Movatterモバイル変換


[0]ホーム

URL:


trimr: Response Time Trimmingin R

For a detailed overview of how to usetrimr, please see thevignettes.

Installation

A stable release oftrimris available onCRAN. To install this, use:

install.packages("trimr")

You can also install the latest developmental version oftrimr. Please note, though, that this version is undergoingtesting and potentially has unidentified bugs. (If you do use thisversion and note a bug,please log it as anissue). To install the developmental version, you will first need toinstall thedevtools package and installtrimrdirectly from GitHub by using the following commands:

# install devtoolsinstall.packages("devtools")# install trimr from GitHubdevtools::install_github("JimGrange/trimr")

Overview

trimr is an R package that implements most commonly-usedresponse time trimming methods, allowing the user to go from a raw datafile to a finalised data file ready for inferential statisticalanalysis.

The trimming functions available intrimr fall broadly intothree families:

  1. Absolute Value Criterion
  2. Standard Deviation Criterion
  3. Recursive / Moving Criterion

The latter implements the methods first suggsted by Van Selst &Jolicoeur (1994).

Example

In the example below, we go from a data frame containing data from 32participants (in total, 20,518 trials) to a trimmed data set showing themean trimmed RT for each experimental condition & participant usingthe modified recursive trimming procedure of Van Selst & Jolicoeur(1994):

# load trimr's librarylibrary(trimr)# load the example data that ships with trimrdata(exampleData)# look at the top of the example raw datahead(exampleData)#>   participant condition   rt accuracy#> 1           1    Switch 1660        1#> 2           1    Switch  913        1#> 3           1    Repeat 2312        1#> 4           1    Repeat  754        1#> 5           1    Switch 3394        1#> 6           1    Repeat  930        1# perform the trimmingtrimmedData<-modifiedRecursive(data = exampleData,minRT =150,digits =0)# look at the trimmedDatatrimmedData#>    participant Switch Repeat#> 1            1   1047    717#> 2           10    779    647#> 3           11   1075    931#> 4           12    871    638#> 5           13    911    763#> 6           14   1014    799#> 7           15   1151    831#> 8           16    983    675#> 9           17    831    664#> 10          18    870    761#> 11          19    672    584#> 12           2   1118   1022#> 13          20   1035    718#> 14          21    807    680#> 15          22   1239    941#> 16          23    786    685#> 17           3   1020    793#> 18           4   1103    804#> 19           5   1184    916#> 20           6   1430   1123#> 21           7    994    851#> 22           8   1118    930#> 23           9    951    721#> 24          24    627    589#> 25          25    590    602#> 26          26    721    682#> 27          27    826    784#> 28          28    706    653#> 29          29    543    560#> 30          30    751    652#> 31          31   1080    977#> 32          32    686    634

Installation Instructions

To install the package from GitHub, you need the devools package:

install.packages("devtools")library(devtools)

Thentrimr can be directly installed:

devtools::install_github("JimGrange/trimr")

References

Van Selst, M., & Jolicoeur, P. (1994). A solution to the effectof sample size on outlier elimination.Quarterly Journal ofExperimental Psychology, 47 (A), 631–650.


[8]ページ先頭

©2009-2025 Movatter.jp