reml(Model,Randomvars[,restrict:F,nonhier:T,marg:T,maxiter:k, usemle:T,tolerance:x]) |

reml(Model,Randomvars) performs a restricted maximum likelihood analysis for the model given in CHARACTER scalar Model. Randomvars is a CHARACTER vector specifying the names of factors in the model which are random. Randomvars can also be REAL with integer elements specifying the index of a factor in the model. If there are no random factors, Randomvars should be NULL. The return value of reml() is a structure with the following components: theta: estimates of the fixed effects phi: estimates of the variance components thetavar: variance matrix of the fixed effects phivar: variance matrix of the variance components phidf: equivalent degrees of freedom for the variance components L: REML log likelihood Any variates in the model must be fixed effects. reml() assumes that if a factor first appears in an interaction, then that factor is nested in the other terms of the interaction. For example, if the first appearance of factor c is in the term a.b.c, then c is assumed nested in the a.b combinations. This nesting is assumed in the remainder of the model. That is, continuing the example, if there is a later term c.d, it will be interpreted as a.b.c.d even though a.b.c.d is not specifically in the model. reml() works for both balanced and unbalanced data. reml(Model,Randomvars,restrict:F) performs the REML analysis assuming no marginal restrictions on the random effects in the model. reml(Model,Randomvars,nonhier:T) performs the REML analysis for an analysis of variance that does not enforce the usual MacAnova hierarchy assumptions. That is, for example, model "y=a+b+c+a.b.c" does not imply that the two-way interaction degrees of freedom are part of the "a.b.c" term. You cannot use anova() to compute such an analysis although it can be done (if you know how) using swp(). reml(Model,Randomvars,usemle:T) performs a maximum likelihood analysis instead of the REML analysis. reml(Model,Randomvars,tolerance:value) uses value as a tolerance for determining singularity and convergence (default is 1e-10). reml(Model,Randomvars,maxiter:value) uses value as the maximum number of iterations in the fitting process (default is 60). See also mixed().

Gary Oehlert 2003-01-15