Seminar calendar

Virtual seminar room on Zoom

Reading:

                  LecturesReading and Materials
Week 1

Meeting 1: Introduction; qualitative research in data science education; teaching functions.

Meeting 2: Teaching functions: an algebraic approach; learning goals; brainstorming on approaches. Slides.

Meeting 3: Precept 1 post-mortem. Tidy data and a refresher on dplyr. Refresher/preview on dplyr

Week 2

Slides. code draft.

Week 3

Meeting 1: study organization

Meeting 2: ggplot.R

Future reading: Handbook of Computing Education Research

Future reading: Open Science Collaboration, Estimating the Reproducibility of Psychological Science

Future reading: Yarkoni, The generalizbility crisis

Reading:
Week 4

Meetings: Notes on field notes; cost functions and inference. Minimizing cost functions with fminb + a factory function (Rmd source).

Just for fun: John von Neumann and the fly

Reading:

Week 5

Likelihood and posterior inference (Rmd source)

Scratch piano program

Cost functions ⇄ inference slides

Reading:

  • Cambridge Handbook of Computing Education Research, Ch. 31
  • Lewis, The Importance of Students’ Attention to Program State: A Case Study of Debugging Behavior, ICER 2012
  • Week 6

    Cost functions ⇄ inference slides, continued

    Hierarchical models, modelling Radon (Rmd, srrs2.dat)

    Meeting 3 recording

    Reading: Ch. 11 of Gelman and Hill (N.B., available for free online via PU library)

    Week 7

    Meeting 1: Hierarchical models, modelling Radon (Rmd, srrs2.dat), continued. Recording

    Meeting 2: Hierarchical models 2 Recording

    Reading: Gelman and Hill Ch. 14.

    Reading: Yarkoni, The Generalizbility Crisis

    Online Stroop task

    Week 8

    Meeting 1: Hierarchical models 3 + the generalizbility crisis. Recording

    Meeting 2: Algorithmic fairness. Recording

    Meeting 3: The Generalizability Crisis. Recording.

    Reading:

    Week 9

    Meeting 1: p-values via simulation, p-values via sampling distributions. Recording.

    Meeting 2: intro to Landy et al (slides). Random-effect models for meta-analysis. Recording.

    Meeting 3: sampling distriubtions of coefficients, a diversion on using PCA to summarize an analyze test scores. Recording

    Reading:

    Week 10

    Meeting 1 recording

    Meeting 2 recording

    Meeting 3 recording

    Reading:

    Week 11

    Meeting 1 recording

    Meeting 2 recording

    Meeting 3 recording

    Reading:

    Week 12

    Meeting 1 recording

    Meeting 2 recording

    Meeting 3 recording

    Patitsas et el, Evidence that computer science grades are not bimodal, Communications of the ACM