm.meanlog | meanlog parameter for the log-normal distribution. |
lnorm.sdlog | sdlog parameter for the log-normal distribution. |
lnorm_lnorm.weight | weight parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.meanlog1 | meanlog1 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.sdlog1 | sdlog1 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.meanlog2 | meanlog2 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.sdlog2 | sdlog2 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.pmix | pmix parameter for the log-normal log-normal mixture distribution. |
weibull.weight | weight parameter for the Weibull distribution. |
weibull.shape | shape parameter for the Weibull distribution. |
weibull.scale | scale parameter for the Weibull distribution. |
fitdists | An object of class fitdists. |
Functions
ssd_qburrIII3(): Quantile Function for BurrIII Distributionssd_qgamma(): Quantile Function for Gamma Distributionssd_qgompertz(): Quantile Function for Gompertz Distributionssd_qinvpareto(): Quantile Function for Inverse Pareto Distributionssd_qlgumbel(): Quantile Function for Log-Gumbel Distributionssd_qllogis_llogis(): Cumulative Distribution Function for Log-Logistic/Log-Logistic Mixture Distributionssd_qllogis(): Cumulative Distribution Function for Log-Logistic Distributionssd_qlnorm_lnorm(): Cumulative Distribution Function for Log-Normal/Log-Normal Mixture Distributionssd_qlnorm(): Cumulative Distribution Function for Log-Normal Distributionssd_qmulti(): Quantile Function for Multiple Distributionsssd_qmulti_fitdists(): Quantile Function for Multiple Distributionsssd_qweibull(): Cumulative Distribution Function for Weibull Distribution
See Also
Examples
ssd_qburrIII3(0.5)ssd_qgamma(0.5)ssd_qgompertz(0.5)ssd_qinvpareto(0.5)ssd_qlgumbel(0.5)ssd_qllogis_llogis(0.5)ssd_qllogis(0.5)ssd_qlnorm_lnorm(0.5)ssd_qlnorm(0.5)# multissd_qmulti(0.5, gamma.weight = 0.5, lnorm.weight = 0.5)# multi fitdistsfit <- ssd_fit_dists(ssddata::ccme_boron)ssd_qmulti_fitdists(0.5, fit)ssd_qweibull(0.5)Random Number Generation
Description
Random Number Generation
Usage
ssd_rburrIII3(n, shape1 = 1, shape2 = 1, scale = 1, chk = TRUE)ssd_rgamma(n, shape = 1, scale = 1, chk = TRUE)ssd_rgompertz(n, location = 1, shape = 1, chk = TRUE)ssd_rinvpareto(n, shape = 3, scale = 1, chk = TRUE)ssd_rlgumbel(n, locationlog = 0, scalelog = 1, chk = TRUE)ssd_rllogis_llogis( n, locationlog1 = 0, scalelog1 = 1, locationlog2 = 1, scalelog2 = 1, pmix = 0.5, chk = TRUE)ssd_rllogis(n, locationlog = 0, scalelog = 1, chk = TRUE)ssd_rlnorm_lnorm( n, meanlog1 = 0, sdlog1 = 1, meanlog2 = 1, sdlog2 = 1, pmix = 0.5, chk = TRUE)ssd_rlnorm(n, meanlog = 0, sdlog = 1, chk = TRUE)ssd_rmulti( n, burrIII3.weight = 0, burrIII3.shape1 = 1, burrIII3.shape2 = 1, burrIII3.scale = 1, gamma.weight = 0, gamma.shape = 1, gamma.scale = 1, gompertz.weight = 0, gompertz.location = 1, gompertz.shape = 1, lgumbel.weight = 0, lgumbel.locationlog = 0, lgumbel.scalelog = 1, llogis.weight = 0, llogis.locationlog = 0, llogis.scalelog = 1, llogis_llogis.weight = 0, llogis_llogis.locationlog1 = 0, llogis_llogis.scalelog1 = 1, llogis_llogis.locationlog2 = 1, llogis_llogis.scalelog2 = 1, llogis_llogis.pmix = 0.5, lnorm.weight = 0, lnorm.meanlog = 0, lnorm.sdlog = 1, lnorm_lnorm.weight = 0, lnorm_lnorm.meanlog1 = 0, lnorm_lnorm.sdlog1 = 1, lnorm_lnorm.meanlog2 = 1, lnorm_lnorm.sdlog2 = 1, lnorm_lnorm.pmix = 0.5, weibull.weight = 0, weibull.shape = 1, weibull.scale = 1, chk = TRUE)ssd_rmulti_fitdists(n, fitdists, chk = TRUE)ssd_rweibull(n, shape = 1, scale = 1, chk = TRUE)Arguments
n | positive number of observations. |
shape1 | shape1 parameter. |
shape2 | shape2 parameter. |
scale | scale parameter. |
chk | A flag specifying whether to check the arguments. |
shape | shape parameter. |
location | location parameter. |
locationlog | location on the log scale parameter. |
scalelog | scale on log scale parameter. |
locationlog1 | locationlog1 parameter. |
scalelog1 | scalelog1 parameter. |
locationlog2 | locationlog2 parameter. |
scalelog2 | scalelog2 parameter. |
pmix | Proportion mixture parameter. |
meanlog1 | mean on log scale parameter. |
sdlog1 | standard deviation on log scale parameter. |
meanlog2 | mean on log scale parameter. |
sdlog2 | standard deviation on log scale parameter. |
meanlog | mean on log scale parameter. |
sdlog | standard deviation on log scale parameter. |
burrIII3.weight | weight parameter for the Burr III distribution. |
burrIII3.shape1 | shape1 parameter for the Burr III distribution. |
burrIII3.shape2 | shape2 parameter for the Burr III distribution. |
burrIII3.scale | scale parameter for the Burr III distribution. |
gamma.weight | weight parameter for the gamma distribution. |
gamma.shape | shape parameter for the gamma distribution. |
gamma.scale | scale parameter for the gamma distribution. |
gompertz.weight | weight parameter for the Gompertz distribution. |
gompertz.location | location parameter for the Gompertz distribution. |
gompertz.shape | shape parameter for the Gompertz distribution. |
lgumbel.weight | weight parameter for the log-Gumbel distribution. |
lgumbel.locationlog | location parameter for the log-Gumbel distribution. |
lgumbel.scalelog | scale parameter for the log-Gumbel distribution. |
llogis.weight | weight parameter for the log-logistic distribution. |
llogis.locationlog | location parameter for the log-logistic distribution. |
llogis.scalelog | scale parameter for the log-logistic distribution. |
llogis_llogis.weight | weight parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.locationlog1 | locationlog1 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.scalelog1 | scalelog1 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.locationlog2 | locationlog2 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.scalelog2 | scalelog2 parameter for the log-logistic log-logistic mixture distribution. |
llogis_llogis.pmix | pmix parameter for the log-logistic log-logistic mixture distribution. |
lnorm.weight | weight parameter for the log-normal distribution. |
lnorm.meanlog | meanlog parameter for the log-normal distribution. |
lnorm.sdlog | sdlog parameter for the log-normal distribution. |
lnorm_lnorm.weight | weight parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.meanlog1 | meanlog1 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.sdlog1 | sdlog1 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.meanlog2 | meanlog2 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.sdlog2 | sdlog2 parameter for the log-normal log-normal mixture distribution. |
lnorm_lnorm.pmix | pmix parameter for the log-normal log-normal mixture distribution. |
weibull.weight | weight parameter for the Weibull distribution. |
weibull.shape | shape parameter for the Weibull distribution. |
weibull.scale | scale parameter for the Weibull distribution. |
fitdists | An object of class fitdists. |
Functions
ssd_rburrIII3(): Random Generation for BurrIII Distributionssd_rgamma(): Random Generation for Gamma Distributionssd_rgompertz(): Random Generation for Gompertz Distributionssd_rinvpareto(): Random Generation for Inverse Pareto Distributionssd_rlgumbel(): Random Generation for log-Gumbel Distributionssd_rllogis_llogis(): Random Generation for Log-Logistic/Log-Logistic Mixture Distributionssd_rllogis(): Random Generation for Log-Logistic Distributionssd_rlnorm_lnorm(): Random Generation for Log-Normal/Log-Normal Mixture Distributionssd_rlnorm(): Random Generation for Log-Normal Distributionssd_rmulti(): Random Generation for Multiple Distributionsssd_rmulti_fitdists(): Random Generation for Multiple Distributionsssd_rweibull(): Random Generation for Weibull Distribution
See Also
Examples
withr::with_seed(50, { x <- ssd_rburrIII3(10000)})hist(x, breaks = 1000)withr::with_seed(50, { x <- ssd_rgamma(10000)})hist(x, breaks = 1000)withr::with_seed(50, { x <- ssd_rgompertz(10000)})hist(x, breaks = 1000)withr::with_seed(50, { x <- ssd_rinvpareto(10000)})hist(x, breaks = 1000)withr::with_seed(50, { x <- ssd_rlgumbel(10000)})hist(x, breaks = 1000)withr::with_seed(50, { x <- ssd_rllogis_llogis(10000)})hist(x, breaks = 1000)withr::with_seed(50, { x <- ssd_rllogis(10000)})hist(x, breaks = 1000)withr::with_seed(50, { x <- ssd_rlnorm_lnorm(10000)})hist(x, breaks = 1000)withr::with_seed(50, { x <- ssd_rlnorm(10000)})hist(x, breaks = 1000)withr::with_seed(50, { x <- ssd_rmulti(1000, gamma.weight = 0.5, lnorm.weight = 0.5)})hist(x, breaks = 100)# multi fitdistsfit <- ssd_fit_dists(ssddata::ccme_boron)ssd_rmulti_fitdists(2, fit)withr::with_seed(50, { x <- ssd_rweibull(10000)})hist(x, breaks = 1000)Sort Species Sensitivity Data
Description
Sorts Species Sensitivity Data by empirical cumulative density (ECD).
Usage
ssd_sort_data(data, left = "Conc", right = left)Arguments
data | A data frame. |
left | A string of the column in data with the concentrations. |
right | A string of the column in data with the right concentration values. |
Details
Useful for sorting data before usinggeom_ssdpoint() andgeom_ssdsegment()to construct plots for censored data withstat = identity toensure order is the same for the various components.
Value
data sorted by the empirical cumulative density.
See Also
Examples
ssd_sort_data(ssddata::ccme_boron)Water Quality Guideline for British Columbia
Description
Calculates the 5% Hazard Concentration usingssd_fit_bcanz()andssd_hc().
Usage
ssd_wqg_bc(data, left = "Conc")Arguments
data | A data frame. |
left | A string of the column in data with the concentrations. |
Value
A tibble of the 5% hazard concentration with 95% confidence intervals.
See Also
Other wqg:ssd_wqg_burrlioz()
Examples
## Not run: ssd_wqg_bc(ssddata::ccme_boron)## End(Not run)Water Quality Guideline for Burrlioz
Description
Calculates the 5% Hazard Concentration usingssd_fit_burrlioz()andssd_hc().
Usage
ssd_wqg_burrlioz(data, left = "Conc")Arguments
data | A data frame. |
left | A string of the column in data with the concentrations. |
Value
A tibble of the 5% hazard concentration with 95% confidence intervals.
See Also
ssd_fit_burrlioz() andssd_hc()
Other wqg:ssd_wqg_bc()
Examples
## Not run: ssd_wqg_burrlioz(ssddata::ccme_boron)## End(Not run)ggproto Classes for Plotting Species Sensitivity Data and Distributions
Description
ggproto Classes for Plotting Species Sensitivity Data and Distributions
Usage
StatSsdpointStatSsdsegmentGeomSsdpointGeomSsdsegmentGeomHcintersectGeomXribbonFormat
An object of classStatSsdpoint (inherits fromStat,ggproto,gg) of length 4.
An object of classStatSsdsegment (inherits fromStat,ggproto,gg) of length 4.
An object of classGeomSsdpoint (inherits fromGeomPoint,Geom,ggproto,gg) of length 1.
An object of classGeomSsdsegment (inherits fromGeomSegment,Geom,ggproto,gg) of length 1.
An object of classGeomHcintersect (inherits fromGeom,ggproto,gg) of length 5.
An object of classGeomXribbon (inherits fromGeom,ggproto,gg) of length 6.
See Also
ggplot2::ggproto() andssd_plot_cdf()
Plot Species Sensitivity Data
Description
Uses the empirical cumulative density/distribution to visualize species sensitivity data.
Usage
stat_ssd( mapping = NULL, data = NULL, geom = "point", position = "identity", ..., na.rm = FALSE, show.legend = NA, inherit.aes = TRUE)Arguments
mapping | Set of aesthetic mappings created by |
data | The data to be displayed in this layer. There are threeoptions: If A A |
geom | The geometric object to use to display the data for this layer.When using a
|
position | A position adjustment to use on the data for this layer. Thiscan be used in various ways, including to prevent overplotting andimproving the display. The
|
... | Other arguments passed on to
|
na.rm | If |
show.legend | logical. Should this layer be included in the legends? |
inherit.aes | If |
See Also
Subset fitdists Object
Description
Select a subset of distributions from a fitdists object.The Akaike Information-theoretic Criterion differences are calculated afterselecting the distributions named in select.
Usage
## S3 method for class 'fitdists'subset(x, select = names(x), ..., delta = Inf, strict = TRUE)Arguments
x | The object. |
select | A character vector of the distributions to select. |
... | Unused. |
delta | A non-negative number specifying the maximum absolute AIC difference cutoff.Distributions with an absolute AIC difference greater than delta are excluded from the calculations. |
strict | A flag indicating whether all elements of select must be present. |
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)subset(fits, c("gamma", "lnorm"))Turn a fitdists Object into a Tibble
Description
Turns a fitdists object into a tidy tibble of theestimates (est) and standard errors (se) by theterms (term) and distributions (dist).
Usage
## S3 method for class 'fitdists'tidy(x, all = FALSE, ...)Arguments
x | The object. |
all | A flag specifying whether to also return transformed parameters. |
... | Unused. |
Value
A tidy tibble of the estimates and standard errors.
See Also
Other generics:augment.fitdists(),glance.fitdists()
Examples
fits <- ssd_fit_dists(ssddata::ccme_boron)tidy(fits)tidy(fits, all = TRUE)