Output dataset created by parmhet
The output dataset (or resultsset) created by parmhet has one observation, or one observation per by-group if the by() option is specified, and data on the heterogeneity-test statistics for the dataset or by-group. The variables are as follows:
Default name Description -------------------------------------------------------------------------- idnum Numeric dataset ID idstr String dataset ID by-variables Variables specified in the by() option sumvar-variables Variables specified in the sumvar() option chi2het Heterogeneity chi-squared dfhet Heterogeneity degrees of freedom i2het Heterogeneity I-squared tau2het Heterogeneity tau-squared fhet Heterogeneity F resdfhet Heterogeneity residual degrees of freedom phet Heterogeneity P-value --------------------------------------------------------------------------
The variables with default names idnum and idstr are only present if supplied with values (constant in all observations in the resultsset) by the idnum() idstr() options, respectively. They may have non-default names, which can be specified using the nidnum() and nidstr() options, described in parmhet_resultsset_opts. The by-variables, if present, identify uniquely the observations in the resultsset, and are specified by the by() option, described in parmhet_basic_opts. If the by() option is not specified, then there is only one observation in the resultsset, containing test statistics for the whole set of input parameters in the input dataset. The sumvar-variables, if present, are specified by the sumvar() option, described in parmhet_resultsset_opts. The other variables contain heterogeneity-test statistics for the dataset, or for the by-group if the by() option is specified. They are described in parmhet_hettest_opts. The variables with default names fhet and resdfhet are only present if an input degrees-of-freedom variable is specified, in addition to the input estimate and standard error variables. The variable with the default name phet contains a P-value for the F-test if an input degrees-of-freedom variable is specified, and a chi-squared P-value otherwise. All of the heterogeneity-test statistic variables can be renamed from their default names, using the options of the same names described in parmhet_hettest_opts.
Author
Roger Newson, National Heart and Lung Institute, Imperial College London, UK. Email: r.newson@imperial.ac.uk
Also see
Manual: [R] meta, [R] test On-line: help for parmhet, parmiv, parmhet_basic_opts, parmhet_resultsset_opts, parmhet_hettest_opts help for test help for parmest, parmby, parmcip, metaparm, metan if installed