Journal articles
Preliminary Guidelines for Empirical Research in Software Engineering
Kitchenham, B., Pfleeger, S.L., Pickard, L.M., Jones, P.W., Hoaglin, D.C., El Emam, K. & Rosenberg, J. (2002). Preliminary Guidelines for Empirical Research in Software Engineering. IEEE Transactions on Software Engineering, 28(8), 721-733
Comment
Collection of guidelines for conducting and reporting empirical research on software engineering. Most of these guidelines are applicable to user modeling as well.
The earth is round (p<.05)
Cohen J. (1994). The earth is round (p<.05). American Psychologist 49, 997-1003.
Comment
Most textbooks on statistical analysis do not explain why and how to analyse the power of statistical tests. Thus, this is an important complement to the standard books.
GPOWER: A general power analysis program
Erdfelder, E., Faul, F., & Buchner, A. (1996). GPOWER: A general power analysis program. Behavior Research Methods, Instruments, & Computers, 28, 1-11.
Comment
G*Power is a small program for power analysis of the most frequent statistical tests. It helps you to plan your sample size apriori or to check the test power post hoc. Moreover it can be used to calculate effect sizes.