|Scott Long is Distinguished Professor and Chancellor's Professor of Sociology and Statistics at Indiana University, Bloomington. He teaches quantitative methods both at Indiana University and at the ICSPR Summer Program. His earlier research examined gender differences in the scientific career. In recent years, he has collaborated with Eliza Pavalko, Bernice Pescsolido, John Bancroft, Julia Heiman and others in studies of health and aging, stigma and mental health, and human sexuality.|
Regression Models for Categorical Dependent Variables Using Stata, Third Edition began shipping on September 2, 2014. This edition is a complete rewrite of the second edition, taking full advantage of Stata's margins command and factor variable notation. Many new methods of interpretation are introduced using SPost13, a complete rewrite of SPost9. In Stata, enter: search spost13 to download commands and sample files. You can read the preface or a preliminary table of contents.
Why use the SPost13 mgen, mchange, and mtable commands instead of margins? Check here.
Short courses: I frequently teach short courses on categorical data analysis, Stata, the workflow of data analysis and other topics.Some of these are listed belows. Please contact me for further information.
Stat 503: Categorical Data Analysis is being taught Fall Semester 2014.
I will be giving the talk Reproducible Results and the Workflow of Data Analysis for the Workshop in Methods on Friday, August 29 2014, 2-3:30 pm in the Social Science Research Commons Grand Hall, Woodburn Hall 200. Many disciplines are paying increasing attention to “reproducible results”. This is the idea other scientists should have access to your data so that they can reproduce the results from your published work. Producing reproducible results is critically important and highly dependent on your workflow of data analysis. This workflow encompasses the entire process of scientific research: Planning, documenting, and organizing your work; creating, labeling, naming, and verifying variables; performing and presenting statistical analyses; preserving your work; and (perhaps, most important) producing replicable results. Most of our work in statistics classes focuses on estimating and interpreting models. In most “real world” research projects, these activities involve less than 10% of the total work. The talk is about the other 90% of the work. An efficient workflow saves time, introduces greater reliability into the steps of the analysis, and generates reproducible results.
Soc 751: Managing statistical research: the workflow of data analysis (1st Summer Session 2017; May 13-June 6, 2014. This intensive class deals with the entire process of research: planning, documenting, and organizing your work; creating, labeling, naming, and verifying variables; performing and presenting statistical analyses; preserving your work; and, critically, producing replicable results. Most classes in statistics focus on estimating and interpreting models. In "real world" research, these activities often involve less than 10% of the total work. This workshop is about the other 90% of the work. Contact Scott Long for authorization to enroll.
ICPSR Summer Program Workshop on Models for Categorical Outcomes Using Stata: June 16-20, 2014 at the Center for Research on Families at the University of Massachusetts-Amherst. This workshop introduces the new SPost13 commands and the third edition of Long and Freese's Regression Models for Categorical Dependent Variables Using Stata! To enroll, go to the ICPSR Summer Program site. For further details, check here. Contact Scott Long if you have questions. 25Feb2013
ICPSR Summer Program Workshop on Managing statistical research: the workflow of data analysis: July 7-11, 2014 at the University of Michigan-Ann Arbor. To enroll, go to the ICPSR Summer Program site. Contact Scott Long if you have questions.
Regression Models for Nominal and Ordinal Outcomes can be downloaded here; updated on 25Feb2013. Your comments are appreciated.
Workflow in Data Analysis. The Workshop in Methods is this talk by Scott Long on Friday, September 3 at 2:30 in Woodburn Library Room 200. A recent entry on a blog discussing Professor Long’s recent book, The Workflow of Data Analysis Using Stata, claimed: “The publication of [this book] may even reduce Indiana’s comparative advantage of producing hotshot quant PhDs now that grad students elsewhere can vicariously benefit from this important aspect of the training there.”
Group comparisons in logit and probit using predicted probabilities This working paper from 2005 is now a complete draft. The paper can be downloaded here. For further information on details on using Stata for group comparisons, go here.
Recommended reading: The Art of Scientific Writing by Ebel, Bliefert, and Russey (2004).
The Department of Statistics at Indiana University was created on July 1, 2006. Click here for details.
The 2nd Edition of Regression Models for Categorical Outcomes Using Stata by J. Scott Long and Jeremy Freese is published. Rich Williams' review of the book is here. For the table of contents and purchasing information, click here. Information about the book and associated software, click here. November 29, 2006
From Scarcity to Visibility: Gender Differences in the Careers of Doctoral Scientists and Engineers by J. Scott Long is now available from the National Academy Press. This book documents the changes that have occurred in the presence and participation of women in science and engineering from 1973 to 1995. For more information, click here.
The Chinese edition of Regression Models for Categorical and Limited Dependent Variables has been published. For details, click here.