I am a professor in statistics at the University of Waterloo in Ontario, Canada. Prior to this appointment I was a statistician at RAND and head of the Rand Statistical Consulting Service. Here are my colleagues in the RAND Statistics group. You can email me at schonlau at uwaterloo dot ca. I spent the academic year 2009/2010 on sabbatical at the German Institute for economic analysis (DIW) in Berlin, Germany. The DIW hosts the longest running household panel in Germany, SOEP. The sabbatical was made possible in cooperation with the Max Planck Institute for Human Development (MPIB). Before joining Rand's Pittsburgh office in 2005, I worked at RAND's Santa Monica headquarters. From 1997-1999 I held a joint appointment with the National Institute of Statistical Sciences and AT&T Labs - Research In 1997, I graduated from the University of Waterloo.

Research Interests:

I am interested in the methodology of web surveys and surveys in general. For example, for web surveys which are often non probability samples the question arises whether it is possible to adjust for selection through the use of additional lifestyle questions that capture the difference between online and offline population. As a result of my sabbatical with the SOEP group in Berlin, Germany, I have also started to work more generally on methodological issues in household panel surveys. In Waterloo, I am involved with the International Tabacco Control project which conducts surveys in 20 countries around the globe. Moving forward, I plan on working on the analysis of open-ended questions.

I have used propensity scoring approaches in several different domains, including in the context of selectivity of web surveys, racial inequities in the way the US death penalty is prosecuted, and whether bullying and victimization of teenagers is related to delinquent behavior.

When the opportunity arises I enjoy programming. Much of my early programming was in C/C++ (e.g. software for the analysis of computer experiments), but because of time constraints I have lately focused on add-on programs in stata that seamlessly integrate with existing stata commands. One highlight was a plugin of the data mining technique "boosting" (programmed from scratch in C++) into stata. More recently, my program for respondent driven sampling in stata has been downloaded from many countries.

Teaching:

I have recently taught "Introduction to Statistics" (Stat 231) and "Statistics for Business I" (Stat 371) which consists of linear regression (6 weeks) and sampling (6 weeks).

Counter as of Apr 18, 2003:
Return to Home Page
Remove navigation bar on the left