![]() See also for diagnostics using option -dofv. Example: bootstrap run12.mod -samples=500 -seed= threads=5 2 Input and options 2.1 Required input A model file is required on the command-line. 2.2 Bootstrap-specific options -samples = N The number of bootstrapped datasets to generate. Default is sample_size = M The number of subjects in each bootstrap data set. The default 1ΔΆ value is set to the number of individuals in the original data set. When the resampling is stratified, the sample_size option can be used to specify the exact number of samples that should be drawn from each strata. Below follows an example of the syntax that should be used in such a case. Stratification is here done based on the study number, STUD, with the values 1001, 1002 and sample_size= 1001=>12,1002=>24,1003=>10 Note the double quotes, single quotes will not work on Windows. ![]() This example specifies that the bootstrap should use 12 samples from study 1001, 24 samples from 1002 and 10 from study If only one sample size is used together with stratified resampling (the default case sample_size=number of individuals in the data set), the strata are assigned samples in proportion to their size in the data set. Please note that this usage of the sample_size option does not guarantee that the sum of the samples of the strata is equal to the given sample_size since PsN needs to round the figures to the closest integer. ![]() For a sample size equal to the number of individuals in the data set, the sum will however always be correct.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |