Simple test-item analysis

Show simple Classical Test Analysis statistics at item and test level

tia_tables(
  dataSrc,
  predicate = NULL,
  type = c("raw", "averaged", "compared"),
  max_scores = c("observed", "theoretical"),
  distractor = FALSE
)

Arguments

dataSrc

a connection to a dexter database, a matrix, or a data.frame with columns: person_id, item_id, item_score

predicate

An optional expression to subset data, if NULL all data is used

type

How to present the item level statistics: raw for each test booklet separately, averaged booklets are ignored, with the exception of rit and rir which are averaged over the test booklets, with the number of persons as weights, or compared, in which case the pvalues, correlations with the sum score (rit), and correlations with the rest score (rit) are shown in separate tables and compared across booklets

max_scores

use the observed maximum item score or the theoretical maximum item score according to the scoring rules in the database to determine pvalues and maximum scores

distractor

add a tia for distractors, only useful for selected response (MC) items

Value

A list containing:

booklets

a data.frame of statistics at booklet level

items

a data.frame (or list if type='compared') of statistics at item level

distractors

a data.frame of statistics at the response level (if distractor==TRUE), i.e. rvalue (pvalue for response) and rar (rest-alternative correlation)