Fall 2014 Classes in Methodology
If you have a question about a specific course, please contact the instructor of that course directly. If you have a general question about the suite of one-credit methodology courses, please email mc@psu.edu.
For more information about the one-credit courses, please see our frequently asked questions:
HD FS 597F - Person-centered methods: Advanced contingency table analysis
Schedule Number: 909307
Instructors: Dr. Mark Stemmler, Professor of Psychological Diagnostics, Department of Psychology and Sports Science, University of Erlangen-Nuremberg, Germany
Credits: 1
Course Dates: August 18-22 (5 days). Note: This is the week PRIOR to the start of the semester.
Time and Location: 1-4 PM at the Methodology Center, 400 Calder Square II
Prerequisites: Some knowledge of multivariate statistics and SPSS; students should bring their own laptops to class.
Enrollment limited to 20 students
Course Description: This course takes an easy-to-understand look at a statistical approach called the person-centered method. Instead of analyzing means, variances, and covariances of scale scores as in the common variable-centered approach, the person-centered approach uses contingency tables to examine persons or objects grouped according to their characteristic patterns or configurations. In contingency tables, the observed patterns are ordered by their indices; a certain position in a table, denoted by a pattern or configuration, is called a cell.
The main focus of the course will be on configural frequency analysis (CFA; Stemmler, in press; von Eye, 2002), which is a statistical method that looks for over- and under-frequented cells or patterns. A pattern or configuration that contains more observed cases than expected is called a type; a pattern or configuration that is observed less frequently than expected is called an antitype. CFA resembles log-linear modeling: log-linear modeling seeks to find a fitting model including all important variables; instead of fitting a model, CFA examines the significant residuals of a log-linear model.
In addition to the theoretical introduction, many data examples will be provided. The course will be using CFA-freeware (Alexander von Eye; voneye@msu.edu) and the R-package confreq.
Required text:
Stemmler, M. (2014). Person-centered methods - configural frequency analysis (CFA) and other methods for the analysis of contingency tables. New York: Springer Briefs in Statistics. Now available! eBook also available
Optional text:
von Eye, A. (2002). Configural frequency analysis - methods, models, and applications. Mahwah, NJ: Lawrence Erlbaum.
Register through the Office of the Registrar--the schedule of courses is listed here.
HD FS 597A - An Introduction to latent class and latent profile analysis
Schedule Number: 231235
Instructors: Dr. Bethany Bray, The Methodology Center
Credits: 1
Course Dates: 3-week intensive:
Tuesday 8/26
Thursday 8/28
Tuesday 9/2
Thursday 9/4
Tuesday 9/9
Time and Location: 5-7:30 PM in 101 HHD East Note: This is a location change from the original listing. The class will NOT be held at the Methodology Center.
Prerequisites: The prerequisite for this course is graduate-level statistics training for the behavioral or health sciences up through linear regression (usually two semesters of course work). Basic familiarity with SAS, Mplus, and logistic regression is helpful, but not a prerequisite.
Enrollment limited to 15 students
Course Description: The goal of this short course is to help students gain the background and skills to be able to address interesting research questions using latent class and latent profile analysis. Latent class theory is conceptually similar to factor analysis. However, in latent class theory, latent variables are categorical, and individuals are sorted into mutually exclusive and exhaustive latent classes based on a set of item responses. Latent class analysis uses categorical indicators to identify underlying subgroups in data and estimate their prevalences, while simultaneously adjusting for measurement error; latent profile analysis is conceptually similar but uses continuous indicators. These models can be extended in a variety of ways; for example, multiple-groups analyses can be performed, covariates can be introduced to predict latent class membership, and latent class membership can be used to predict later outcomes.
Class time will be spent in lecture, discussion, and software demonstrations. Laboratory exercises will be provided for students to do outside of class. In addition, students will be required to do a small project. The software used in this course will be (a) a downloadable add-on procedures for SAS Version 9 for Windows: PROC LCA (for latent class analysis), and (b) Mplus (for latent profile analysis).
Register through the Office of the Registrar--the schedule of courses is listed here.
STAT 597B - Data Privacy Methods for the Social and Behavioral Sciences
Schedule Number: forthcoming
Instructors: Aleksandra (Sesa) Slavkovic, Associate Professor of Statistics, Penn State
Credits: 1-3
Course Dates: October 21, 28, November 4, 11, 18 (5 weeks) lectures for 1 credit and plus by appointment for 3 credits
Time and Location: 4:00 - 6:30 PM at the Methodology Center, 400 Calder Square II
Prerequisites: STAT 414/415, STAT 501 or equivalent or permission of the instructor. Working knowledge of R or other statistical packages.
Enrollment limited to 15 students
Course Description: Data privacy is a growing problem due to the large amount of sensitive and personal data being collected, stored, analyzed and shared across multiple domains and stakeholders. Researchers are facing new policies and technical requirements imposed by funding agencies on accessing and sharing of the research data. The ultimate goal is to enable data sharing that supports useful statistical inference while minimizing the disclosure of sensitive information. The problem is variously known as “statistical disclosure limitation", “privacy- preserving data mining", “anonymization", “private data analysis", or simply "data privacy."
- Week 1: General Overview. Introduction to statistical methodology for limiting disclosure risk and enabling data sharing. Overview of problems and techniques including current government guidelines and policies (e.g., US Census, HIPAA).
- Week 2: Microdata methods, with a tutorial including the SDC package in R.
- Week 3: Tabular data methods, with a tutorial including the SDC package in R.
- Week 4: Synthetic data methods, with a tutorial including the SDC package in R.
- Week 5: Differential Privacy and privacy in distributed databases.
Register through the Office of the Registrar--the schedule of courses is listed here.
Register through the Office of the Registrar. View the schedule of courses.