Stage 4

Member Training: Coarsened Exact Matching, an Alternative to Propensity Score Matching

February 29th, 2024 by

The objective for quasi-experimental designs is to establish cause and effect relationships between the dependent and independent variables. However, they have one big challenge in achieving this objective: lack of an established control group.


Member Training: Frailty Models

November 2nd, 2023 by

Most survival analysis models for time-to-event data, like Cox regression, assume independence. The survival time for one individual cannot influence the survival time for another.

This assumption doesn’t hold in many study designs. You may have animals clustered into litters, matched pairs, or patients in a multi-center trial with correlated survival times within a center.


Member Training: Moderated Mediation, Not Mediated Moderation

February 28th, 2023 by

Moderated mediation, also known as Conditional Process Modeling, is great tool for understanding one type of complex relationship among variables.


Member Training: Multinomial Logistic Regression

December 30th, 2022 by

Multinomial logistic regression is an important type of categorical data analysis. Specifically, it’s used when your response variable is nominal: more than two categories and not ordered.

Exogenous and Endogenous Variables in Structural Equation Modeling

July 22nd, 2022 by

In most regression models, there is one response variable and one or more predictors. From the model’s point of view, it doesn’t matter if those predictors are there to predict, to moderate, to explain, or to control. All that matters is that they’re all Xs, on the right side of the equation.


Member Training: Interrupted Time Series

February 28th, 2022 by

Interrupted time series analysis is a useful and specialized tool for understanding the impact of a change in circumstances on a long-term trend. The data for interrupted time series is a specific type of longitudinal data and must meet two criteria.