Join the Quantitative Psychology area for a talk by Dr. Carl F. Falk (Associate Professor, McGill University)!
This is a virtual event. Join the talk online.
Title: Methods for modeling and detecting aberrant responding in survey research
Abstract: In this talk, I highlight two lines of research relevant for survey data consisting of multi-item scales. Part one focuses on confirmatory use of a multidimensional parameterization of the nominal response model. One primary application involves the modeling of response styles, such as a preference for endpoints or midpoint response options, which are thought to be problematic for the measurement of psychological constructs using Likert-type items. This model can be understood in part by starting from sum score-based approaches to studying response styles as well as generalized linear models such as (multinomial) logistic regression. Part two considers random responding behavior that may contaminate data. An approach to detection of random responding is presented and evaluated in a series of simulation studies. This approach can calibrate sensitivity without making strong measurement model assumptions. Simulations leverage data from a well-known item response theory model as well as contamination of publicly available datasets to understand the algorithm’s classification accuracy. Extensions of the algorithm to patterned responding and comparisons with model-based approaches are also discussed.
About Carl F. Falk: Carl F. Falk is an Associate Professor of Quantitative Methods and Modeling at McGill University. His research focuses on the development, computer programming, and evaluation of innovative statistical methods and latent variable models with applications across the social, behavioral, and health sciences. This work spans multiple modeling frameworks and topics, including detecting and modeling aberrant responding in survey research, appropriate ways of handling missing and non-normal data, statistical mediation analysis with latent variable models, and techniques for model selection and evaluating model complexity. Carl has over 50 publications, including at methodological outlets such as Psychological Methods, Multivariate Behavioral Research, Structural Equation Modeling, Psychometrika, and Behavior Research Methods. Carl is co-author on three papers that have won research awards from the Quantitative Methods Section of the Canadian Psychological Association. He is also PI or co-investigator/co-applicant on grants from all three federal funding agencies in Canada.