Movatterモバイル変換

an object of class 'mirtCAT_design' returned from themirtCAT functionwhen passingdesign_elements = TRUE

item selection criteria (seemirtCAT'scriteria input)

(required whenx is missing) internal person object. To be used whencustomNextItem function has been defined

(required whenx is missing) internal test object. To be used whencustomNextItem function has been defined

(required whenx is missing) internal design object. To be used whencustomNextItem function has been defined

an integer vector indicating which items should be included in the optimal search;the defaultNULL includes all possible items. To allow only the first 10 items to be selected from this can be modified tosubset = 1:10. This is useful when administering a multi-unidimensional CAT session where unidimensional blocks should be clustered together for smoother presentation. Useful when using thecustomNextItem function inmirtCAT

logical; if more than one trait is present in the test, should the respective informationmatricies be returned instead of the scalar summary statistics (e.g., D-rule). When TRUE will return a list of matricies associated with each respective item

number of upper/lower characters to sample

logical; include the current date/time the function was calledin the string as well? This further helps with the uniqueness of the generatedstring

a shiny UI function used to define the interface. IfNULL, the default one will be used. SeemirtCAT:::default_UI for the internal code

logical; iscreateShinyGUI() being used on a remote server or executed locally?WhenTRUE any calls tostopApp are suppressed to allow for multiple sessions tobe executed. Note thatFALSE gives the same behaviour as the GUI inmirtCAT

either theperson,design, ortest object defined through acustomNextItem definition

a character vector extracting the desired element (see the Details section)

an object of class 'mirtCAT_design' returned from themirtCAT functionwhen passingdesign_elements = TRUE

(required whenx is missing) internal person object. To beused whencustomNextItem function has been defined

(required whenx is missing) internal test object. To beused whencustomNextItem function has been defined

(required whenx is missing) internal design object. To beused whencustomNextItem function has been defined

item selection criteria (seemirtCAT'scriteria input).If not specified the value fromextract.mirtCAT(design, 'criteria') will be used

a vector of values used as the optimization criteria to be passed tolp(objective.in). This is typically the vector of criteria values returned fromcomputeCriteria, however supplying othercriteria are possible (e.g., to minimize the number of items administered simply pass a vectorof -1's)

an integer vector indicating which items should be included in the optimal search;the defaultNULL includes all possible items. To allow only the first 10 items to beselected from this can be modified tosubset = 1:10. This is useful when administeringa multi-unidimensional CAT session where unidimensional blocks should be clustered togetherfor smoother presentation. Useful when using thecustomNextItem function inmirtCAT

logical; return all items instead of just the most optimal?WhenTRUE a vector of items is returned instead of the most optimal,where the items are sorted according to howwell they fit the criteria (e.g., the first element is the most optimal, followed by the secondmost optimal, and so on). Note that this does not work for some selection criteria (e.g.,'seq' or 'random')

additional arguments to be passed tolp

a matrix or data.frame of parameters corresponding to the model definitionslisted inmirt. Each row represents a unique item, while the column names correspond to the respective parameter names. If a parameter is not relevantfor a particular item/row then useNA's as placeholders

a character vector indicating the type of item with which the parameters refer. See theitemtype argument inmirt. Note that this input is only used to determine the relevant item class for the rows inparameters, therefore many inputs are interchangeable (e.g., '2PL' generates the same internal model object as '3PL').If only a single value is provided then all items types will be assumed identical

(optional) a numeric vector used to define the population latent meanstructure. By default the mean structure is centered at a 0 vector

(optional) a matrix used to define the population variance-covariance structure between the latent traits. By default the relationship is assumed to be orthogonal standard normal (i.e., an identity matrix)

scoring key required for nested-logit models. Seemirt for details

the value representing the lowest category index. By default this is 0,therefore the response suitable for the first category is 0, second is 1, and so on up toK - 1

single group object defined by themirt package

a numeric vector indicating the latent theta values for a single person

(optional) data.frame object containing questions, options, and scoringkeys. SeemirtCAT for details

the name of the session defined inmirtCAT

adata.frame containing thecharacter vector inputs required to generate GUI questions through shiny. Iffactors are supplied instead ofcharacter vectors then the inputs will be coerced using theas.character() function (setstringsAsFactors = FALSE when defining adata.frame to avoid this). Each row in the object corresponds to a uniqueitem. The object supports the follow column name combinations as inputs to specify the type of response format, questions, options, answers, and stems:

Type

Indicates the type of response input to use from the shiny package. The supported types are:'radio' for radio buttons (radioButtons),'select' for a pull-down box for selecting inputs (selectInput),'rankselect' for a set of pull-down boxes rank-orderinginputs (selectInput) associated with each option supplied,'text' and'textArea' for requiring typed user input (textInput andtextAreaInput),'checkbox' for allowing multiple responses to be checked off (checkboxGroupInput),'slider' for generating slider inputs (sliderInput), or'none' for presenting only an item stem with no selection options. Note that sliderinputs require additional arguments to be passed; see... instructions below).

Additionally, if the above types are not sufficient for the desired output then users can create their own response formats and inputs via thecustomTypes list input (see below). E.g., if a function with the name'MyTableQuestion' is supplied tocustomTypes then supplying this type to thedf will use this function forthe respective item. Note that this is more advanced and requires a working knowledge of shiny's design, inputs, and specifications. This is generally for advanced usersto use on an as-per-needed basis.

Question

A character vector containing all the questions or stems to be generated.By default these character vectors are passed toHTML, and therefore allow for HTML tags to be included directly. For example, the following example defines two stems, where the second uses an emphasis tag to provide italics.

Question = c('This is the first item stem.', 'This is the <em>second</em> item stem.'))

Alternatively, if tag constructor function are preferred these need only be wrapped withina final call toas.character to coerce the shiny.tag expressions into suitablecharacter vectors of HTML code. For example, the above could be expressed as

Question = c('This is the first item stem.', as.character(div('This is the', em('second'), 'item stem.')))

Moreover, because this input must be a character vector, the use ofsapply in concert withas.character can apply this conversion to all elements (oftenredundantly). Here's an example of this format:

                    Question = sapply(list('This is the first item stem.',                        div('This is the', em('second'), 'item stem.'),                        div('This is the', strong('third'), br(), br(), 'item stem.'),                        div('Fourth with some code:', code('obj <- 42'))),                    as.character)

Option.#

Names pertaining to the possible responseoptions for each item, where the # corresponds to the specific category. Forinstance, a test with 4 unique response options for each item would containthe columns (Option.1,Option.2,Option.3,Option.4).If, however, some items have fewer categories than others thenNA's can be used for responseoptions that do not apply.

Answer orAnswer.#

(Optional) A character vector (or multiple charactervectors) indicating the scoring key for items that have correct answer(s). If thereis no correct answer for a question then a value ofNA must be declared.

Note that 'scoring' some item response data can be ambiguous depending on the stimuli provided, which requires greater attention. For example, when using'rankselect': should partial scoring be used if the ranks are mostly correct; should partial scoring be used if the response are only off by a ranking constant (e.g., correct rank is 1-2-3-4-5, but the respondent ranks 2-3-4-5-1, in whichcase four relative rankings are correct but 1 is incorrect); should a 0-1 scoring be used to indicate none-all correct?. When this type of ambiguity exists in the multiple-answers cases it is strongly recommended to use theAnswerFuns argument instead for better functional control

Forced

(Optional) logical vector indicating whether the respondent is forced (TRUE) or not (FALSE) to include a response for the respective item.If omitted from thedf definition this will be automatically set toTRUEfor each item. For surveys, it is generally recommended to set this toFALSE toallow respondents the ability to not answer questions they may be uncomfortable answering

Stem

(Optional) a character vector of absolute or relative paths pointing external markdown (.md) or HTML (.html) files to be used as item stems.NAs are used if the item has no corresponding file.

Timer

(Optional) a numeric vector indicating a time limit (in seconds) for each respective item. If a response is not provided before this limit then the questionwill automatically advance to the next selected item. The valuesNA andInfindicate no time limit for the respective items. Note that this option can only be used whendf$Forced = TRUE

Mastery

(Optional) a logical vector indicating whether the item must be masteredprior to continuing. Naturally, this requires that one or moreAnswers are provided,or suitable functions for scoring are supplied

HTMLOptions

(Optional) a logical vector indicating whether the respectiveOption.# terms should be wrapped within anHTML function and renderedfor suitable shiny inputs (e.g., radio buttons). This is a short-hand wrapper to the moreflexiblechoiceNames approach, which can be used to wrap option inputs with alternative functions.

...

In cases where'slider' inputs are used instead only theQuestion input is required along with (at minimum) amin,max, andstep column. In rows where theType == 'slider' the column names will correspond to the input arguments tosliderInput. Other input column options such asstep,round,pre,post,ticks,inline,placeholder,width, andsize are also supported for the respective input types.

single group object defined by themirt::mirt() function. This is requiredif the test is to be scored adaptively or non-adaptively, but not required for general questionnaires. The object can be constructed by using thegenerate.mirt_object function if population parameters are known or byincluding a calibrated model estimated from themirt function with real data.

argument passed tomirt::fscores() for computing new scores in the CAT stage, with the addition of a'fixed' input to keep the latent trait estimatesfixed at the previous values. Whenmethod = 'ML', if there is no variability in the given response pattern during the CAT (i.e., the participant is responding completelycorrectly or completely incorrectly) then the method will temporarily be set to MAP until sufficient response variability is present. Default is 'MAP'

adaptive criteria used, default is to administer each item sequentially usingcriteria = 'seq'.

Possible inputs for unidimensional adaptive tests include:'MI' for the maximuminformation,'MEPV' for minimum expected posterior variance,'MLWI' for maximum likelihood weighted information,'MPWI' for maximum posterior weighted information,'MEI' for maximum expected information, and'IKLP' as well as'IKL' for the integration based Kullback-Leibler criteria with and without the prior density weight,respectively, and their root-n items administered weighted counter-parts,'IKLn' and'IKLPn'.

Possible inputs for multidimensional adaptive tests include:'Drule' for the maximum determinant of the information matrix,'Trule' for the maximum (potentially weighted) trace of the information matrix,'Arule' for the minimum (potentially weighted) trace of the asymptotic covariance matrix,'Erule' for the minimum value of the information matrix, and'Wrule' for the weighted information criteria. For each of these rules, the posterior weight for the latent trait scores can also be included with the'DPrule','TPrule','APrule','EPrule', and'WPrule', respectively.

Applicable to both unidimensional and multidimensional tests are the'KL' and'KLn' for point-wise Kullback-Leibler divergence and point-wise Kullback-Leibler with a decreasing delta value (delta*sqrt(n), wheren is the number of items previous answered), respectively. Thedelta criteria is defined in thedesign object

Non-adaptive methods applicable even when nomo object is passed are:'random' to randomly select items, and'seq' for selecting items sequentially.

two possible inputs to determine the starting item are available. Passing a number will indicate the specific item to be used as the start item;default is 1, which selects the first item in the defined test/survey. If a character string is passed then the item will be selected from one of the item selections criteria available (see thecriteria argument). For off-line runs where alocal_pattern input is used then a vector of numbers/charactersmay be supplied and will be associated with each row response vector

a character/numeric matrix of response patterns used to run the CAT application without generating the GUI interface. This option requires complete response pattern(s) to be supplied.local_pattern is required to be numeric if noquestions are supplied, and the responses must be within a valid range of the definedmo object.Otherwise, it must contain character values of plausible responses which corresponds to theanswer key and/or options supplied indf. If the object contains an attribute'Theta' then these values will be stored within the respective returned objects. Seegenerate_pattern to generate response patterns for Monte Carlo simulations

a list with the length equal to the number of items in the item bank consisting of user-defined functions. These functions are used to determine whether a givenresponse obtained from the GUI is 'correct' or 'incorrect' by returning a logical scalar value, whileNA's must be used to indicateAnswerFuns should not be used for a given item. Note thatAnswerFuns is given priority over the answers provided bydf, therefore any answersprovided bydf will be entirely ignored.

For example, the following provides a customized response function for the first item.

   AnswerFuns <- as.list(rep(NA, nrow(df)))   AnswerFuns[[1]] <- function(input) input == '10' || to.lower(input) == 'ten'

logical; return an object containing the test, person, and design elements? Primarily this is to be used with thefindNextItem function

an object definition to be passed to the parallel package (see?parallel::parLapply for details). If defined, and ifnrow(local_pattern) > 1, then each row will be run in parallel to help decrease estimation times in simulation work

logical; print a progress bar to the console with thepbapply package for given response patterns? Useful for gauging how long Monte Carlo simulations will take to finish

logical; when acl object is supplied, should the cluster be primed first before running the simulations in parallel? Setting toTRUE will ensure that using the cluster will be optimal every time a newcl is defined. Default isTRUE

an optional list input containing functions for Designing Original Graphical Stimuli (DOGS).DOGS elements in the input list must contain a unique name, and the item with which it is associated must bedeclared in the adf$Type input. The functions defined must be of the form

myDOGS <- function(inputId, df_row) ...

and must return, at the very minimum, an associatedshiny input object that makes use of theinputId argument (e.g.,radioButtons). Any valid shiny object can be returned,including lists of shiny objects. As well, thedf_row argument containsany extra information the users wishes to obtain from the associated row in thedf object.

The following is a simple example of DOGS for a true-false question and how it is passed:

good_dogs <- function(inputId, df_row){   return(list(h2('This statement is false'),               radioButtons(inputId = inputId, label='',                             choices = c('True', 'False'), selected = '')         ))   }   df <- data.frame(Question = '', ..., Type = 'Doug') results <- mirtCAT(df=df, customTypes = list(Doug = good_dogs))

IMPORTANT: When using the custom inputs the select definedType must be unique,even when the function defined (e.g.,good_dog above) is recycled. Hence, if two itemswere to use thegood_dog function thendf should be defined as something likedf$Type <- c('Doug1', 'Doug2') with the associatedcustomTypes = list(Doug1=good_dog, Doug2=good_dog)

a list of design based control parameters for adaptive and non-adaptive tests. These can be

min_SEM

Default isrep(0.3, nfact); minimum standard error or measurementto be reached for the latent traits (thetas) before the test is stopped. If the test ismultidimensional, either a single value or a vector of values may be supplied to provideSEM criteria values for each dimension

delta_thetas

Default isrep(0, nfact); stopping criteria based on the change in latenttrait values (e.g., a change fromtheta = 1.5 totheta = 1.54 would stop the CAT ifdelta_thetas = 0.05). The default disables this stopping criteria

thetas.start

a numeric vector of starting values for the theta parameters (default isrep(0, nfact)) or anmatrix with N rows and nfact columns, where Nis equal tonrow(local_pattern)

min_items

minimum number of items that must be answered before the test is stopped. Default is1

max_items

maximum number of items that can be answered. Default is the length of the item bank

max_time

maximum time allowed for the generated GUI, measuredin seconds. For instance, if the test should stop after 10 minutes then the number 600 should be passed (10 * 60). Default isInf, therefore no time limit

quadpts

Number of quadrature points used per dimension for integration (if required). Default is identical to scheme infscores

theta_range

upper and lower range for the theta integration grid. Used in conjunction withquadpts to generate an equally spaced quadrature grid. Default isc(-6,6)

allow_constrain_breaks

logical; should the test be allowed to terminate in the middle of administering the items in an (un)ordered testlet set specified inconstraints? Default isFALSE

weights

weights used whencriteria == 'Wrule', but also will be applied for weighted trace functions in the T- and A-rules. The default weights the latent dimensions equally. Default isrep(1, nfact), wherenfact is the number of test dimensions

KL_delta

interval range used whencriteria = 'KL'orcriteria = 'KLn'. Default is0.1

content

an optional character vector indicating the type of content measuredby an item. Must be supplied in conjunction withcontent_prop

content_prop

an optional named numeric vector indicating the distribution of item content proportions. Acontent vector must also be suppliedto indicate the item content membership. For instance, ifcontent contains threepossible item content domains 'Addition', 'Subtraction', and 'Multiplication', and the test should contain approximately half multiplication and a quarter of both addition and subtraction, then a suitable input would be

content_prop = c('Addition'=0.25, 'Subtraction'=0.25, 'Multiplication'=.5)

Note thatcontent_prop must sum to 1 in order to represent valid population proportions.

classify

a numeric vector indicating cut-off value(s) for classificationabove or below some prior threshold. Default does not use the classification scheme

classify_CI

a numeric vector indicating the confident intervals used to classify individuals being above or below values inclassify. Values must be between 0 and 1 (e.g., 0.95 gives 95% confidence interval)

sprt_lower

a numeric vector indicating lower cut-off value(s) for classificationabove or below some prior threshold using the sequential probability ratio test.Default does not use the classification scheme

sprt_upper

a numeric vector indicating upper cut-off value(s) for classificationabove or below some prior threshold using the sequential probability ratio test.Default does not use the classification scheme

sprt_alpha

a numeric vector indicating the lower-bound error rate to use for SPRT. Default is .05

sprt_beta

a numeric vector indicating the upper-bound error rate to use for SPRT. Default is .05

exposure

a numeric vector specifying the amount of exposure control to apply foreach successive item (length must equal the number of items). Note that this includes the first item as well when a selection criteria is specified, therefore if a specific first item should be used then the first element toexposure should be 1. The default uses no exposure control.

If the item exposure is greater than 1 then then most optimalcriteria will be randomly sampled from. For instance, ifexposure[5] == 3, andcriteria = 'MI', then when the fifth item is to be selected from the remaining pool of items the top 3 candidate items demonstrating the largest information criteria will be sampled from. Naturally, the first and last elements ofexposure are ignored since exposure control will be meaningless.

If all elements inexposure are between 0 and 1 then the Sympson-Hetter exposure control method will be implemented. In this method, an item is administered only if it passes a probability simulation experiment; otherwise, it is removed from the item pool.Values closer to 1 are more likely to appear in the test, while value closer to 0 are morelikely to be randomly discarded.

constraints

A named list declaring various item selection constraints for whichparticular item, where each list element is a vector of item numbers. Unless otherwise stated,multiple elements can be declared (e.g.,list(ordered = c(1:5), ordered = c(7:9)) isperfectly acceptable). These include:

not_scored

declaring items that can be selected but will not be used in the scoring of the CAT. This is primarily useful when including experimental items forfuture CATs. Only one vector ofnot_scored elements can be supplied

excluded

items which should not actually appear in the session (useful when re-testing participants who have already seen some of the items). Only one vector ofexcluded elements can be supplied

independent

declaring which items should never appear in the same CAT session.Use this if, for example, item 1 and item 10 have very similar questions types and therefore should not appear within the same session

ordered

if one item is selected during the CAT, administer this particular group of items in order according to the specified sequence

unordered

same as ordered, except the items in the group will be selected at random until the group is complete

customUpdateThetas

a more advanced function of the formcustomUpdateThetas <- function(design, person, test) to update the ability/latent trait estimates throughout the CAT (or more generally, scoring) session.Thedesign,person, andtest are the same as incustomNextItem. The latent trait terms are updated directly in theperson object, which is aReferenceClasses type, and therefore direct assignment to the object will modify the internalelements. Hence, to avoid manual modification users can pass the latent trait estimates and their respective standard errors to the associatedperson$Update_thetas(theta, theta_SE) function.Note that thefscores() function can be useful hereto capitalize on the estimation algorithms implemented inmirt.

For example, a minimal working function would look like the following (note the use ofrbind() toappend the history terms in theperson object):

       myfun <- function(design, person, test){           mo <- extract.mirtCAT(test, 'mo')           responses <- extract.mirtCAT(person, 'responses')           tmp <- fscores(mo, response.pattern = responses)           person$Update_thetas(tmp[,'F1'],                                tmp[,'SE_F1', drop=FALSE])           invisible()        }

customNextItem

a more advanced function of the formcustomNextItem <- function(design, person, test) to use a customized item selectionmethod. This requires more complex programming and understanding ofmirtCATs internal elements,and it's recommended to initially use abrowser to understand the state of the input arguments. When defined, all but thenot_scored input to the optionalconstraints list will be ignored.

Use this if you wish to program your item selection techniques explicitly, though this can be combined the internalfindNextItem function with analogous inputs. Function must return a single integer value indicating the next item to administer or anNA value to indicate that the testshould be terminated. Seeextract.mirtCAT for details on how to extract and manipulatevarious internal elements from the required functional arguments

constr_fun

(WARNING: supplying this function will disable a number of the heuristic item selection constraints in theconstraints list as a consequence; namely, all list optionsexcept for"not_scored").

This argument contains an optional user-defined function of the formfunction(design, person, test) that returns adata.frame containing the left hand side, relationship, and right hand sideof the constraints forlp. Each row corresponds to a constraint, while the number of columns should be equal to the number of items plus 2. Note that the column names of the returneddata.frame object do not matter.

For example, say that for a given test the user wants to add the constraint that exactly 10 items should be administered to all participants, and that items 1 and 2 should not be included in the same test. The input would then be defined as

const_fun <- function(design, person, test){       nitems <- extract.mirt(test@mo, 'nitems')       lhs <- matrix(0, 2, nitems)       lhs[1, ] <- 1       lhs[2, c(1,2)] <- 1       data.frame(item=lhs, relation=c("==", "<="), value=c(10, 1))     }

The definition above corresponds to the constraints1 * x1 + 1 * x2 + ... + 1 * xn = 10 and1 * x1 + 1 * x2 + 0 * x3 + ... + 0 * xn <= 1 , where thex terms represent binary indicators for each respective item which the optimizer is searching through. Given some objective vector supplied tofindNextItem,the most optimal 10 items will be selected which satisfy these two constraints, meaning that1) exactly 10 items will be administered, and 2) if either item 1 or 2 wereselected these two items would never appear in the same test form (though neither is forced toappear in any given test). SeefindNextItem for further details and examples

test_properties

a user-defineddata.frame object to be usedwith a suppliedcustomNextItem function. This should be used to define particularproperties inherent to the test items (e.g., whether they are experimental, have a particularweighting scheme, should only be used for one particular group of individuals, and so on). The number of rows must be equal to the number of items in the item bank, and each row corresponds to the respective item. This input appears within the internaldesign objectin atest_properties slot.

person_properties

a user-defineddata.frame object to be usedwith a suppliedcustomNextItem function. This should be used to define particularproperties inherent to the individuals participants (e.g., known grouping variable, age, whether they've taken the test before (and which items they took), and so on). In off-line simulations, the number of rows must be equal to the number of participants. This input appears within the internaldesign object in aperson_properties slot; for Monte Carlo simulations, rows should be manually indexed using theperson$ID slot.

a list of GUI based parameters to be over-written. These can be

title

A character string for the test title. Default is'mirtCAT'

authors

A character string for the author names. Default is'Author of survey'. If the input is an empty string ('') then the author information will be omitted in the GUI

instructions

A two part character vector indicating how to use the GUI. Default is:

c("To progress through the interface, click on the action button below.",       "Next")

The second part of the character vector provides the name for the action button.

itemtimer

A character string to display the item-timer clock. Default is'Item timer: '

incorrect

A character string to display in case of a failed response. Default is'The answer provided was incorrect. Please select an alternative.'

failpass

A character string to display in case of a failed password input. Default is'Incorrect Login Name/Password. Please try again (you have %s attempts remaining).'

timemsg

A three part character vector indicating words for hour, minute, second & and. Default isc('hour ','minutes ','seconds ', 'and ')

firstpage

The first page of the shiny GUI. Default prints the titleand information message.

          list(h1('Welcome to the mirtCAT interface'),              sprintf('The following interface was created using the mirtCAT package v              To cite the package use citation(\'mirtCAT\') in R.',                  packageVersion("mirtCAT")))

If an empty list is passed, this page will be skipped.

begin_message

Text to display on the page prior to beginning the CAT. Default is"Click the action button to begin." for scored tests whereby amo object has been include,while the default is"" for non-scored tests (which disables the page).

demographics

A person information page used in the GUI for collecting demographic information, generated using tools from the shiny package. For example,the following code asks the participants about their Gender:

          list(selectInput(inputId = 'gender',                  label = 'Please select your gender.',                  choices = c('', 'Male', 'Female', 'Other'),                  selected = ''))

By default, the demographics page is not included.

demographics_inputIDs

a character vector required if a custom demographicsinput is used. Default isdemographics_inputIDs = 'gender', corresponding tothedemographics default

stem_default_format

shiny function used for the stems of the items. Default uses theHTML wrapper, allowing for HTML tags to be included directly in the character vector definitions. To change this to something different, likeh5 for example, passstem_default_format = shiny::h5 to theshinyGUI list

temp_file

a character vector indicating where a temporary .rds file containing the response information should be saved while the GUI is running. The object will be saved after each item is successfully completed. This is used to save response information to the hard drive in case there are power outages or unexpected computer restarts.

IfNULL, no temp file will be created. Upon completion of the test, the temp file will be deleted. If a file already exists, however, then this will be used to resume the GUI at the last location where the session was interrupted

lastpage

A function printing the last message, indicating that the test has been completed (i.e., criteria has been met). The function requires exactly one argument (calledperson), where the input argument is the person object that has been updated throughout the test. The default function is

function(person){                     return(list(h5("You have successfully completed the interface.                                    It is now safe to leave the application.")))                     }

css

a character string defining CSS elements to modify the GUI presentation elements. The input string is passed to the argumenttags$style(HTML(shinyGUI$css))prior to constructing the user interface

theme

a character definition for theshinytheme package to globally change the GUI theme

choiceNames

a list containing thechoiceNames input for each respective item whenthe input is 'radio' or 'checkbox' (seeradioButtons), where eachelement is itself a list of instructions.

This is used to modify the output of the controllers using suitable HTML code. If a row indf should not have a customized names then supplying the valueNULL in the associated list element will use the standard inputs instead. Alternatively, if specified the names of the elements to this list can be used to match the rownames of thedf object to avoid the use ofNULL placeholders

choiceValues

associated values to be used along withchoiceNames (see above)

time_before_answer

a numeric value representing the number of seconds that must have elapsedwhendf$Forced = FALSE before a response can be provided or skipped. This is used to control accidental skips over items when responses are not forced. Default is 1, indicatingone full second

password

adata.frame object indicating the user name (optional) and passwordrequired prior to beginning the CAT. Possible options are

No User Information

a single rowdata.frame. Each column supplied in this case will be associatedwith a suitable password for all individuals. Naturally, if only 1 column is defined thenthere is only 1 global password for all users

User Information Pairing

a multi-rowdata.frame where the first column represents the user name and all other columns as the same as the first option. E.g., if two users ('name1' and 'name2') are given the same password '1234' thenpassword = data.frame(User = c('user1', 'user2'), Password = rep('1234', 2))

response_msg

string to print when valid responses are required but the users does not providea valid input. Default is"Please provide a suitable response"

ui

a shiny UI function used to define the interface. IfNULL, the default one will be used. SeemirtCAT:::default_UI for the internal code definition

a list object which can be used to specify a pre-CAT block in which different test properties may be applied prior to beginning the CAT session. If thelist is empty, no preCAT block will be used. All of the following elements are required to use thepreCAT input:

min_items

minimum number of items to administer before the CAT session begins.Default is 0

max_items

max number of items to administer before the CAT session begins.An input greater than 0 is required to run the preCAT stage

criteria

selection criteria (see above). Default is 'random'

method

estimation criteria (see above). It is generally recommended to select a method which can deal with all-or-none response patterns, such as 'EAP','MAP', or 'WLE'. Default is 'MAP'

response_variance

logical; terminate the preCAT stage when there is variability in the response pattern (i.e., when maximum-likelihood estimation contains a potential optimum)?Default is FALSE

additional arguments to be passed tomirt,fscores,runApp, orlattice

object of class'mirtCAT'

object of class'mirtCAT'

logical; sort the response patterns based on the order they were administered? If FALSE, the raw response patterns containing NAs will be returnedfor items that were not administered

a number indicating which theta to plot (only applicable for multidimensional tests). The default is to facet each theta on one plot, but to plot only the first factor passpick_theta = 1

logical; include a horizontal line indicating where the population-level theta values are? Only applicable to Monte Carlo simulations because this value would not be known otherwise

size of the standard errors to plot. The default is 1, and therefore plots thestandard error. To obtain the 95% interval useSE = 1.96 (from the z-distribution)

title of the plot. Will default to'CAT Standard Errors' or'CAT ##% Confidence Intervals' depending on the SE input

plotting argument passed tolattice

plotting argument passed tolattice

plotting argument passed tolattice

arguments passed tomirtCAT

a function called just before the shiny GUI has been terminated, primarily forsaving results externally with packages such asrDrop2,RAmazonS3,googlesheets,RMySQL, personal servers, and so on when applications are hosted on the web. The functionmust be of the formfinal_fun <- function(person){...}, whereperson is the standard output returned frommirtCAT

an object of class 'mirtCAT_design' returned from themirtCAT functionwhen passingdesign_elements = TRUE

a numeric vector indicating which items to select

a numeric vector indicating the responses the the selected items

logical; update the internal ability terms after the new item response has beenadded to the internal objects?