NEWS {random.polychor.pa}R Documentation

News for Package random.polychor.pa

Description

The function performs a parallel analysis using simulated polychoric correlation matrices. The function will extract the eigenvalues from each random generated polychoric correlation matrix and from the polychoric correlation matrix of real data. A plot comparing eigenvalues extracted from the specified real data with simulated data will help determine which of real eigenvalue outperform random data. A series of matrices comparing MAP vs PA-Polychoric vs PA-Pearson correlations methods, FA vs PCA solutions are finally presented. Random data sets are simulated assuming or a uniform or a multinomial distribution or via the bootstrap method of resampling (i.e., random permutations of cases). Also Multigroup Parallel analysis is made available for random (uniform and multinomial distribution and with or without difficulty factor) and bootstrap methods. An option to choose between default or full output is also available as well as a parameter to print Fit Statistics (Chi-squared, TLI, RMSEA, RMR and BIC) for the factor solutions indicated by the Parallel Analysis.

Changes in version 1.1.4-5

Version 1.1.4-5 fixes some bugs.

Changes in version 1.1.4-4

Version 1.1.4-4 the following parameters were added: 1) weights allows the reader to pass a vector of weights to compute a weighted random polychor (or pearson) correlation matrix and simulate weighted samples. If also bootstrap is selected then weighted samples will be bootstrapped. Finally if multisample is also selected then the random.polychor.pa function will simulate weighted random samples for each sub-sample. Version 1.1.4-4 fixed the following issues: 1) if a value is passed for continuity check now the correct values is displayed in the output, and not the fixed values of .5 as was in previous version; 2) in previous versions if fit.pa parameter was selected it was not infrequent that the random.polychor.pa() function unexpectedly stopped after having run part of the simulations. The problem was due to the fact that for some simulated data, the function found non-valid value for RMSEA and/or for BIC indices. In the present version a series of checks were added to prevent the function to stop unxepectedly for these problems linked to fit indices estimation.

Changes in version 1.1.4-3

Version 1.1.4-3 fixed two problems: in example 1 we use bfi data from psych package as data example. However the datafile has been moved to psychTools so the example is modified accordingly. The second problem concerns an unexpected crash of random.polychoric.pa when calling polychoric function (from psych package) due to the correction for continuity that is set by default to 0.5 (i.e. correct=TRUE in polychoric function. Correction for continuity is used for replacing cells with zero counts. This correction for continuity in some situations determines NAs that causes the polychoric function to stop. To handle such problem we added a parameter to the random.polychor.pa function to set to 0.0 the correction for continuity. Users are warned that polychoric correlation matrices with and without correction for continuity differ.

Changes in version 1.1.4-2

Version 1.1.4-2 fixed minor bugs when running the example 1, and when displaying the time needed to complete the simulations.

Changes in version 1.1.4-1

Version 1.1.4-1 a problem with the psych dependency was fixed:

Changes in version 1.1.4

Version 1.1.4 added a number of cahnges:

Changes in version 1.1.3.6

Changes in version 1.1.3.5

Changes in version 1.1.3.5

Changes in version 1.1.3

Version 1.1.3 tackles two problems signalled by users:

Changes in version 1.1.2

Changes in version 1.1.1


[Package random.polychor.pa version 1.1.4-5 Index]