### VPERMEST

VPERMTEST is a new procedure in Genstat 22 for assessing the importance of the fixed terms in a linear mixed model using permutation tests.

### Linear mixed models for censored data

Easily fit a linear mixed model to censored data and obtain well-behaved and reliable estimates of the treatment means.

**Selecting your REML fixed model**

A major focus of the 21st Edition of Genstat is the new menus and procedures to help determine the appropriate fixed terms to include in REML analysis. As REML arose out of breeding trials, where the main interest is in obtaining BLUPs for estimating genetic merit, the focus has traditionally been on the **random model**. In Genstat 21, you can now explore the **fixed model **by adding and dropping terms, just as you would in ordinary regression.

Roger Payne’s AASC talk – detailed analysis of data set from 17:13.

The referenced research paper.

# Random coefficient regression

Random coefficient regression can be used when we want to explore the relationship between a response variable (y) and a continuous explanatory variable (x) and we have *repeated measurements* of x and y on individual subjects.

###### Estimating critical values for REML fixed effects

`VCRITICAL`

provides an alternative method of assessment to Wald or F tests that may be useful if the decision from the conventional tests is not clear-cut, or if contrasts are to be assessed.

###### Procedures for assessing the adequacy of a model in a REML analysis

`VSOM`

and `VRCHECK`

can assess the adequacy of a linear mixed model fitted using REML. `VSOM`

can be used to assess the residuals and random effects for outliers. `VRCHECK`

can be used to check the properties of the random effects.

### VRPERMTEST

Performs permutation tests for random terms in `REML`

analysis.