Richard Gonzalez
Center Director, Research Center for Group Dynamics, Institute for Social Research
Co-Director, BioSocial Methods Collaborative
Amos N Tversky Collegiate Professor, Psychology and Statistics, LSA
Professor of Integrative Systems and Design, College of Engineering
E-mail: | Email Richard Gonzalez |
Address: | Research Center for Group Dynamics Institute for Social Research University of Michigan 426 Thompson Street Ann Arbor, Michigan 48106 |
Phone: | 734-647-6785 |
Articles in Statistics/Methods
A call to take a population approach to neuroscience
We describe and promote a perspective—population neuroscience—that leverages interdisciplinary expertise to (i) emphasize the importance of sampling to more clearly define the relevant populations and sampling strategies needed when using neuroscience methods to address such questions; and (ii) deepen understanding of mechanisms within population science by providing insight regarding underlying neural mechanisms.
Using computer adaptive methods to select the next query in a decision making study
We extend the adaptive design optimization (ADO) approach to decision making under risk. ADO is a Bayesian method that adapts the experimental design in real time; it chooses the next question that can maximally discriminate the predictions of competing theories.
Standard errors for parameters in dyadic models
We show how to derive standard errors for a few basic models in dyadic data analysis. The chapter was written for Michael Browne’s festschrift.
Analyzing multivariate dyadic data for exchangeable dyads
This was our first paper on dyadic analysis. In retrospect, one of our main contributions was more pedagogical in that we showed how to get solid intuition about dyadic data and presented a framework in which to derive estimates and their standard errors. The framework illuminated several aspects of dyadic data, including why a correlation of dyadic means is sometimes difficult to interpret. Our results are identical to multilevel models using maximum likelihood estimation.
Understanding circumplex models: An application to vocational interest
In trying to understand an application of the circumplex structure to vocational structure, I struggled with geometric representation in theory development and data analysis. This short paper discusses some diagnostics one could apply to data to test the circumplex structure and provides some thoughts on the role of models in theory development.
How do we distort probability when making risky decisions?
We present preference conditions for the curvature of the probability weighting function in the context of cumulative prospect theory. Those conditions are tested with a new “ladder” procedure.
The important role of replication in research
This paper is gaining some new interest given the recent attention the field of social psychology is giving to the issue of replication. When we wrote this paper the field was debating the use of null hypothesis testing. We argued that replication needs to be emphasized as well. But this wasn’t new to Fisher who wrote:
Data analysis for distinguishable dyads
In this paper we present methods for the analysis of dyadic data when the two members are distinguishable (e.g., gender distinguishes the members in a heterosexual couple). We develop the pairwise model for the distinguishable case and show that it provides identical parameter estimates as a latent level model in a structural equations model framework.
Measuring the degree of ordinal association between two variables
In this paper Tom Nelson and I review several alternative measures of association. Most researchers make ordinal statements such as “when one variable goes up, the other goes down.” But then they assess such an ordinal statement with a Pearson correlation or a linear regression. There are better measures available as reviewed in this paper. We also address the thorny issue of how to handle ties in data.
A sales pitch for modern Bayesian data analysis
A basic chapter introducing psychologists to the world of modern Bayesian statistics. We cut out a lot of the dogma and go into sales pitch mode on the benefits of going Bayesian. If we pique your interest in learning more about what Bayesian tools can offer, then we consider the chapter a success.