Some of the most common questions asked of statistical consultants: our favorite responses and recommended readings

We addressed some of the most common questions or concerns encountered when consulting with applied researchers: detecting and managing outliers; handling missing data; multiple comparisons and familywise alpha rate protection; the disadvantages of dichotomization; the nature of the general linear model; writing the results section; determining the number of factors to retain in factor analysis; power analysis; parametric versus nonparametric statistics; appropriate numbers of predictor variables for use in multiple regression; variable selection procedures in multiple regression; interpreting interaction effects; and alternative analyses for pretest-posttest control group designs.