Families of lines: random effects in linear regression analysis

Abstract

Laboratory experiments often involve two groups of subjects, with a linear phenomenon observed in each subject. Simple linear regression as propounded in standard textbooks is inadequate to treat this experimental design, particularly when it comes to dealing with random variation of slopes and intercepts among subjects. The author describes several techniques that can be used to compare two independent families of lines and illustrates their use with laboratory data. The methods are described tutorially, compared, and discussed in the context of more sophisticated and more naive approaches to this common data-analytic problem. Technical details are supplied in APPENDIX A.