University of Ljubljana

The summary or overview of a course includes the course content and structure, the prerequirements, a brief description of the learning objectives, mandatory and/or voluntary course literature as well as important examination information.

Prerequisites (knowledge of topic)
There is no prerequisite knowledge. However, familiarity with principles of experimental design is very useful, as the course delves deep into conceptual and practical aspects of conducting experimental research online.

Students will complete course work on their own laptop computers.

The course will rely on several online research tools, including Prolific, Qualtrics, asPredicted, and more. Accounts are typically free to open (at least in trial version).

Learning objectives 
On successful completion of this course, students will be able to:
– conduct online “lab” surveys and experiments on alternative platforms
– maximize data quality in online “lab” studies
– use advanced features to conduct richer and more innovative online “lab” studies
– design online “field” studies on social media platforms and beyond
– increase the reproducibility, replicability, and publishability of students’ own research

Course content
The Internet is revolutionizing how empirical research is conducted across the social sciences. Without the need for intermediaries, individual researchers can now conduct large-scale experiments on human participants, longitudinal surveys of rare populations, A/B tests on social media, and more. In this course, you will learn how to harness these opportunities while avoiding the many pitfalls of online research. The course is tailored for researchers in psychology, economics, business, and any other area of academia or industry who investigate human behavior.


We will cover the nuts and bolts of conducting “lab” experiments on alternative Internet platforms, including techniques to maximize the validity and reproducibility of research findings. We will also discuss how to unlock the potential of the Internet for more elaborate, richer designs that go beyond simple survey experiments (e.g., diary studies, “field” studies on social media), gathering externally valid insights about consumers, workers, and Internet users more generally. Importantly, technical and practical insights will explicitly serve the goal to improve the rigor and the publishability of participants’ own research. To this end, we will include discussions on whether and how to combine online and offline investigations, how to preregister and report online research in a paper, and more.

Every day, morning sessions are prevalently, though not exclusively,  devoted to introducing and criticizing new concepts and techniques in online behavioral research. Afternoon sessions are mostly devoted to putting this content in practice, with students designing, setting up, and discussing their own online research applications.

Day 1: Conducting virtual “lab” studies

How is online “lab” research different

Choosing between platforms: MTurk, Prolific, and more

Choosing within platforms: power, pay, and more

Day 2: Sampling Matters

Online sampling bias(es)

Recruiting representative, rare, recurring participants

Unselective and Selective Attrition

Day 3: Data Quality

Inattentive, Deceptive, Non-naive participants

More concerns with data quality

Making the lab open (e.g., preregistration for online research)

Day 4: Beyond “simple” studies

Beyond simple “lab” studies

Field studies on social media and beyond

Navigating validity trade-offs in online behavioral research 

Day 5: Project Presentations



Recommended Overviews:

Boegershausen, J., Yi, S., Cornil, Y. & Hardisty, D. J. (working paper). Testing the Digital Frontier: Opportunities and Validity Trade-offs in Digital Quasi-Experiments.

Goodman and Paolacci (2017), “Crowdsourcing Consumer Research,” Journal of Consumer Research, 44, 1, 196-210.

Hauser, D., Paolacci, G., Chandler, J. (2019). Common Concerns with MTurk as a Participant Pool. Evidence and Solutions. In Handbook of Research Methods in Consumer Psychology, ed. F. R. Kardes, P. M. Herr, and N. Schwarz, Routledge.

Mosleh, M., Pennycook, G., & Rand, D. G. (2022). Field experiments on social media. Current Directions in Psychological Science, 31(1), 69-75.


Additional Background Readings:

Arechar, A. A., Gächter, S., & Molleman, L. (2018). Conducting interactive experiments online. Experimental Economics, 21(1), 99–131. 

Casey, L. S., Chandler, J., Levine, A. S., Proctor, A., & Strolovitch, D. Z. (2017). Intertemporal differences among MTurk workers. SAGE Open, 7(2).

Chandler, J (forthcoming). Participant Recruitment. In Cambridge Handbook of Research Methods and Statistics for the Social and Behavioral Sciences. Austin Lee Nichols and John E. Edlund (Eds.)

Chandler, J., Paolacci, G. (2017). Lie for a Dime: When Most Prescreening Responses Are Honest but Most Study Participants Are Impostors. Social Psychological and Personality Science, 8(5), 500-508.

Chandler, J., Paolacci, G., Hauser, D. (2020). Data Quality Issues on MTurk. In Conducting Online Research on Amazon Mechanical Turk and Beyond, ed. L. Litman, Sage.

Coppock, A. (2018). Generalizing from survey experiments conducted on Mechanical Turk: A replication approach. Political Science Research and Methods, 1–16.

Chandler, J., Mueller, P., Paolacci, G. (2014). Nonnaïveté Among Amazon Mechanical Turk Workers: Consequences and Solutions for Behavioral Researchers. Behavior Research Methods, 46(1), 112-130.

Chandler, J., Sisso, I., & Shapiro, D. (2020). Participant carelessness and fraud: Consequences for clinical research and potential solutions. Journal of Abnormal Psychology, 129(1), 49–55.

Curran, P. G. (2016). Methods for the detection of carelessly invalid responses in survey data. Journal of Experimental Social Psychology, 66, 4–19.

Eckles, D., Gordon, B. R., & Johnson, G. A. (2018). Field Studies of Psychologically Targeted Ads Face Threats to Internal Validity. Proceedings of the National Academy of Sciences, 115(23), E5254.

Goldfarb, A., Tucker, C., & Wang, Y. (2022). Conducting research in marketing with quasi-experiments. Journal of Marketing, 86(3), 1-20.

LeBel, E. P., McCarthy, R. J., Earp, B. D., Elson, M., & Vanpaemel, W. (2018). A Unified Framework to Quantify the Credibility of Scientific Findings. Advances in Methods and Practices in Psychological Science, 1, 389-402.

Mize, T. D., & Manago, B. (2022). The past, present, and future of experimental methods in the social sciences. Social Science Research, 108, 102799.

Molnar, A. (2019). SMARTRIQS: A Simple Method Allowing Real-Time Respondent Interaction in Qualtrics Surveys. Journal of Behavioral and Experimental Finance, 22, 161-169.

Morales, A. C., Amir, O., & Lee, L. (2017). Keeping it real in experimental research—Understanding when, where, and how to enhance realism and measure consumer behavior. Journal of Consumer Research, 44(2), 465-476.

Moss, A. J., Rosenzweig, C., Robinson, J., & LItman, L. (2020). Is it ethical to use Mechanical Turk for behavioral research? Relevant data from a representative survey of MTurk participants and wages. PsyArXiv. 

Munafò, M. R., Nosek, B. A., … & Ioannidis, J. (2017). A manifesto for reproducible science. Nature Human Behaviour, 1(1), 1-9.

Orazi, D. C., & Johnston, A. C. (2020). Running field experiments using Facebook split test. Journal of Business Research, 118, 189-198.

Paolacci, G., Chandler, J., Ipeirotis, P. G. (2010). Running Experiments on Amazon Mechanical Turk. Judgment and Decision Making, 5(5), 411-419. 

Paolacci, G., Chandler, J. (2014). Inside the Turk: Understanding Mechanical Turk as a participant pool. Current Directions in Psychological Science, 23(3), 184-188. 

Peer, E., Rotschild, D., Gordon, A., Evernden, Z., Damer, E. (2022). Data quality of platforms and panels for online behavioral research. Behavior Research Methods, 54: 1643-1662.

Simons, D. J., Shoda, Y., & Lindsay, D. S. (2017). Constraints on generality (COG): A proposed addition to all empirical papers. Perspectives on Psychological Science, 12(6), 1123-1128

Simmons, J., D Nelson, L., & Simonsohn, U. (2021). Pre‐registration: Why and how. Journal of Consumer Psychology, 31(1), 151-162.  

Weinberg, J., Freese, J., & McElhattan, D. (2014). Comparing data characteristics and results of an online factorial survey between a population-based and a crowdsource-recruited sample. Sociological Science, 1, 292–310.

Woike, J. K. (2019). Upon repeated reflection: Consequences of frequent exposure to the cognitive reflection test for Mechanical Turk participants. Frontiers in Psychology, 10. 

Zallot, C., Paolacci, G., Chandler, J., Sisso, I. (2022). Crowdsourcing in observational and experimental research. Handbook of Computational Social Science. Volume 2 Data Science, Statistical Modelling, and Machine Learning Methods, eds. U. Engel, A. Quan-Haase, S. Xun Liu, & L.E. Lyberg, Routledge. 

Zhou, H., & Fishbach, A. (2016). The pitfall of experimenting on the web: How unattended selective attrition leads to surprising (yet false) research conclusions. Journal of Personality and Social Psychology, 111(4), 493–504. 

Examination part
Performance will be evaluated with an individual assignment to be handed in at the end of the course. Students will design, program, and preregister an online “lab” study testing their own hypothesis. They will detail and justify their methodological choices (e.g., how they avoided the validity threats discussed in the course), and propose how to complement this “lab” approach with more ecologically valid (e.g., field) online investigations.

Supplementary aids
The assignments are “open book”. Lecture slides and notes are recommended, and all background readings are additional recommended sources.

Examination content
Lecture slides and notes.

Examination relevant literature
Lecture slides and notes.

Many fields of science are transitioning from null hypothesis significance testing (NHST) to Bayesian data analysis. Bayesian analysis provides rich information about the relative credibilities of all candidate parameter values for any descriptive model of the data, without reference to p values. Bayesian analysis applies flexibly and seamlessly to complex hierarchical models and realistic data structures, including small samples, large samples, unbalanced designs, missing data, censored data, outliers, etc. Bayesian analysis software is flexible and can be used for a wide variety of data-analytic models.

This course shows you how to do Bayesian data analysis, hands on, with free Software called R and JAGS. The course will use new programs and examples. This course is closely modeled on the very successful series of Workshops given by Prof. John Kruschke. We will be using his software, and I strongly recommend his book (see below) and his blog: doingbayesiandataanalysis.blogspot.com.

Course Objectives:

  • The rich information provided by Bayesian analysis and how it differs from traditional (Frequentist) statistical analysis
  • The concepts of Bayesian reasoning along with the easy math and intuitions for Bayes’ rule
  • The concepts and hands-on use of modern algorithms (“Markov chain Monte Carlo”) that achieve Bayesian analysis for realistic applications
  • How to use the free software R and JAGS for Bayesian analysis, readily useable and adaptable for your research applications
  • An extensive array of applications, including comparison of two groups, ANOVA-like designs, linear regression, and logistic regression.
  • How to apply Bayesian estimation to hierarchical (multi-level) models. See more details in the list of topics, below.
  • What to look for when doing data analysis in a variety of other software settings, including SPSS, SAS, JASP, M-Plus and packages like brms or r-stan-arm in R.

Course Audience
The intended audience is advanced students, faculty, and other researchers, from all disciplines, who want a ground-floor introduction to doing Bayesian data analysis.

No specific mathematical expertise is presumed. In particular, no matrix algebra is used in the course. Some previous familiarity with statistical methods such as a t-test or linear regression can be helpful, as is some previous experience with programming in any computer language, but these are not critical.

It is important to bring a Notebook Computer to the course, so you can run the programs and see how their output corresponds with the presentation material. Please install the software before arriving at the course. The software and programs are occasionally updated, so please check here a week before the course to be sure you have the most recent versions. For complete installation instructions, please go to:




Day 1

  • Overview / Preview: Bayesian reasoning generally. (See this introductory chapter)
  • Robust Bayesian estimation of difference of means. Software: R, JAGS, etc.
  • NHST t test: Perfidious p values and the con game of confidence intervals.
  • Bayes’ rule, grid approximation, and R. Example: Estimating the bias of a coin.
  • Markov Chain Monte Carlo and JAGS. Example: Estimating parameters of a normal distribution.
  • HDI, ROPE, decision rules, and null values.

Day 2

  • Hierarchical models: Example of means at individual and group levels. Shrinkage.
  • Examples with beta distributions: therapeutic touch, baseball, meta-analysis of extrasensory perception.
  • The generalized linear model.
  • Simple linear regression. Exponential regression. Sinusoidal regression, with autoregression component.
  • How to modify a program in JAGS & rjags for a different model.
  • Robust regression for accommodating outliers, for all the models above and below.
  • Multiple linear regression.
  • Logistic regression.
  • Ordinal regression.
  • Hierarchical regression models: Estimating regression parameters at multiple levels simultaneously.

Day 3

  • Hierarchical model for shrinkage of regression coefficients in multiple regression.
  • Variable selection in multiple linear regression.
  • Model comparison as hierarchical model. The Bayes factor. Doing it in JAGS.
  • Two Bayesian ways to assess null values: Estimation vs model comparison.

Day 4

  • Bayesian hierarchical oneway “ANOVA”. Multiple comparisons and shrinkage.
  • Example with unequal variances (“heteroscedasticity”).
  • Bayesian hierarchical two way “ANOVA” with interaction. Interaction contrasts.
  • Split plot design.
  • Log-linear models and chi-square test.
  • Bayesian generalized linear models in other statistical software packages

Day 5

  • Power: Probability of achieving the goals of research. Applied to Bayesian estimation of two groups.
  • Sequential testing.
  • The goal of achieving precision, instead of rejecting/accepting a null value.
  • How to report a Bayesian analysis.
  • Catch-up and individual consultations

Highly recommended textbook:
Doing Bayesian Data Analysis, 2nd Edition: A Tutorial with R, JAGS, and Stan. The book is a genuinely accessible, tutorial introduction to doing Bayesian data analysis. The software used in the course accompanies the book, and many topics in the course are based on the book. (The course uses the 2nd edition, not the 1st edition.) Further information about the book can be found at https://sites.google.com/site/doingbayesiandataanalysis/.

Install software before arriving:
It is important to bring a notebook computer to the course, so you can run the programs and see how their output corresponds with the presentation material. Please install the software before arriving at the course. The software and programs are occasionally updated, so please check here a week before the course to be sure you have the most recent versions.

For complete installation instructions, please go to https://sites.google.com/site/doingbayesiandataanalysis/software-installation

Examination information
Examination paper written at home

Prerequisites (knowledge of topic)
This course assumes no prior experience with machine learning or R, though it may be helpful to be familiar with introductory statistics and programming.

A laptop computer is required to complete the in-class exercises.

R (https://www.r-project.org/) and R Studio (https://www.rstudio.com/products/rstudio/) are available at no cost and are needed for this course.

Course content
Machine learning, put simply, involves teaching computers to learn from experience, typically for the purpose of identifying or responding to patterns or making predictions about what may happen in the future. This course is intended to be an introduction to machine learning methods through the exploration of real-world examples. We will cover the basic math and statistical theory needed to understand and apply many of the most common machine learning techniques, but no advanced math or programming skills are required. The target audience may include social scientists or practitioners who are interested in understanding more about these methods and their applications. Students with extensive programming or statistics experience may be better served by a more theoretical course on these methods.

The course will be designed to be interactive, with ample time for hands-on practice with the Machine Learning methods. Each day will include several lectures based on a Machine Learning topic, in addition to hands-on “lab” sections to apply the learnings to new datasets (or your own data, if desired).

The schedule will be as follows:

Day 1: Introducing Machine Learning with R
  • How machines learn
  • Using R, R Studio, and R Markdown
  • k-Nearest Neighbors
  • Lab sections – installing R, using R Markdown, choosing own dataset (if desired)

Day 2: Intermediate ML Methods – Classification Models
  • Quiz on Day 1 material
  • Naïve Bayes
  • Decision Trees and Rule Learners
  • Lab sections – practicing with Naïve Bayes and decision trees
Day 3: Intermediate ML Methods – Numeric Prediction
  • Quiz on Day 2 material
  • Linear Regression
  • Regression trees
  • Logistic regression
  • Lab sections – practicing with regression methods
Day 4: Advanced Classification Models
  • Quiz on Day 3 material
  • Neural Networks
  • Support Vector Machines
  • Random Forests
  • Lab section – practice with neural networks, SVMs, and random forests

Day 5: Other ML Methods
  • Quiz on Day 4 material
  • Association Rules
  • Hierarchical clustering
  • k-Means clustering
  • Lab section – practice with these methods, work on final report


Machine Learning with R (3rd ed.) by Brett Lantz (2019). Packt Publishing

Supplementary / voluntary
None required.

Mandatory readings before course start
Please install R and R Studio on your laptop prior to the 1st class. Be sure that these are working correctly and that external packages can be installed. Instructions for doing this are in the first chapter of Machine Learning with R.

Examination part
100% of the course grade will be based on a project and final report (approximately 10 pages), to be delivered within 2-3 weeks after the course. The project is intended to demonstrate your ability to apply the course materials to a dataset of your own choosing. Students should feel free to use a project related to their career or field of study. For example, one may use this opportunity to advance his/her dissertation research or complete a task for his/her job. The exact scoring criteria for this assignment will be provided on the first day of class. This will be graded based on its use of the methods covered in class as well as making appropriate conclusions from the data.

There will also be brief quizzes at the start of each lecture, which cover the previous day’s materials. These are ungraded and are designed to provoke thought and discussion.

Supplementary aids
Students may reference literature and class materials as needed when writing the final project report.

Examination content

The final project report should illustrate an ability to apply machine learning methods to a new dataset, which may be on a topic of the student’s choosing. The student should explore the data and explain the methods applied. Detailed instructions will be provided on the fist day of class.

Prerequisites (knowledge of topic)
Basic knowledge of Python programming and familiarity with Machine Learning

A laptop

A google account to access colab

Learning objectives
On successful completion of this course, students will be able to:

– Understand the fundamentals of Generative AI and Large Language Models.
– Understand how to Implement and fine-tune LLMs for various tasks.
– Evaluate the performance of LLMs using various metrics.
– Understand the ethical and societal implications of using LLMs.
– Develop their own projects utilizing Generative AI.


Day 1: Introduction to Generative AI

Generative vs. Discriminative Models

Overview of Generative AI

Applications of generative AI


Day 2: Basics of Language Models

Understanding Language Models

Unigram, Bigram, N-gram Models

Neural network based (seq2seq) Language Models


Day 3: Transformer Models and Attention Mechanism

Introduction to Transformer Models

Self-Attention and Multi-Head Attention



Day 4: Large Language Models (LLMs)

Introduction to LLMs

Architecture of GPT-4

Fine-tuning LLMs


Day 5: Evaluating and Improving LLMs

Evaluation metrics

Issues in LLMs

Prompt engineering


We will have a take-home exam.

Supplementary aids
Open Book

Examination Content
Students are expected to work on one individual project related to the application of LLMs on a specific domain (e.g., healthcare, finance, or social marketing).


Prerequisites (knowledge of topic)
Comfortable familiarity with univariate differential and integral calculus, basic probability theory, and linear algebra is required. Students should have completed Ph.D.-level courses in introductory statistics, and in linear and generalized linear regression models (including logistic regression, etc.), up to the level of Regression III. Familiarity with discrete and continuous univariate probability distributions will be helpful.

Students will be required to provide their own laptop computers.

All analyses will be conducted using the R statistical software. R is free, open-source, and runs on all contemporary operating systems. The instructor will also offer support for students wishing to use Stata.

Learning objectives
Students will learn how to visualize, analyze, and conduct diagnostics on models for observational data that has both cross-sectional and temporal variation.

Course content

Analysts increasingly find themselves presented with data that vary both over cross-sectional units and across time. Such panel data provides unique and valuable opportunities to address substantive questions in the economic, social, and behavioral sciences. This course will begin with a discussion of the relevant dimensions of variation in such data, and discuss some of the challenges and opportunities that such data provide. It will then progress to linear models for one-way unit effects (fixed, between, and random), models for complex panel error structures, dynamic panel models, nonlinear models for discrete dependent variables, and models that leverage panel data to make causal inferences in observational contexts. Students will learn the statistical theory behind the various models, details about estimation and inference, and techniques for the visualization and substantive interpretation of their statistical results. Students will also develop statistical software skills for fitting and interpreting the models in question, and will use the models in both simulated and real data applications. Students will leave the course with a thorough understanding of both the theoretical and practical aspects of conducting analyses of panel data.

Day One:
•     (Very) Brief Review of Linear Regression
•     Overview of Panel Data: Visualization, Pooling, and Variation
•     Regression with Panel Data
•     Unit Effects Models: Fixed-, Between-, and Random-Effects

Day Two:
•     Dynamic Panel Data Models: The Instrumental Variables / Generalized Method of Moments Framework
•     More Dynamic Models: Orthogonalization-Based Methods

Day Three:
•     Unit-Effects and Dynamic Models for Discrete Dependent Variables
•     GLMs for Panel Data: Generalized Estimating Equations (GEEs)

Day Four:
•     Introduction to Causal Inference with Panel Data (Including Unit Effects)
•     Models for Causal Inference: Differences-In-Differences, Synthetic Controls, and Other Methods

Day Five:
•     Practical Issues: Model Selection, Specification, and Interpretation
•     Course Examination


Hsiao, Cheng. 2014. Analysis of Panel Data, 3rd Ed. New York: Cambridge University Press.
Croissant, Yves, and Giovanni Millo. 2018. Panel Data Econometrics with R. New York: Wiley.

Supplementary / voluntary
Abadie, Alberto. 2005. “Semiparametric Difference-in-Differences Estimators.” Review of Economic Studies 72:1-19.

Anderson, T. W., and C. Hsiao. 1981. “Estimation Of Dynamic Models With Error Components.” Journal of the American Statistical Association 76:598-606.

Antonakis, John, Samuel Bendahan, Philippe Jacquart, and Rafael Lalive. 2010. “On Making Causal Claims: A Review and Recommendations.” The Leadership Quarterly 21(6):1086-1120.

Arellano, M. and S. Bond. 1991. “Some Tests Of Specification For Panel Data: Monte Carlo Evidence And An Application To Employment Equations.” Review of Economic Studies 58:277-297.

Beck, Nathaniel, and Jonathan N. Katz. 1995. “What To Do (And Not To Do) With Time-Series Cross-Section Data.” American Political Science Review 89(September): 634-647.

Bliese, P. D., D. J. Schepker, S. M. Essman, and R. E. Ployhart. 2020. “Bridging Methodological Divides Between Macro- and Microresearch: Endogeneity and Methods for Panel Data.” Journal of Management, 46(1):70-99.

Clark, Tom S. and Drew A. Linzer. 2015. “Should I Use Fixed Or Random Effects?” Political Science Research and Methods 3(2):399-408.

Doudchenko, Nikolay, and Guido Imbens. 2016. “Balancing, Regression, Difference-In-Differences and Synthetic Control Methods: A Synthesis.” Working paper: Graduate School of Business, Stanford University.

Gaibulloev, K., Todd Sandler, and D. Sul. 2014. “Of Nickell Bias, Cross-Sectional Dependence, and Their Cures: Reply.” Political Analysis 22: 279-280.

Hill, T. D., A. P. Davis, J. M. Roos, and M. T. French. 2020. “Limitations of Fixed-Effects Models for Panel Data.” Sociological Perspectives 63:357-369.

Hu, F. B., J. Goldberg, D. Hedeker, B. R. Flay, and M. A. Pentz. 1998. “Comparison of population-averaged and subject-specific approaches for analyzing repeated binary outcomes.” American Journal of Epidemiology 147(7):694-703.

Imai, Kosuke, and In Song Kim. 2019. “When Should We Use Unit Fixed Effects Regression Models for Causal Inference with Longitudinal Data?” American Journal of Political Science 62:467-490.

Keele, Luke, and Nathan J. Kelly. 2006. “Dynamic Models for Dynamic Theories: The Ins and Outs of Lagged Dependent Variables.” Political Analysis 14(2):186-205.

Lancaster, Tony. 2002. “Orthogonal Parameters and Panel Data.” Review of Economic Studies 69:647-666.

Liu, Licheng, Ye Wang, Yiqing Xu. 2019. “A Practical Guide to Counterfactual Estimators for Causal Inference with Time-Series Cross-Sectional Data.” Working paper: Stanford University.

Mummolo, Jonathan, and Erik Peterson. 2018. “Improving the Interpretation of Fixed Effects Regression Results.” Political Science Research and Methods 6:829-835.

Neuhaus, J. M., and J. D. Kalbfleisch. 1998. “Between- and Within-Cluster Covariate Effects in the Analysis of Clustered Data. Biometrics, 54(2): 638-645.

Pickup, Mark and Vincent Hopkins. 2020. “Transformed-Likelihood Estimators for Dynamic Panel Models with a Very Small T.” Political Science Research & Methods, forthcoming.

Xu, Yiqing. 2017. “Generalized Synthetic Control Method: Causal Inference with Interactive Fixed Effects Models.” Political Analysis 25:57-76.

Zorn, Christopher. 2001. “Generalized Estimating Equation Models for Correlated Data: A Review with Applications.” American Journal of Political Science 45(April):470-90.

Mandatory readings before course start

Hsiao, Cheng. 2007. “Panel Data Analysis — Advantages and Challenges.” Test 16:1-22.

Examination part
Students will be evaluated on two written homework assignments that will be completed during the course (20% each) and a final examination (60%). Homework assignments will typically involve a combination of simulation-based exercises and “real data” analyses, and will be completed during the evenings while the class is in session. For the final examination, students will have two alternatives:

•    “In-Class”: Complete the final examination in the afternoon of the last day of class (from roughly noon until 6:00 p.m. local time), or

•    “Take-Home”: Complete the final examination during the week following the end of the course (due date: TBA).

Additional details about the final examination will be discussed in the morning session on the first day of the course.

Supplementary aids

The exam will be a “practical examination” (see below for content). Students will be allowed access to (and encouraged to reference) all course materials, notes, help files, and other documentation in completing their exam.

Examination content

The examination will involve the application of the techniques taught in the class to one or more “live” data example(s). These will typically take the form of either (a) a replication and extension of an existing published work, or (b) an original analysis of observational data with a panel / time-series cross-sectional component. Students will be required to specify, estimate, and interpret various statistical models, to conduct and present diagnostics and robustness checks, and to give detailed justifications for their choices.

Examination relevant literature
See above. Details of the examination literature will be finalized prior to the start of class.

Prerequisites (knowledge of topic)

Participants should have a basic working knowledge of the principles and practice of multiple regression and elementary statistical inference. Because this is a second course, participants should either be familiar with the contents of the first edition of Introduction to Mediation, Moderation, and Conditional Process Analysis and the statistical procedures discussed therein or should have taken the first course through GSERM or elsewhere. Participants should also have experience using syntax in SPSS, SAS, or R, and it is assumed that participants will already have some experience using the PROCESS macro. No knowledge of matrix algebra is required or assumed, nor is matrix algebra ever used in the course.



Students are strongly encouraged to bring their own laptops (Mac or Windows)



Laptops need a recent version of SPSS Statistics (version 19 or later), SAS (release 9.2 or later) or R (3.6 or later) installed. SPSS users should ensure their installed copy is patched to its latest release. SAS users should ensure that the IML product is part of the installation. STATA users can benefit from the course content, but PROCESS makes these analyses much easier and is not available for STATA.


Learning objectives

  • Apply and report on tests of moderated mediation using the index of moderated mediation
  • Identify models for which partial and conditional moderated mediation are appropriate.
  • Apply and report mediation analysis with multicategorical independent variables.
  • Test and probe an interaction involving a multicategorical independent variable or moderator.
  • Apply and report tests of moderated mediation involving a multicategorical independent variable.
  • Generalize the index of moderated mediation to models with serial mediation
  • Estimate and conduct inference in mediation, moderation, and moderated mediation contexts for two-instance repeated-measures designs.
  • Generate and specify custom models in PROCESS


Course content

Statistical mediation and moderation analyses are among the most widely used data analysis techniques. Mediation analysis is used to test 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 ʺinteraction.ʺ Conditional process analysis is the integration of mediation and moderation analysis and used when one seeks to understand the conditional nature of processes

(i.e., ʺmoderated mediationʺ).


In Introduction to Mediation, Moderation, and Conditional Process Analysis: A Regression‑Based Approach (www.guilford.com/p/hayes3) Dr. Andrew Hayes describes the fundamentals of mediation, moderation, and conditional process analysis using ordinary least squares regression. He also explains how to use PROCESS, a freely‑available and handy tool he invented that brings modern approaches to mediation and moderation analysis within convenient reach.

This seminar‑ a second course ‑picks up where the first edition of the book and the first course offered by GSERM leaves off. After a review of basic principles, it covers material in the second and third editions of the book as well as new material including recently published methodological research.


Topics covered include:

  • Review of the fundamentals of mediation, moderation, and conditional process analysis.
  • Testing whether an indirect effect is moderated and probing moderation of indirect effects.
  • Partial and conditional moderated mediation.
  • Mediation analysis with a multicategorical independent variable.
  • Moderation analysis with a multicategorical (3 or more groups) independent variable or moderator.
  • Conditional process analysis with a multicategorical independent variable
  • Moderation of indirect effects in the serial mediation model.
  • Mediation, Moderation, and Conditional Process Analysis in Two-Instance Repeated-Measures Designs
  • Advanced uses of PROCESS, such as how to modify a numbered model or customize your own model.


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, nested data (i.e., multilevel models), or the use of structural equation modeling.



Day 1:

  • Review of fundamentals
  • Testing whether and indirect effect is moderated
  • Estimating conditional indirect effects

Day 2:

  • Representing multicategorical predictors
  • Mediation analysis with a multicategorical independent variable
  • Estimating Moderation models with a multicategorical independent variable

Day 3:

  • Probing moderation models with a multicategorical independent variable
  • Estimating and probing moderation models with a multicategorical moderator
  • Estimating conditional process models with a multicategorical independent variable

Day 4:

  • Inference and probing of conditional process models with a multicategorical independent variable
  • Conditional process analysis involving serial mediation
  • Custom models in PROCESS

Day 5:

  • Mediation analysis in two-instance repeated-measures designs
  • Moderation analysis in two-instance repeated-measures designs
  • Conditional process analysis in two-instance repeated-measures designs



Introduction to Mediation, Moderation, and Conditional Process Analysis (3rd edition)


Examination part

Homework delivered during week of the course (4 assignments, 60%)

Homework delivered after the course (1 assignment, 40%)


Supplementary aids

Open Book


Examination content

Homework 1 (Due Tuesday Morning):

  • Review of fundamentals
  • Testing whether and indirect effect is moderated
  • Estimating conditional indirect effects

Homework 2 (Due Wednesday Morning):

  • Representing multicategorical predictors
  • Mediation analysis with a multicategorical independent variable
  • Estimating Moderation models with a multicategorical independent variable

Homework 3 (Due Thursday Morning):

  • Probing moderation models with a multicategorical independent variable
  • Estimating and probing moderation models with a multicategorical moderator
  • Estimating conditional process models with a multicategorical independent variable

Homework 4 (Due Friday Morning):

  • Inference and probing of conditional process models with a multicategorical independent variable
  • Conditional process analysis involving serial mediation
  • Custom models in PROCESS

Homework 5 (Due within 2 weeks of end of course):

  • All content listed above+
  • Mediation analysis in two-instance repeated-measures designs
  • Moderation analysis in two-instance repeated-measures designs
  • Conditional process analysis in two-instance repeated-measures designs


Examination relevant literature

Introduction to Mediation, Moderation, and Conditional Process Analysis: A Regression‑Based Approach (www.guilford.com/p/hayes3) Dr. Andrew Hayes