Syllabus

Instructor

  •   Dr. Léo Belzile
  •   4.850, Côte-Sainte-Catherine
  •   <a href=“mailto:leo.belzile@hec.ca”>leo.belzile@hec.ca

Course details

  •   Winter 2024
  •   Monday
  •   8:30-11:30
  •   C-Ste-Cath, Caracas

Course content

Basic concepts for data collection planning; appropriate statistical analyses of these data and interpretation of results. Advantages and disadvantages of the various experimental designs.

This course has four main objectives:

  • to present the major experimental designs used for research in management and in the behavioural sciences;
  • to familiarize students with the statistical methods and a software to analyze experimental data (e.g., SPSS);
  • to interpret and present results from the statistical analyses and discuss the validity and limits of the results;
  • to understand and to critique the methodology and statistical results of published articles in the research fields of the students.

Target audience and prerequisites

The course is part of the PhD program in Administration offered by HEC Montréal jointly with McGill, Concordia and Université du Québec à Montréal (UQÀM).

The course is designed for non-specialists, but a college/freshman/undergraduate level exposition to statistics is assumed. I expect students to know what are data types (continuous, categorical, binary variables), basic graphical representation (histogram, box-and-whisker plots), descriptive statistics (mean, variance), how to perform an hypothesis test (e.g., a t-test for comparing two means, simple linear regression), etc. The pace the first few weeks will be quite fast if you have no prior exposure to statistics.

What we cover, notably analysis of variance, could appear in an undergraduate level course. However, the course is calibrated for PhD students needs (how to write a statistical analysis in a paper, how to assess the statistical methodology of a paper as a peer-reviewer, how to avoid statistical fallacies that could invalidate your work, etc.)

If you want to brush up, I can recommend the free resource Advanced High School Statistics by Open Intro or Diez et al. (2019) — the material is pretty comprehensive and well structured. I expect many students will have at least this level of knowledge.

Programming

Most programming language with dedicated statistics module can be used to perform the analyses we will cover in class1

Property software options include IBM SPSS Statistics (Windows and Mac only) and SAS (Windows only). HEC Montréal provides download for SPSS and SAS, but the latter can be freely accessed using the cloud-based version SAS OnDemand for Academics.2

I am a strong advocate of R and will provide code and material for the latter. There is a steep learning curve, but the user community is vibrant, so most routines of interest have been contributed by other users and you can get support through help forums. You can find instructions for installing R, RStudio, and all the tidyverse packages here.

If you are more comfortable with click-and-drop menus, JAMOVI, PSPP and JASP are suitable open-access options but are limited.

Course materials

I will provide slides and videos. In addition to those, there will be assigned readings from textbook and reference papers.

Textbooks

Course notes for the class can be found online.

A comprehensive reference is Maxwell et al. (2017), which is available via HEC’s library online. I will also assign readings from Meier (2022) ANOVA and Mixed Models: A Short Intro Using R, which is available online for free reading.

Other references

  • Keppel & Wickens (2004): out of print; comprehensive reference with a focus on effect size and marginal effects, all calculations are done by hand.
  • Cox (1958): out of print, but beautifully written and nontechnical.

Course content

Below is a tentative schedule for the semester.

  1. Introduction and motivation
    • Review (population and samples, observational versus experimental studies)
    • Introduction to experimental designs
    • Terminology and key concepts of experimental design
    • Requirements for a good experiment
  2. Review of key statistics concepts
    • Sampling variability
    • Hypothesis testing
    • Confidence intervals
    • Examples of basic tests
      • two sample t-test and Welch’s t-test
      • chi-square test for contingency table
      • permutation test
  3. Completely randomized designs with one factor
    • Introduction to one-way analysis of variance
    • \(F\)-statistic and sum of square decomposition
    • Parametrization
    • Model assumptions
  4. Contrasts and multiple testing
    • Contrasts
    • Multiple testing, family-wise error rate and false discovery rate
    • Methods for control: methods for ANOVA (Tukey, Dunnett and Scheffé)
    • General methods (Bonferroni, Holm and Benjamini-Hochberg)
  5. Completely randomized designs with two factors
    • Interactions
    • Marginal and conditional contrasts
  6. General completely randomized designs
    • Unbalanced designs and implications for inference
    • Three-way ANOVA: Simple, marginal and conditional means
  7. Blocked designs and analysis of covariance
    • Designs to reduce the error
    • Terminology (blocking factor, covariate, noise variable)
    • Complete block design
    • Repeated measure designs and tests of sphericity
    • Analysis of covariance and equal slope assumptions
  8. Effect sizes and power
    • Effect sizes
    • Interplay between sample size, effect and power
    • Power calculations
  9. General design principles
    • More general linear regression models
    • Nonparametric tests (rank tests, via linear model)
    • AB testing and stopping rules
    • Repeated measures and tests of sphericity
  10. Mixed models
    • Intro to random effects
    • Linear mixed models
    • Model specification: crossed and nested factors
    • Showcase: replication and meta-analysis
  11. Replication crisis and introduction to causal inference
    • Replication crisis and reproducibility
    • Statistical fallacies
    • Solutions to replication crisis
    • Directed acyclic graphs
    • Types of association: causation, mediation, confounding and collision
  12. Causal inference (continued) and linear mediation model
    • Assumptions for causal inference
    • do-operator and backdoor
    • Baron–Kenny linear mediation model: Sobol’s statistic and introduction to the bootstrap.
    • Linear mediation model
  13. Categorical data analysis and final review
    • Contingency tables and count data
    • Goodness-of-fit, independence, Fisher and McNemar tests
    • Q&A, final review and practice exam

Course policies

Student hours

I am available Monday after class and from 13:30-15:00. My office, 4.850, is located next to the southern elevators in Côte-Sainte-Catherine building.

Please watch this video:

Student hours are set times dedicated to all of you (most professors call these “office hours”; I don’t3). This means that I will be in my office waiting for you to come by if you want to talk to me in person (or remotely) with whatever questions you have. This is the best and easiest way to find me and the best chance for discussing class material and concerns.

Late work

Problem sets and weekly check-ins are due by Sunday. Timely submission will allow me to discuss problem sets in class. The submission modules will stay open for two weeks after the due date. I will not assign late work penalties, but will gently nudge you to stay on track.

Intellectual integrity

Please don’t cheat! The official policy lists the school rules regarding plagiarism and academic integrity.

Student services

Students with special needs should feel free to approach me so we can best discuss accommodations. Do check out HEC Montréal’s disabled students and [psychological] (https://www.hec.ca/en/students/support-resources/psychological-support/index.html) support services.

Harassment and sexual violence

The Center for Harassment Intervention (BIMH) is the unique access point for all members of the community subject to harassment or sexual violence. You can reach them at 514 343-7020 or by email at harcelement@hec.ca from Monday until Friday, from 8:30 until 4:30pm.

If you are in an emergency situation or fear for your safety, call emergency services at 911, followed by HEC Montréal security services at 514 340-6611.

Check the school official policy on these matters for more details.

Family policy

HEC does not have an official family policy, so the following guidelines reflect my own beliefs and commitments towards parent students4

  1. Babies are welcome in class as often as necessary for support feeding relationship.
  2. You are welcome to bring your child to class in order to cover unforeseeable gaps in childcare.
  3. If you come with babies or toddler, I ask that you sit close to the door so that, in case your little one needs special attention and is disrupting the learning of other students, you may step outside of class until their needs are met. Seats close to the door are reserved for parents attending class with their child.

Evaluations and grades

You can find descriptions for all the assignments on the evaluations page.

Your final grade will be based on weekly assignments and feedback, a methodological review of a paper and a final examination. The exam will take place on Saturday, April 20th, from 13:30–16:30.

Team work counts towards your final grade only if you score more than 50% on individual evaluations.

Assignment Points
Weekly check-in (12 × 0.5 pt) 6
Problem sets (11 x 4 pt) 44
Paper review (10 pt) 10
Final examination (40 pt) 40
Total 100
Grade Range Grade Range
A+ 90-100% B 70-75%
A 85–90% B- 65-70%
A- 80–85% C+ 60-65%
B+ 75-80% F <60%

References

Cox, D. R. (1958). Planning of experiments. Wiley.
Diez, D., Çetinkaya-Rundel, M., & Barr, C. D. (2019). OpenIntro statistics (4th ed.). OpenIntro.
Keppel, G., & Wickens, T. D. (2004). Design and analysis: A researcher’s handbook. Pearson Prentice Hall.
Maxwell, S. E., Delaney, H. D., & Kelley, K. (2017). Designing experiments and analyzing data: A model comparison perspective (3rd ed.). routledge. https://doi.org/10.4324/9781315642956
Meier, L. (2022). ANOVA and mixed models: A short introduction using R (Chapman & Hall/CRC, Eds.). https://doi.org/10.1201/9781003146216

Footnotes

  1. The ability to compute custom contrasts and fit linear mixed models are deal breakers.↩︎

  2. This is the easiest way to set up SAS and does not require a virtual machine with Windows alongside a Unix operating system.↩︎

  3. There’s fairly widespread misunderstanding about what office hours actually are! Many students often think that they are the times I shouldn’t be disturbed, which is the exact opposite of what they’re for!↩︎

  4. Shamelessly stolen/adapted from similar policy by Drs. Melissa Cheney, Guy Grossman and Rohan Alexander↩︎