200.314 Advanced Statistical Methods

Steven Yantis

Fall, 2007

V. Kandinsky, Composition viii (1923)

Meets Tues and Wed 2-3:15pm in 233 Ames Hall

Instructor: Steven Yantis
email: yantis@jhu.edu
Office hours: Tues 1pm

TAs:
Adam Greenberg <agreenb@jhu.edu>
Mike McDannald <mcd@jhu.edu>

This course is the first half of the graduate statistics sequence. The goals are (1) to introduce elementary concepts in probability theory and statistics that are important for describing and interpreting quantitative data, and (2) to develop skills in analyzing and thinking critically about empirical data. We will cover probability theory, random variables, probability distributions, signal detection theory, hypothesis testing, t-tests, nonparametric tests, bootstapping and resampling, one- and two-way analysis of variance, correlation, and simple linear regression.


Text:
Hays, W.L. (1994). Statistics (5th edition). Belmont, CA: Wadsworth.
ISBN 0-03-074467-9

  HANDOUTS


Additional Readings:

Platt (1964) Strong inference. Science, 146, 347-353.

Chamberlain (1965) The method of multiple working hypotheses. Science, 148, 754-759

Loftus, G. (1996). Psychology will be a much better science when we change the way we analyze data. Current Directions in Psychological Science, 5, 161-171.

Poldrack, R.A. (2006) Can cognitive processes be inferred from neuroimaging data? Trends in Cognitive Sciences, 10, 59-63.

Wickens, T. D. (2002). Elementary Signal Detection Theory. New York: Oxford University Press. [Chap 1; Chap 2 (sections 2.1-2.3); Chap. 3 (sections 3.1-3.3)]

Swets, J.A., Dawes, R.M., & Monahan, J. (2000). Psychological science can inprove diagnostic decisions. Psychological Science in the Public Interest, 1, 1-26. [This reading is optional but you should read it.]

Howell, D.C. (2002). Statistical Methods for Psychology, Chapter 18. Resampling and Nonparametric Approaches to Data (pp. 692-719).

Byrne, M.D. (1993). A better tool for the cognitive scientist’s toolbox: Randomization statistics. IN W. Kintsch (Ed). Proceedings of the Fifteenth Annual Conference of the Cognitive Science Society (pp. 289-293). Mawah, NJ: Erlbaum.


Grading:
30% Homework
35% Midterm Exam
35% Final Exam

Homework:
There will be weekly homework assignments. You are encouraged to discuss the homework assignments with classmates in advance of completing them; however, the homework assignments must reflect your own work and should not be completed in group sessions. Generally, the assignment will be given out on Wednesday and due back on the following Tuesday at the beginning of class. We will attempt to return graded homework when new homework is assigned. In order to maintain this rapid turn around, late assignments will not be accepted.

Exams:
There will be two exams in the course, a midterm and a final. Each exam will have a take-home portion and an in-class portion. Each exam will cover the relevant material from lectures, readings, and homework. Exams are to be completed without discussion or collaboration. The final is cumulative but with an emphasis on the second half of the course.

Course Schedule:

Lecture notes for each week will be made available prior to class.
Go to Handouts to download file.

Week

Dates

Topic

Homework

Readings

1

9/11-12

  • Philosophy of Science
  • Probability theory

HW 1

HW Key 1

 Chamberlin (1965)
Platt (1964)
Hays Ch. 1
Poldrack(2006)

2

9/18-19

  • Probability Distributions
  • Random Variables
  • Counting Rules
  • Binomial Distribution

HW 2

HW Key 2

Review Appendix E.1-E.13
Hays Ch. 2
, 3

3

9/25-26

  • Central Tendency and Variability
  • Sampling distributions
  • Matlab tutorial

Matlab Ex 1
HW3

Matlab Key 1
HW Key 3

Hays Ch. 4
Hays Ch. 5 (sections 5.1-5.10 only)
Review Appendix A
Sampling Disn Demo

4

10/2-3

  • Normal (Gaussian) Distribution
  • Central Limit Theorem
  • Confidence Intervals

Matlab Ex 2
HW 4

Matlab Key 2
HW Key 4


Hays Ch. 6

5

10/9-10

  • Signal Detection Theory

Matlab Ex 3
HW5

Matlab Key 3
HW Key 5

Wickens (2002)
Swets et al. (2000)
SDT demo

6

10/16-17

  • Hypothesis Testing
  • In-class part of midterm exam (Wed 10/17)

(Distribute take-home part of midterm exam)

Midterm Exam
In-class Key
Take-home Key

Hays Ch. 7
Loftus(1996)

 

10/22

MIDTERM EXAM DUE (noon)

 

7

10/23-24

  • Inferences about population means: t-test
  • Confidence intervals
  • Nonparametrics and resampling

HW6
Matlab Ex4
Wilcoxon table
HW Key 6
Matlab Key 4

 

Hays Ch. 8
Howell Ch. 18
Howell's Resampling page
Byrne(1993)

8

10/30-31

  • Chi-square and F distributions
  • General Linear Model

HW7
HW Key 7

Hays Ch. 9,10
F calculator

 
11/6-7
NO CLASS (SFN)
   

9

11/13-14

  • Analysis of Variance
  • Contrasts

HW8
HW Key 8

Hays Ch. 10, 11

10
11/20
  • Factorial ANOVA and contrasts
HW9
HW Key 9
Hays Ch. 12
2-way ANOVA demo
 
11/21
NO CLASS (Thanksgiving)
   

11

11/27-28

  • Linear Regression and correlation

HW10
HW Key 10

Hays Ch. 14, sections 0-10, 14-15, 21-24

Restriction of range demo
Regression demo

12

12/4-5

  • Wrap-up
  • In-class part of final exam (Dec 5)
  • Distribute final exam

FInal Exam due 12/10/07 at noon

Final study guide

 Final Exam
Keys: In-class
Take-home


 

Last modified 12/12/2007