This dialog allows you to assess the significance of the all the fixed terms in a REML analysis using a permutation test done by the VPERMTEST procedure.
This controls what output is printed from the analysis:
|Wald probabilities||The wald probabilities calculated over the permutation set|
|Critical values||Critical values at the 5%, 1% and 0.1% significance levels for the Wald statistics|
|Monitoring||The progress of the permutation tests|
Type of Wald statistics to calculate
This option controls whether the significances of adding a term or dropping a term are calculated.
|Add||The test statistics will be for adding the fixed terms.|
|Drop||The test statistics for the dropping fixed terms. Only those terms which are not marginal to others in the model can be dropped, e.g. with a model A + B + A.B, only A.B can be dropped as both A and B are marginal to A.B.|
Number of permutations
This option specifies the number of permutation samples that are performed, default 99 (as well as the “null” permutation where the data keep their original order).
Number of retries
This option specifies the number of extra permutations that are performed when the REML model does not converge for a permutation, default 99. Increasing the value will give a more precise probability, but will slow down the analysis.
Specifies the seed for the random number generator used to make the permutations; default 0 continues from the previous generation or (if none) initializes the seed automatically.
This lets you save results from the from the VPERMTEST analysis in Genstat data structures. After selecting the appropriate boxes, you need to type the names for the identifiers of the data structures into the corresponding In: fields.
|Wald statistics||Pointer||A pointer to a variates for all fixed terms. The variates contain the Wald statistics for all the successful permutations. The pointer suffixes are the names of the fixed terms.|
|Wald probabilities||Pointer||A pointer to scalars giving the Wald probabilities for each fixed term. The pointer suffixes are the names of the fixed terms.|
|Wald critical values||Pointer||A pointer to three variates for the 5%, 1% and 0.1% critical values for the Wald statistics. The variates contain a row for each fixed term. The variates have unit labels giving the names of the fixed terms.|
|No. tests not converged||Scalar||The number of analyses of permuted data sets that did not converge.|
Display in spreadsheet
The saved results will be displayed in a new spreadsheet.
|Clear||Clear all fields and list boxes.|
|Help||Open the Help topic for this dialog.|
- Linear Mixed Model menu.
- Linear Mixed Models with Censoring menu.
- Linear Mixed Model Options dialog.
- Linear Mixed Model Further Output dialog.
- All Subsets of the REML Fixed Model dialog.
- REML Permutation Test dialog for calculating the significance of a random term using a permutation test.
- REML Screening tests dialog
- Explore fixed model dialog for exploring which terms are important in the fixed model.
- VPERMTEST procedure.
- VRPERMTEST procedure.