Manfred te Grotenhuis passed away. He was a respected sociologist, statistician, and teacher. I’ll leave it to others to comment on these achievements. To me, he was my teacher and mentor in statistics, and a ...

Weighted effect coding is a technique for dummy coding that can have attractive properties, particularly when analysing observational data. In a new publication in the R Journal we explain the rationale of weighted effect coding, ...

We have been developing weighted effect coding in an ongoing series of publications (hint: a publication in the R Journal will follow). To include nominal and ordinal variables as predictors in regression models, their categories ...

Categorical variables in regression models are often included by dummy variables. In R, this is done with factor variables with treatment coding. Typically, the difference and significance of each category are tested against a preselected ...

BMC Bioinformatics has published a paper by colleagues of mine, about calculating exact p-values for pairwise comparison of Friedman rank sums. The paper provides fast and easy-to-use R code, making it an interesting read for ...

We have uploaded a new version of WEC, an R package to apply ‘weighted effect coding’ to your dummy variables. With weighted effect coding, your dummy variables represent the deviation of their respective category from ...

Weighted effect coding is a variant of dummy coding to include categorical variables in regression analyses, in which the estimate for each category represents the deviation of that category from the sample mean. The ‘wec’ ...

If your regression model contains a categorical predictor variable, you commonly test the significance of its categories against a preselected reference category. If all categories have (roughly) the same number of observations, you can also ...

The other day, Kevin Darras contacted me about my R package influence.ME. The package didn’t work with the kind of models he wanted to estimate, and Kevin was looking for a solution. He had been ...

Influence.ME is an R package that helps detecting influential cases in multilevel regression models. It has been around for a while now, and recent changes in lme4 broke the functionality of using influence.ME with sampling weights. Thanks to a kind contribution of some code by user Jennifer Bufford, influence.ME now should work with multilevel models… Continue Reading

e-mails with the latest R posts.

(You will not see this message again.)