PSYC 5104- Foundations of Research in the Psychological Sciences I (Fall 2019)

Instructor: Ian Stevenson (ian.stevenson@uconn.edu)
Office: BOUS 112
Office hours by appointment

Lecture meets in BOUS 160 Mon and Wed 10:10am - 11:40am

TAs: Naixin Ren (naixin.ren@uconn.edu) and Charles Davis (charles.davis@uconn.edu)
TA sessions: Thurs 11-12, Bous 190C and by appointment (poll)

This course is designed to introduce you to graduate-level behavioral research with a focus on data analysis. We will examine the core concepts in inferential statistics, as well as issues of replication and reproducibility. The course also provides a survey of methods that serves as a foundation for other quantitative courses, both within and outside the department.

Prerequisites: This course assumes that students have taken a previous undergraduate-level research methods course (e.g. PSYC 2100WQ) and have a strong understanding of descriptive statistics, t-tests, and correlations. If you are concerned about your readiness for the course you may want to discuss how to approach the course with Professor Stevenson or your advisor.

Problem sets require using your choice of R or SPSS. R is available here (or Rstudio). SPSS is available here (or AnyWare).

Textbook:
Judd, McClelland, and Ryan (2017). Data Analysis: A Model Comparison Approach to Regression, ANOVA, and Beyond

Refreshers on undergraduate statistics and methods:
Crump et al (2018). Answering questions with data: Intro stats for psych students
Crump et al (2018). Research methods for psychology
Diez, Barr, and Cetinkaya-Rundel (2015). OpenIntro Statistics, 3rd ed.

Other Resources:
R for Psychological Science
Learning Statistics with R
DataCamp Introduction to R
SPSS Tutorials
Nature Methods – Points of Significance
Tutorials in Quantitative Methods for Psychology
Fundamentals of Data Visualization
Data Visualization: A Practical Introduction
Open Stats Lab
TopicAssignments & Readings
08.26
08.28
Course Intro
Exploratory Data Analysis

Problem Set 1 due 8/30 - submit
09.02
09.04
Labor Day (no class)
Data Visualization


09.09
09.11
Validity and Reliability
Experimental Design
Problem Set 2 due 9/10 - submit

09.16
09.18
Null Hypothesis Significance Testing
...and its interpretation

Problem Set 3 due 9/20 - submit
09.23
09.25
Effect size and power
Simple models and simple regression


09.30
10.02
One-way ANOVA
Contrasts and trend analysis
Problem Set 4 due 10/01 - submit

10.07
10.09
Factorial ANOVA
Factorial ANOVA con't

Problem Set 5 due 10/11 - submit
10.14
10.16
ANCOVA
Multiple comparisons


10.21
10.23
Repeated-measures ANOVA
Repeated-measures ANOVA con't
Problem Set 6 due 10/22 - submit

10.28
10.30
Mixed effects models
Intro to multi-level models

Problem Set 7 due 11/01 - submit
11.04
11.06
Outliers and other tricky things
Intro to GLMs


11.11
11.13
Intro to nonparametric tests
Intro to bootstrapping
Problem Set 8 due 11/12 - submit

11.18
11.20
Intro to Bayesian methods
Intro to Factor Analysis


11.25
11.28
Fall Break (no class)
Fall Break (no class)


12.02
12.04
Project Presentations
Project Presentations
Presentations - submit
Project Reports due 12/13 - submit

Problem Sets

Working on your problem sets in groups is encouraged, but you must turn in your own work. Problems involve programming in your choice of SPSS or R (discuss with your advisor/program, which would make the most sense for you). If your advisor does not have a strong preference, I recommend using R. TA will host weekly computer-lab sessions to go through programming exercises.

Projects

Find a paper with publicly shared data and attempt to reproduce (at least some of) their results. Find an aspect of the published analysis that could be improved and implement this improvement. At the end of the semester, you should turn in a short report (5-10 pages) that describes what you did, why you did it, what you found, and why it matters.

Additionally, during the last week of classes everyone will give a short oral presentation on their project. The format should be similar to a short (data blitz) conference talk. Allow 5-10 min for the presentation

Open Data

Further Reading

Grading

Based on problem sets (60%) and project (40%).

Accessibility

Students with disabilities who believe they may need accommodations in this class are encouraged to contact the Center for Students with Disabilities as soon as possible to better ensure that such accommodations are implemented in a timely fashion.

Academic Student Code

Academic dishonesty of any type will not be tolerated. Students should refer to the Student Code for specific guidelines (see section on Academic Integrity).

Site built on Bootstrap v2.3.1
Updated