My scientific interest concentrates on the measurement of individual differences with respect to psychological constructs. Reliable and valid measurement is a conditio sine qua non for the usefulness of any psychological variable that reflects an underlying construct. Obviously, this requirement generalizes to any area of scientific research in which multi-item instruments measure underlying constructs, such as in education, marketing, medicine and health, opinion and policy research, political science, and sociology. Without high-quality measurement, in research the data cannot answer the researcher's questions, and in measurement applications students, job applicants and clinical patients cannot be validly assessed. My research covers topics such as reliability of measurement and scalability of stimuli; the definition and investigation of the theoretical properties of modern measurement models known as item response models, both for dichotomous and polytomous item response data; goodness-of-fit investigation of such models; person-fit analysis of patterns of item scores; and item selection aimed at constructing useful measures. Part of my research deals with problems in test and questionnaire data, in particular the analysis of missing item scores and the detection of outliers. The cognitive processes that lead to the responses to items have been the topic of several projects, while another part of my research supports the construction of tests and questionnaires for use in practical applications. I am co-author of two textbooks on measurement that aim to educate graduate students, PhD's and researchers in the area of measurement and psychometrics, and have published approximately 200 articles and book chapters. Many articles have appeared in journals such as Applied Psychological Measurement, Assessment, British Journal of Mathematical and Statistical Psychology, Multivariate Behavioral Research, Psychological Methods, and Psychometrika.