East Carolina University
Department of Psychology
Choosing an Appropriate Bivariate Inferential Statistic -- This document will help you learn when to use the various inferential statistics that are typically covered in an introductory statistics course.
PSYC 6430: Howell Chapter 1 -- Elementary material covered in the first chapters of Howell's Statistics for Psychology text.
PSYC 2101: Howell Chapters 1 & 2 -- Elementary material covered in the first two chapters of Howell's Fundamentals text.
Scales of Measurement -- This document covers the topic of Scales of Measurement.
Ratio versus Interval Scales of Measurement -- a graphical explanation.
Descriptive Statistics -- This document covers Basic Descriptive Statistics.
Exercises involving descriptive statistics
The Three Quarter Rule -- This document illustrates how the graph can be used to either minimize or exaggerate your perception of differences.
Exploratory Data Analysis (EDA) -- This document covers Exploratory Data Analysis.
Skewness, Kurtosis, and the Normal Curve -- Platykurtic curves are short in the tails like platypuses; leptokurtic curves are heavy in the tails like kangaroos, noted for 'lepping.'
The Normal Distribution -- This document introduces the normal probability density function.
Describing the Shapes of Frequency Distributions -- advice for the novice
Making Inferences About Parameters -- An introduction to parametric inferential statistics.
An Introduction to Power Analysis, N = 1 -- See how to calculate power, using the normal curve, and how various factors affect power.
Basic Probability -- An introduction to the most basic concepts in probability theory and working with contingency tables.
Monte Carlo -- Use an applet to simulate various sampling distributions.
Testing Hypotheses with the Binomial Probability Distribution -- An introduction to the binomial distribution, including using it to test hypotheses about the binomial parameter p.
Comparing Correlated Proportions -- McNemar's Test
The Statistics of Democracy -- an interesting application of the binomial distribution
Common Univariate and Bivariate Applications of the Chi-square Distribution -- one sample variance, one-way chi-square, two-way chi-square.
Barnard's Exact Test -- Use instead of Fisher's exact test
Odds Ratios and the Wald Chi-square -- you can get a CI that includes one when the Pearson or LR Chi-square is significant
Reporting the Strength of Effect Estimates for Simple Statistical Analyses -- Independent t, one-way independent ANOVA, correlation/regression, contingency table analysis.
Power Analysis for Contingency Tables -- Using G*Power 3.
Reversal Paradox -- also known as Simpson's Paradox.
One Mean Inference -- Testing hypotheses about a single population mean, constructing confidence intervals, effect size estimation, and writing APA-style summary statements.
Two Mean Inference -- Testing hypotheses about the difference between two population means (independent or correlated) or variances, constructing confidence intervals, effect size estimation, and writing APA-style summary statements.
Measurement Scales and Psychological Statistics: Empirical Science or Metaphysics?
CL: The Common Language Effect Size Statistic -- this may help you better understand effect size estimates such as the d statistic.
Reporting the Strength of Effect Estimates for Simple Statistical Analyses -- Independent t, one-way independent ANOVA, correlation/regression, contingency table analysis.
Power Analysis -- Learn how to do power analysis for one and two sample designs.
Examples of the Use of Power Analysis in Actual Research Projects
Estimating the Sample Size Necessary to Have Enough Power -- for common designs.
Power Analysis for Contingency Tables -- Using G*Power 3.
Power Analysis for t Tests -- Using G*Power -- one sample, two samples, Pearson r.
Power Analysis for One-Way Independent Samples ANOVA -- Using G*Power
Power Analysis for Two-Way Independent Samples ANOVA, G*Power 3
Power Analysis for Three-Way Independent Samples ANOVA, G*Power 3
Power Analysis for Change in R^{2}, Multiple Linear Regression -- G*Power3
What is R^{2 } When N = p + 1 (and df = 0)? -- why you need to adjust (shrink) the correlation coefficient when sample size is small.
Contingency Tables with Ordinal Variables -- partition the overall effect into linear and nonlinear components
Comparing Correlation Coefficients, Slopes, and Intercepts
Differences in Slopes versus Differences in Correlation Coefficients
SAS and SPSS Programs for Comparing Pearson Correlations and OLS Regression Coefficients
Reporting the Strength of Effect Estimates for Simple Statistical Analyses -- Independent t, one-way independent ANOVA, correlation/regression, contingency table analysis.
One-Way Independent Samples Analysis of Variance
Easy Intro (PP Slides)
Confidence Intervals for Eta-Squared and RMSSE -- what should the confidence coefficient be?
Omega-Squared Discussion -- EDSTAT-L posting on Omega-Squared.
Power Analysis for One-Way ANOVA -- Using G*Power
Reporting the Strength of Effect Estimates for Simple Statistical Analyses -- Independent t, one-way independent ANOVA, correlation/regression, contingency table analysis.
T Tests, ANOVA, and Regression Analysis -- mathematical equivalence of these
Factorial-Basics -- Basic concepts in factorial ANOVA.
Factorial-Computations -- Computations in factorial ANOVA.
Triv-Int.doc: Trivial interactions in factorial ANOVA.
Example Presentation of Results from a Two-Way Factorial ANOVA.
Mixed-Effects ANOVA -- one fixed factor, one random
Random Effects, Omega-Squared, and the Intraclass Correlation Coefficient -- random effects factors and nested effects are included in the analysis presented here.
Summer Workshop -- Multiple Regression, ANOVA, and ANCOV.
Bumblebee Regression -- guaranteed to fit any data.
A Brief Introduction to Multiple Correlation/Regression Analysis
Presenting the Results of a Multiple Correlation/Regression Analysis.
Multiple R^{2} and Partial Correlation/Regression Coefficients.
Redundancy and Suppression in Trivariate Correlation/Regression Analysis. Also available in PowerPoint format.
Reversal Paradox -- predicting fire damage from severity of fire and number of fire-fighters.
Example of Multiple Correlation/Regression With Three Predictor Variables -- checking assumptions, transformation, suppression.
Inverting Matrices: Determinants and Matrix Multiplication. Also available in PowerPoint format.
Using Matrix Algebra to do Multiple Correlation/Regression. Also available in PowerPoint format.
Binary Logistic Regression with SPSS. Also available in PowerPoint format.
Multinomial Logistic Regression with SPSS Also available in PowerPoint format.
Power Analysis for Change in R^{2}, Multiple Linear Regression -- G*Power3
Mediation, Moderation, and Conditional Process Analysis
Moderation: Comparing Regression Lines From Independent Samples -- Continuous Y, One continuous predictor, one categorical predictor, interaction model.
Also available in PowerPoint format.
Continuous Moderator Variables. Also available in PowerPoint format.
Mediation, Overview, Simple Models -- one X, one Mediator, one Y
Also available in PowerPoint format.
The Multivariate Approach to the One-Way Repeated Measures ANOVA
The Pretest-Posttest x Groups Design: How to Analyze the Data
Two x Two Within-Subject ANOVA Interaction = Correlated t on Difference Scores
Proc Mixed -- zip file: document, code, and data for using Proc Mixed for Correlated Samples ANOVA
Three-Way Analyses of Variance Containing One or More Repeated Factors
Doubly Multivariate Analysis of Repeated Measures Designs: Multiple Dependent Variables
Mixed ANOVA With a Continuous Predictor and All Interactions
Three-Way Hierarchical Log-Linear Analysis: Positive Assortative Mating
Three-Way Nonhierarchical Log-Linear Analysis: Escalators and Obesity
Four Variable LOGIT Analysis: The 1989 Sexual Harassment Study
Principal Components Analysis
Factor Analysis
Factor Analysis With Data from Dichotomous or Likert-Type Items
SPSS Discriminant Analysis on Factor Scores Produced By SAS.
SEM Assignment
The Power Point slide for creating the diagram -- save this to your computer, do not open it in your browser.
Hierarchical Linear Modeling
Contact Information for the Webmaster,
Dr. Karl L. Wuensch
This page most recently revised on 26-May-2015.