There are a few industries that seem to perennially have the reputation of terrible customer service: internet providers, phone companies…and airlines. How often have you head someone gush about the amazing customer care and support they received from an airline, or raved about how enjoyable their flight was (especially if not business or first class)?Continue reading “Logistic Regression in R: Logits, Odds, and Odds Ratios”
Category Archives: R
Finite Mixture Modeling – Latent Profile Analysis, Part 2
Welcome to Part 2 of this three part series! If you have not read Part 1, and are unfamiliar with latent profile analysis, I recommend taking a few minutes to do that before you dive in here. Additionally, check out Spurk et al. (2020) for a succinct overview of the profile enumeration process. In thisContinue reading “Finite Mixture Modeling – Latent Profile Analysis, Part 2”
A Deeper Dive into CFA and Measurement Invariance Fit Issues
Confirmatory Factor Analysis In a previous post I did an exploratory and confirmation factor analysis, and measurement invariance work with data generated from the depression, anxiety, and stress scale (DASS). In that post there were no fit issues with the CFA or the measurement invariance models. However, this is often not the case when weContinue reading “A Deeper Dive into CFA and Measurement Invariance Fit Issues”
Confirmatory Factor Analysis and Measurement Invariance
Factor Analysis Many constructs of interest related to human behavior, attitude, identity, and motivation are not directly observable. For example, the Depression, Anxiety, and Stress scale (DASS) measures individuals’ perceptions of their depression, anxiety, and stress. We can not directly measure any of these constructs, so we refer to them as “latent variables”. We haveContinue reading “Confirmatory Factor Analysis and Measurement Invariance”
The Importance of Within and Between-Subject Correlations for Multilevel Data
Multilevel data are those data which are ordered in a hierarchy, data that has a “nested” structure. A common nesting structure is having multiple measurements within one subject. For example, if we measure students’ engagement in science class several times over the course of an entire semester the data we get has a specific hierarchy.Continue reading “The Importance of Within and Between-Subject Correlations for Multilevel Data”
Quantitative Quandaries 