1 / 39

Instructors: Markus Brauer Bas Rokers Teaching Assistants: Kristina Kellett

Statistical Analysis of Psychological Experiments (PSYCH 610) The General Linear Model series. Instructors: Markus Brauer Bas Rokers Teaching Assistants: Kristina Kellett Xiaoming Ma. Today ’ s Outline. Quick introductions Syllabus & course outline

steffi
Download Presentation

Instructors: Markus Brauer Bas Rokers Teaching Assistants: Kristina Kellett

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Statistical Analysis of Psychological Experiments (PSYCH 610) The General Linear Model series Instructors: Markus Brauer Bas Rokers Teaching Assistants: Kristina Kellett Xiaoming Ma

  2. Today’s Outline • Quick introductions • Syllabus & course outline • Data analytic framework for 610/710

  3. Munich

  4. Montpellier

  5. Paris

  6. Boulder

  7. Konstanz

  8. Clermont-Ferrand

  9. My research • I am a social psychologist. • My graduate students and I study • Prejudice, discrimination, diversity, inclusiveness • Promotion of sustainable behaviors • How to design and test social interventions • "Normative tightness" and people's reactions to norm violations

  10. Bas Rokers

  11. Rotterdam

  12. Utrecht

  13. Newark Austin Los Angeles

  14. My research • I am visual neuroscientist • My graduate students, postdocs, and I study • Visual motion perception and motion blindness • 3D perception and binocular integration • Neural causes and consequences of visual impairments such as amblyopia (lazy eye) • Neural organization of the visual system

  15. So tell us who you are….. • Our TAs: Xiaoming Ma and Kristina Kellett • You • Your preferred name/nickname • Department/area group • Your year in your program • Any other information you are willing to share

  16. The Syllabus: Overview Lecture: Tuesday and Thursday 9:30-10:45 am, room 101 Labs: Friday 9:00 - 11:00 am or 1:00 - 3:00 pm, room 106 Professors: Markus BrauerBas Rokers E-Mail: brauer2@wisc.edu E-Mail : rokers@wisc.edu Office hours: Wed 9:45-10:45am Office hours : Mon 10:00-11:00 Room 417 (Brogden Psychology) Room 420 (Brogden Psychology) Teaching Assistants: Kristina KellettXiaomingMa E-mail: kellett@wisc.edu E-mail: xma22@wisc.edu Office hours: Tue 12:00-1:00, or by apptOffice Hours: Thu 10:50-11:50, or by appt Room: 596 (Psychology) Room: 638 (Psychology) Please attend your assigned discussion section. Email list if MUST switch. Need two volunteers to switch sections.

  17. The Syllabus: Objectives The goal of this class (610/710) is to familiarize you with statistical data analysis procedures. Our main focus is the "General Linear Model" but we will talk about other data analysis procedures as well. We will also provide instruction on issues of reliability and validity of research designs. In the first semester, we will give special attention to the interpretation of regression coefficients, regression models with quantitative and dichotomous predictors, mediation, and the interpretation of interaction effects in regression analysis. Extensive work outside the classroom is required in order to succeed in this class. We want to encourage you to participate actively in the class, both the lecture and the lab session.

  18. The Syllabus: Requirements & Grading Course requirements include regular attendance, active participation in class discussion, and completion of all homework assignments and tests. Your grade will be based on 5 exams (80%) and lab/homework assignments (20%). There will be two closed book exams (class mid-point and finals week) completed to assess conceptual knowledge (Conceptual Concepts Exams). There will also be three open-book, take-home exams to evaluate application of concepts to brief statistical problems (Application Exams). These will be completed approximately every five weeks. The homework assignments will involve hands-on application of the material, mostly involving computer exercises. They will be assigned weekly.

  19. The Syllabus: Listserv and Website Course Email List: psych610@lists.wisc.edu Or contact us individually. Default is that each of us cc's the three other instructors. Course Website: http://dionysus.psych.wisc.edu/GLM.htm

  20. The Syllabus: Reading Required Text: Judd, C.M., McClelland, G. H., & Ryan, C. (2008). Data Analysis: A Model-Comparison Approach (2nd ed.). New York, US: Routledge. Additional required and supplemental reading will be provided as pdfs on the Lecture Outline and Materials page on the course website. These readings are password protected: GLM

  21. The Syllabus: Required Software • This course will contain a significant applied component. • In the context of this course, we will rely heavily on R (http://www.r-project.org/). • R has many advantages … • R is freely available, open source, and is rapidly become the standard for statistical analysis in many disciplines. • R is highly collaborative and infinitely customizable. • R “forces” good analysis practices. • R is a true computer language and provides a powerful and flexible programming environment. • … but R is not very user friendly. • Although the primary goal of this course is NOT to teach you how to use R, you will become quite familiar with this computational platform across the two semesters of the course.

  22. The Syllabus: Schedule This schedule on the syllabus is provisional so that we may adjust our rate of progress as necessary to ensure maximal mastery of the material. See course website for the most up to date version of the assigned readings and topics.

  23. The Website http://dionysus.psych.wisc.edu/GLM.htm

  24. The Website

  25. Evaluation (of us!) • Ongoing Course Evaluation: • Two formal evaluations per semester. • Informal feedback about content or style always welcome

  26. Brauer vs. Rokers • 5k run or soccer game or bocci ball or frisbee golf or …

  27. General Linear Models as Models • General Linear Models are ‘models’ • DATA = MODEL + ERROR • Three general uses for models: • Describe and summarize DATA (Ys) in a simpler form using MODEL • Prediction of DATA (Ys) from MODEL (Xs) • Will want to know precision of prediction. How big is error? Better prediction with less error. • Understanding (describing and testing) complex relationships between individual predictors (Xs) in MODEL and the DATA (Ys). Do relationships exist? How precise are estimates of relationship? • MODELS are simplifications of reality. As such, there is ERROR. They also make assumptions that must be evaluated.

  28. Different Types of Models DV Dichotomous DV Categorical DV with >2 levels Continuous DV Logistic Regression Discriminant Analysis

  29. Different Types of Models Continuous DV No IV One or more between- subjects IVs At least one within-subjects IV One-sample t-test

  30. Different Types of Models Continuous DV One or more between- subjects IVs One or more dichotomous or continuous IVs At least one categorical IV with >2 levels

  31. Different Types of Models One or more dicho- tomous or continuous between-subjects IVs One IV Two or more IVs Two or more IVs and their interactions Independent samples t-test Multiple regression Interactions Moderated mediation Simple regression Statistical control (covariates) Polynomial regression Mediation

  32. Different Types of Models At least one categorical between-subjects IV with >2 levels • 1 contrast • multiple orthogonal contrasts • multiple non-orthogonal contrasts • no hypotheses Contrast Analysis One IV Two or more IVs Two or more IVs and their interactions

  33. Different Types of Models Continuous DV No IV One or more between- subjects IVs At least one within-subjects IV

  34. Different Types of Models At least one within- subjects IV One or more categorical within-subjects IVs At least one continuous within-subjects IV Paired-samples t-test Linear Mixed-Effects Models (LMEM) Within-subjects ANOVA Analyze as GLM or LMEM

  35. Different Types of Models Continuous DV No IV One or more between- subjects IVs At least one within-subjects IV Clustered data One or more categorical IVs At least one conti- nuous IV LMEM LMEM LMEM

  36. Different Types of Models For all these models: • - Case analysis • Model assumptions and transformations

  37. Learning and Success - Be aware of variability but know that you belong Not so great data analysis skills Great data analysis skills - Cooperation (classroom climate, help, grading) - It's all about mastery (nobody cares about grades)

More Related