Least-squares means are predictions made at specific values of the predictors. For each categorical variable in the term, the value is the combination of levels. For all other variables that are not part of the term, the values are neutral values. The neutral value for a quantitative variable is the mean. The neutral value of a nominal variable is the average over all levels which is equivalent to values of 0 for each dummy predictor variable in an effect coding scheme. The neutral value of an ordinal variable is the reference level.
From the Statistical Reference Guide for Analyse-it 6.24.0: https://analyse-it.com/docs/user-guide/fit-model/linear/effect-means
We use essential cookies to run the site. With your permission we'd also like to use analytics and
advertising cookies to see how visitors find and use Analyse-it, so we can keep improving it and reach
more people like you.
You can change your mind at any time, see our
Privacy policy.