Resources

Below is a collection of various statistical and technical notes,  computer code, and Shiny apps that I have created throughout the years.

• General & Generalized Linear Models

  • T-test programming - R demo 

  • Bivariate Regression - Calculus demo 

  • Regression Computations - R demo 

  • Continuous by Continuous Interactions 

  • Logistic Regression, Dose-Response Example (online link in text) 

  • Mixed Effects Baby Steps 

• Analytic Demonstrations

  • Using Optim for Maximum Likelihood - basic demo 

  • Maximum Likelihood and Nonlinear transformations 

  • Maximum Likelihood: Gaussian, Bernoulli, and OLS - Analytic demo 

  • Variance Sum Law - Analytic demo 

• ANOVA & ANCOVA

  • Bayesian One-way ANOVA with JAGS 

  • ANCOVA example (online link in text) 

  • ANCOVA of Cholesterol data 

• SEM & Latent Variables

  • Using SymPy for Understanding SEM (Rmd | PDF)

  • Principal Components Analysis (PCA) - introductory demo

  •  Exploratory Factor Analysis (EFA)

    • EFA estimation(s) and rotation(s) 

    • EFA extraction to targeted rotation 

  • Common Factor Model  loading computations

  • Introductory Path Analysis 

  • Factorial Invariance - Replication of Horn & McArdle (1992) 

  • Nonlinear SEM - Replication of Ram & Grimm (2007) 

• Technical Demonstrations

  • Sampling Distributions & Standard Error demo 

  • Solving Systems of Equations - QR, Cholesky, & SVD 

  • Sum of Squared Errors vs Sum of Absolute Errors - Optimization example 

• Coded Libraries & Applications

  • Tucker Curves - R code 

  • Mplus-to-OpenMx syntax converter - Perl code 

  • Central Limit Theorem demo - Shiny App 

  • Continuous-by-Continuous Interaction Visualization - Shiny App 

Here is a list of available example datasets to use for statistical modeling demonstrations. Please note these data are not guaranteed to reflect actual observations and many of these datasets include simulated observations.

anxiety.sav - Researchers interested in how different relaxation techniques can reduce anxiety levels surveyed 30 people taking various Physical Education courses at a college. 10 people took a traditional course, 10 people took a course in yoga, and 10 people took a course in tai chi. Each were tested on an anxiety measure where higher scores indicate greater anxiety. The data set anxiety.sav indicates the experimental groups (1 for traditional, 2 for yoga, and 3 for tai chi) and their scores on the anxiety test.

Arithmetic_Learning.csv - A sample of 66 second-graders was identified, and 11 were randomly assigned to each of the six combinations of reinforcement schedules and reinforcers. Students study arithmetic problem solving under these six conditions for three weeks, and then took a test over the material they studied. The data file includes 66 cases and three variables: a factor distinguishing between the two types of reinforcement schedules (random or spaced), a second factor distinguishing among three types of reinforcers (token, money, or food) and the dependent variable, an arithmetic problem-solving test.

birthweight.sav - These data were collected at Baystate Medical Center, Springfield, Massachusetts, during 1986. The variables include measures of low-birth weight (defined as a baby weighing less than 2500 grams), the mother’s age, whether the mother smoked during the pregnancy, whether the mother had hypertension, and the weight of the mother during her last menstrual period, as well as various other measures.

CholesterolOverTime.csv - Three longitudinal measures on subjects regarding their overall cholesterol levels.

Cholesterol_Study_Example.csv - Cholesterol data collected from participants in two states.

classrooms.sav - A psychologist conducted an experiment where one classroom followed a traditional method of instruction; however, in the other classroom, an experimental cooperative method of instruction was used. Prior to instruction, student knowledge was assessed using a standardized test; after instruction, student knowledge was assessed with a different version of the standardized test. For both tests, higher scores indicate better understanding of the material.

DisabilityPlay.csv - Measures of hours of play between fathers and their children based on disability status and gender of the child.

drugtreat.sav - These data represent measures from individuals who participated in a drug treatment program and were follow-up on 12 months later. The measures include, age at enrollment, depression score at enrollment, IV drug use history, prior treatments, race, treatment group, site/location of treatment and whether they remained drug free at follow-up.

FR_subset.csv - Subset of data representing scores on fluid reasoning tests including scores on the following sub-tests: vocabulary, block design, and matrix reasoning. Additional data include age, gender (sex assigned at birth), and performance IQ.

hsb.txt - Excerpt of the High School and Beyond dataset used in various manuscripts. Scores include gender, race, SES, school type, program type, reading, writing, math, science, and social studies scores.

injury.sav - This file contains data on 100 women and various measures their strength and injury status. Measures include: 1) quads: A measure of strength of the quadraceps muscles in the legs, 2) gluts: A measure of strength of the muscles in the upper part of the back of the leg and the buttocks, 3) medindex: A measure of medication, 4) abdoms: A measure of strength of the abdominal muscles, 5) arms: A measure of overall arm strength, 6) grip : A measure of overall grip strength, 7) injury: Overall injury index based on the records kept by the participants, 8) age: The age of the women when the study began.

KIMS_QuestionsAndDemographics.csv - These data come from an online sample of respondents who filled out the Kentucky Inventory of Mind-fulness Skills. The items Q1-Q39 were presented on a single page and were rated on a 5 point scale where: 1=Never or very rarely true, 2=Rarely true, 3=Sometimes true, 4=Often true, 5=Very often or always true (0=none selected). On the next page the takers entered the following information:
age: Entered as as text then parsed to an integer (ages<14 removed)
gender Biological sex: Chosen from drop down list (1=male, 2=female)
The original scale was first presented in
Baer, R. A., Smith G. T., Allen, K. B. (2004). Assessment of mindfulness by self-report: The Kentucky Inventory of Mindfulness Skills. Assessment, 11, 191–206.

KIMS_SummaryData.csv - Four subscale scores of the original KIMS data with age and biological sex.

MigraineSufferingOverTime.csv - Participants were measured regrading how many hours of migraine headaches they endured in a given week. For the design of this study participants were measured twice prior to receiving training in a relaxation therapy that was intended to reduce the amount of migraines participants experienced. They were then followed up and measured again three times. Each measurement, both baseline measures and three follow-up measures, were a week apart.

ProfRatings.csv - Measures of average ratings of teaching, courses over 10 years collected from social science professors along with their total number of publications and citations over the same timeframe.

PTSS_Therapy.csv - These data were collected from subjects were 45 trauma survivors who were suffering from PTSD symptoms (ptss). Each was randomly assigned to one of four groups. The four groups were: 1) Stress Inoculation Therapy (SIT) in which subjects were taught a variety of coping skills, 2) Prolonged Exposure (PE) in which subjects went over the trauma in their mind repeatedly for seven sessions, 3) Supportive Counseling (SC) which was a standard therapy control group, 4) a Waiting List (WL) control. The outcome reported here are total count of ptss or postraumatic stress symptoms reported at follow-up.

sociability.sav - A psychologist measured the sociability of a boy and a girl from each of four families. Higher scores on this measure correspond with greater sociability. (Note that because each boy/girl pair came from the same family the boy and girl groups in this study are not independent).

willett.csv - These data are presented in Willett (1988) on the growth in opposite naming task on four occasions for 35 individuals.