CHANGES IN conquestr VERSION 1.9.2

NEW FEATURES

• pvRegression() now returns an object of class "pvRegression" (still a data frame) with print(), summary(), coef(), vcov(), confint(), predict() and nobs() methods. vcov() gives the full Rubin-combined covariance matrix of the coefficients.

DEPRECATED AND DEFUNCT

• pvMeanVar() has been removed. Use pvMean() and pvVar() (or pvDescribe()) instead, which also support weights and replicate standard errors.

CHANGES IN conquestr VERSION 1.8.3

NEW FEATURES

• genResponses() gains a debug argument. When debug = TRUE it returns a list holding the responses and the intermediate data from each step: the standardised inputs, the parsed perturbations, the perturbed item parameters, which perturbation was applied to each case and item, the random draws, and the category probabilities used (and those under the unperturbed items). Responses are identical to debug = FALSE for the same seed.
• New genResponsesProbs() tabulates the response probabilities used for each case, item, and category alongside the unperturbed probabilities, to check that perturbations were applied to the intended cases. See the “Generate item responses” vignette.
• Perturbations in genResponses(perturbR = ) can now apply to all cases (omit group, or use NULL or NA), one group, or several groups (e.g., group = c("g1", "g2")). Elements can be given by name.
• The same item can now be perturbed differently for different groups. If two perturbations apply to the same case and item, the later one is used, with a warning (previously, the last was used silently).
• “discrimination” perturbations gain pivotAt = "item", which changes the discrimination around a point pivot logits from the item’s location, so that the item location does not move (category probabilities are unchanged at the pivot point). The default, pivotAt = "theta", keeps the previous behaviour. A separate shift can be added to move the item location without moving the discrimination pivot.
• New family of functions for population statistics from plausible values (PVs) with replicate-weight standard errors. Each statistic is computed for every PV under the full-sample weight and each replicate weight (in C++), then combined with Rubin’s rules. Supported replication methods are BRR, Fay’s variant of BRR (repMethod = "Fay", with fayK), and the delete-one ("JK1") and paired ("JK2") jackknife. All support a grouping variable (by). See the “Population statistics from plausible values” section of the introductory vignette.
  • pvStat() is the core function: mean, variance, SD, median, quantiles, IQR, sum of weights, or a user-supplied function(x, w).
  • pvMean(), pvVar(), pvSd(), pvMedian(), pvQuantile(), pvIqr() and pvDescribe() are wrappers for common descriptive statistics.
  • pvDiff() estimates differences between groups (e.g., girls minus boys), computing the difference within each PV and replicate so the standard error reflects covariance induced by the sampling design.
  • pvCor() estimates correlations between a measure and one or more other measures, combined on the r scale (default) or the Fisher-z scale (combine = "fisherZ"), with confidence intervals. Each measure may be latent (a set of PVs) or manifest (a single observed column).
  • pvCorMatrix() and pvCovMatrix() estimate the correlation and covariance matrices of several measures, e.g., the outcome domains of IELS, PISA or TIMSS. Latent and manifest measures can be mixed: latent measures are paired by PV draw, and a manifest variable’s column is reused for every draw. With only manifest variables, the ordinary weighted matrix is returned with replicate standard errors. Results are available in long or matrix form. Cases are dropped listwise so the matrix is valid; a warning is given if Fisher-z combining produces a matrix that is not positive semi-definite.
  • pvRegression() fits a weighted linear regression of PVs on background variables given as a one-sided formula, and returns coefficients and R-squared with standard errors and confidence intervals.

MINOR CHANGES

• pvMeanVar() is now a thin wrapper around pvMean() and pvVar(). Results are unchanged. Its documentation now correctly describes the input as n cases by m PVs.
• genResponses() has been split into steps (genRespInputs(), parsePerturbations(), perturbItem(), buildPerturbMap(), and genMissingMCAR()), each of which can be called on its own.
• genResponses() now gives informative errors for invalid perturbations (e.g., a missing factor or pivot, or a group not found in groups) and for mcarP outside 0 to 1.
• The documentation of pivot in genResponses() has been corrected: it is added to the delta dot. For a dichotomous item, perturbed and unperturbed curves cross at theta = pivot / (a * (factor - 1)).

BUG FIXES

• getCqParams() (and so getCqRespModel()) removed the wrong parameters when a model had unidentified (problem) gins, misaligning parameter estimates with their gins and, in some cases, failing with “arguments imply differing number of rows”.

CHANGES IN conquestr VERSION 1.8.1

MAJOR CHANGES

• The readers for ‘ACER ConQuest’ system files and rout files (ReadSys and the Read* helpers) have been rewritten in C++. The file is read into memory once and parsed in C++; ConQuestSys() is roughly 10-20 times faster on the included examples, and the results are identical.
• Truncated or corrupt files now give an informative “unexpected end of file” error instead of silently returning short reads or trying to allocate huge vectors.
• The low-level Read* helpers now take a ‘cqReader’ (an in-memory file created internally by ConQuestSys() and ConQuestRout()) rather than a connection. DecompressSys() now takes and returns a raw vector, and no longer writes a temporary file.

CHANGES IN conquestr VERSION 1.6.1

NEW FEATURES

• Added cpp helper functions to handle complex strings in Itanal helpers see conquestr::lcs and conquestr::lcs_vec
• This allows more complex support for conquestr::getCqItanal, and conquestr::getCqItanalSummary for example when group variables or levels within groups contain punctuation (e.g., “my-group_variable.”, and “my-group_level_1”)

MAJOR CHANGES

• Patched issue with getCqRespModel when the model has both anchors and problem (unidentified) items
• Patched internal tests for getCqRespModel.

CHANGES IN conquestr VERSION 1.5.5

NEW FEATURES

• Added support for ACER ConQuest system files version 30 which are created by the command put (https://conquestmanual.acer.org/s4-00.html#put) in ACER ConQuest Version > 5.47.
• Improved handling of missing values or items where all responses are in one category itanal output (see e.g., conquestr::getCqItanal, and conquestr::getCqItanalSummary)

MAJOR CHANGES

• Patched internal tests for upstream dependencies.

CHANGES IN conquestr VERSION 1.5.0

NEW FEATURES

• Added support for ACER ConQuest system files version 29 which are created by the command put (https://conquestmanual.acer.org/s4-00.html#put) in ACER ConQuest Version > 5.42.

MAJOR CHANGES

• conquestr::getCqItan now returns estimated scores in the item tables rather than raw scores. Previous versions would the pre-key value and the raw score associated with the pre-key value (these two values are identical when no key or recode is used). The values are now the pre-key value and the estimated score. In the case of models without estimated scores (e.g., Rasch models) the raw score is the same as the estimated score.

CHANGES IN conquestr VERSION 1.4.4

NEW FEATURES

• Added support reading uncompressed system files in markdown and shiny workflows previously, the function that worked out if a system file was compressed threw an invisible error that would break, for example, knitr workflows.
• Added support for polytomies and scores in genItems.
• added support for itanals that include groups.

MAJOR CHANGES

• conquesrt::getCqItan now returns a list of list of lists. The top level list is the return object. Each element of this list is a group from the itanal. In most use cases this is “all cases” and the length of this list is 1. Therefore, to get the 4th item analysis table for the first group is now accessed by returnObject[[1]][[4]] instead of returnObject[[4]]

CHANGES IN conquestr VERSION 1.4.0

NEW FEATURES

• added support for ACER ConQuest system file v27 (ConQuest V5.40.14)
• added gTokenList

CHANGES IN conquestr VERSION 1.3.6

NEW FEATURES

• added support for long labels in history files. See ?conquestr::getCqHistory.
• added gYBetaAll - the regression mean for the cases.

CHANGES IN conquestr VERSION 1.3.0

NEW FEATURES

• added support for reading compressed system files.

MAJOR CHANGES

Bug fixes

CHANGES IN conquestr VERSION 1.2.0

NEW FEATURES

• added support for reading “mini” system file.

MAJOR CHANGES

Bug fixes

CHANGES IN conquestr VERSION 1.1.1

NEW FEATURES

• added support for plotting item characteristics curves, see e.g., plotCCC

MAJOR CHANGES

• Bug fixes

CHANGES IN conquestr VERSION 1.0.0

NEW FEATURES

• added support for producing and plotting model expected curves related to items and tests, see e.g., plotModelICC
• added support for extracting item parameters, variances, fits, labels in getCqRespModel

MAJOR CHANGES

• functions that deal with items scores are more general and apply to any model that scores categories including those that do not assume integer scoring.

Bug fixes

• many.

CHANGES IN conquestr VERSION 0.9.4

NEW FEATURES

• added support for producing and plotting test information functions

MAJOR CHANGES

• ConQuestCall now will call “cmd.exe” via system2 on Windows. This is morre consistent with behaviour on Mac.

Bug fixes

• compiled (win binary) version previously could cause error when using ConQuestCall with paths with spaces. Fixed.

CHANGES IN conquestr VERSION 0.9.1

NEW FEATURES

• added support for analysing standardised residuals as per DOI: 10.1177/0013164410379322

MAJOR CHANGES

• ConQuestCall now will try and find the ConQuest executable rather than requiring explicit declaration

Bug fixes

CHANGES IN conquestr VERSION 0.8.5

NEW FEATURES

• added support for ACER ConQuest system files from BTL/pairwise models
• added generic S3 function, plotRout to support plotting rout obejcts

MAJOR CHANGES

• conquestr now requires ACER ConQuest > 5.12.3
• plotRout has methods for ICC and for Infomap objects.

Bug fixes

• fix in getCqHist: matrix was previously the transpose of history (truncated where n iter > n params and vice-versa), now corrected.

CHANGES IN conquestr VERSION 0.4.0

NEW FEATURES

• added support for ACER ConQuest system files from MCMC models (estimate ! method = patz…)
• added searchConQuestSys to help users search names in system file objects

MAJOR CHANGES

• conquestr now requires ACER ConQuest > 4.34.0
• replaceInDataFrame replaces zapSystemMissing in calls to createDfFromSys - this uses Rccp in place of base R and is approx 25 times faster making this function usable for large analyses.

CHANGES IN conquestr VERSION 0.3.7

NEW FEATURES

• Initial CRAN release.