QUANTITATIVE PSYCHOLOGY
ASSOCIATE PROFESSOR
Amanda Kay Montoya
UPCOMING EVENTS
One of my primary goals is to present and teach at a variety of conferences and universities. See below for upcoming posters, presentations, and workshops.
For upcoming events for other members of the MAC lab see lab website.
Feel free to contact me if you are interested in hosting a workshop on mediation, moderation, and conditional process modeling or two-instance repeated-measures mediation or moderation analysis.
Calendar of Events
June 8, 2026
Mediation, Moderation, and Conditional Process Analysis I - Hybrid
University of St.Gallen
Statistical mediation and moderation analyses are among the most widely used data analysis techniques in social science, health, and business fields. Mediation analysis is used to test hypotheses about various intervening mechanisms by which causal effects operate. Moderation analysis is used to examine and explore questions about the contingencies or conditions of an effect, also called “interaction”. Increasingly, moderation and mediation are being integrated analytically in the form of what has become known as “conditional process analysis,” used when the goal is to understand the contingencies or conditions under which mechanisms operate. An understanding of the fundamentals of mediation and moderation analysis is in the job description of almost any empirical scholar. In this course, you will learn about the underlying principles and the practical applications of these methods using ordinary least squares (OLS) regression analysis and the PROCESS macro for SPSS, SAS and R invented by the course instructor.
Topics covered in this five-day course include:
- Path analysis: Direct, indirect, and total effects in mediation models.
- Estimation and inference about indirect effects in single mediator models.
- Models with multiple mediators
- Mediation analysis in the two-condition within-subject design.
- Estimation of moderation and conditional effects.
- Probing and visualizing interactions.
- Conditional Process Analysis (also known as “moderated mediation”)
- Quantification of and inference about conditional indirect effects.
- Testing a moderated mediation hypothesis and comparing conditional indirect effects
As an introductory-level course, we focus primarily on research designs that are experimental or cross-sectional in nature with continuous outcomes. We do not cover complex models involving dichotomous outcomes, latent variables, models with more than two repeated measures, nested data (i.e., multilevel models), or the use of structural equation modeling.
This course will be helpful for researchers in any field—including psychology, sociology, education, business, human development, political science, public health, communication—and others who want to learn how to apply the latest methods in moderation and mediation analysis using readily-available software packages such as SPSS, SAS and R.
June 15, 2026
Structural Equation Models
University of St.Gallen
This is an interactive course on data analysis focused on the application of multivariate analysis with latent variables using structural equation models (SEMs). These models can be used to explore research questions involving complex relationships among many variables (specifically multiple outcome variables) and these variables may be observed or latent.
Topics include:
1. Introduction to and History of Structural Equation Models.
2. Model Notation
3. Path Tracing Rules and Covariance Algebra
4. Total, Direct, and Indirect Effects
5. Identification and Estimation with Observed Variables
6. Understanding Measurement Error, Validity, and Reliability
7. Confirmatory Factor Analysis
8. Identification, Estimation, and Evaluation with Latent Variables
9. Accounting for Missing Data
10. Mean Structures and Latent Means Models
11. Categorical Data and Multiple Group Models
This course will be helpful for researchers in any field—including psychology, sociology, education, business, human development, political science, public health, communication—and others who want to learn how to apply the latest methods in latent variable and structural equation models using readily-available software in R.
PAST EVENTS
Simple Slopes and Johnson-Neyman Probing Methods Extended to Two-Condition Within-Subjects Designs
Annual Convention for the Association for Psychological Science
Poster Session XVII, Board Number XVII-95
Sunday, May 28, 2017 10:00 AM - 10:50 AM
APS Exhibit Hall
Sheraton Boston Hotel
Boston, MA
For two-condition within-subject designs, this research generalizes the simple slopes and Johnson-Neyman technique to probing interactions between a within-subject factor and a stable covariate and generalizes to multiple moderator models. I have created a macro for SPSS and SAS to simplify computations and facilitate implementation by researchers.
SMEP Poster
Introduction to R through Mediation and Moderation
University of Washington, Dept. of Psychology
May 17th, 2017 9:00am - 4:00pm
Savery 117 (The Big Lab)
University of Washington
Seattle, WA
This workshop will provide an introduction to R by teaching researchers to conduct mediation and moderation analyses. The morning section will focus on basic R skills and an introduction to linear models in R. The next sections will show researchers how to reproduce mediation and moderation analyses, frequently conducted using PROCESS in SPSS and SAS, but in R. Special focus will be given to writing resampling procedures and probing interactions by hand. Registration for this workshop is limited, and University of Washington personnel will be given priority. If you are interested in attending this workshop please contact Brian Flaherty at bxf4@u.washington.edu.
Cautions on Using Model Fit to Choose Number of Factors in EFA
National Council on Measurement in Education
April 28th, 2017 12:25pm - 1:55pm
Issues in Model-data (mis)fit
San Antonio Marriott Rivercenter
San Antonio, TX
Researchers often use fit indices to determine the number of factors to retain in EFA. We caution against this, as existing cut-off recommendations do not work well and the fit statistics are dependent on attributes unrelated to the number of factors (e.g., overall misfit of the model and correlated residuals).
Estimating and Probing Interactions in Two Instance Repeated-Measures Designs
Methodological Colloquium Series
March 24st, 2017 12pm - 1pm
136 Ramseyer Hall
College of Education and Human Ecology
Ohio State University
Columbus, OH
Education researchers have become increasingly focused on understanding when or or whom certain effects occur; statistical moderation analysis assists in answering these questions. Though within-subjects designs often boast the advantage of increased power and provide often more valid tests of intra-individual hypotheses, the analytical methods for testing and probing moderation are less well understood for these designs than between subjects designs. Judd et al (1996) describe a regression based approach for estimating moderation analysis in two instance repeated measures designs. My research explicitly shows how to estimate and conduct inference on conditional effects using the regression framework outlined by Judd et al. (1996). I will show how to estimate both the conditional effect of a repeated-measures factor on an outcome for values of a between-participant variable as well as the conditional effect of the between participant variable on the outcome for values of the repeated-measures factor. I use the principles outlined in Bauer and Curran (2005) to derive the simple-slopes method and Johnson-Neyman approach for the specific case of two-condition within-subjects designs. To facilitate the adoption of this approach, I provide an easy-to-use and freely available macro for SPSS and SAS, and a full worked example with code for this macro, to help researchers adopt this new method.
MEMORE: Mediation and Moderation in Repeated Measures Designs
Society for Personality and Social Psychology Annual Meeting
January 21st, 2017 3:30pm - 6:15pm
San Antonio Convention Center, Rm 209
San Antonio, TX
This workshop overviews mediation and moderation analysis in repeated-measures designs when the independent variable of interest is a within-participant factor. We will cover implementation (using a freely available tool for SPSS and SAS) interpretation for questions of mediation and moderation in these designs. Participants are strongly encouraged to bring laptops.
Using MEMORE: Mediation in Two-Instance Repeated Measures Designs
Social Psychology Graduate Student Workshop Series
Thursday, September 8th, 2016 4pm - 5pm
Columbus, OH
This workshop will focus on using MEMORE, a new tool for SPSS/SAS, to estimate and test indirect effects when the causal variable of interest is a two-instance repeated measures factor. We will also discuss more than two-conditions, longitudinal mediation, and multilevel mediation.
This workshop is organized by the OSU Social Psychology Graduate Students, but outside attendees are welcome. Please contact Ashley Brown at brown.5497@buckeyemail.osu.edu if you are interested in attending.
Two Condition Within-Subjects Mediation: Power and Type I Error for Methods of Inference for the Indirect Effect
Southeastern Psychological Association Annual Meeting
March 30th - April 2nd, 2016
New Orleans, LA
I will present a way to reframe the “causal-steps” approach for mediation with a two-condition within-subjects design, as described by Judd, Kenny, and McClelland (2001), to a path analytic framework. The analytic approach I will present applies particularly to designs where the within-person manipulation X is proposed to cause some outcome through a mediator(s) and the researcher has a measure of the proposed mediators and outcome for each variation of X. Using this framework allows for an estimate of a total effect which partitions into an estimate of the direct and indirect effect. Having an estimate of the indirect effect opens doors to a number of methods of inference about the indirect effect, based on previous practice in cross-sectional mediation. Using a broad Monte-Carlo simulation, I examined the performance of different methods of inference for indirect effects in these designs. The results of this simulation suggest that methods which do not rely on assumptions of normality of the indirect effect, such as bootstrapping or Monte Carlo confidence intervals, provide better power and closer to expected Type I error, than methods which assume normality, such as the Sobel test. These results replicate simulation results from the literature on cross-sectional mediation. Additionally, I will discuss study factors which might result in reduced power (e.g. high correlation among repeated measurements of the mediator), how to plan high-powered studies using repeated-measures designs, and a new macro available for SPSS and SAS called MEMORE which can be used to easily estimate these models and provide results from all of the inferential tests described in this presentation.
Conditional Process Analysis: Moderation of Mediation
Southeastern Psychological Association Annual Meeting
March 30th - April 2nd, 2016
New Orleans, LA
The purpose of this workshop is to review mediation and moderation analysis and focus on integrating these in conditional process analysis. Conditional process analysis examines if the potential paths through which one variable may influence another depends on a potential moderator. I will use PROCESS a freely available macro for SPSS and SAS to show implementation of these analyses. The presentation will be in lecture format, with “work-along” examples throughout. Datasets, slides, and code will be provided online and a hardcopy of the slides will be provided. Participants are encouraged to bring a device with SPSS or SAS.
Estimating and Comparing Indirect Effects in Two-Condition Within-Subject Multiple Mediator Models
Annual Convention of the Society of Personality and Social Psychology
Friday, January 29th, 2016 2pm
San Diego, CA
Statistical mediation analysis is commonly used in social psychological research, but primarily using data from between-subjects experimental and cross-sectional observational designs. Within-subjects designs are popular in social psychology, such as when subjects experience multiple versions of a stimulus representing X and are measured on mediators M and outcomes Y in response to each version of the stimulus. Mediation analysis for these designs has not received as much attention by methodologists and has focused exclusively on single mediator models. In this talk, I discuss extensions of the Judd et al. (2001, Psychological Methods) approach to mediation in the two-condition within-subjects design with multiple mediators, including parallel and serial models. I discuss estimation, inference and comparison of indirect effects and demonstrate implementation using a new macro for SPSS and SAS that does all the computations.