Charles S. Reichardt
I'm a methodologist and statistician. My research focuses on the logic
and practice of causal inference in both laboratory and field settings.
I'm particularly interested in quasi-experimentation, structural equation
modeling, and program evaluation.
Currently, I'm developing a logic for estimating causal effects and writing
a text on quasi-experimentation. Both works are concerned with the means
of ruling out alternative explanations for a presumed treatment effect,
and with representing and reducing uncertainty about the size of treatment
effects especially where uncertainty arises from sources other than random
sampling error. Another topic of long standing interest is how, when estimating
treatment effects, to take account of initial differences between treatment
groups when individuals have not been randomly assigned to the groups.
In addition to traditional academic research, I consult for a wide range
of organizations and individuals, and include students as apprentices
in this work as well.
Like my research, my teaching focuses more on the logic and practice
of statistical procedures than on their mathematical derivation. I'd very
much welcome collaborators in research as well as in developing hands-on
materials for students in both introductory and advanced statistics courses.
Reichardt, C. S. & Bormann, C. A. (1994). Using
regression models to estimate program effects. In Wholey, J. S., Hatry,
H. P. & Newcomer, K. E. (Eds.), Handbook of Practical Program Evaluation.
(pp. 417-455). San Francisco: Jossey-Bass.
Reichardt, C. S. & Rallis, S. F. (Eds.) (1994).
The qualitative-quantitative debate: New perspectives. New Directions
for Program Evaluation, no. 61. San Francisco: Jossey-Bass.
Reichardt, C. S. & Coleman, S. C. (1995). The
criteria for convergent and discriminant validity in a multitrait-multimethod
matrix. Multivariate Behavioral Research, 30, 513-538.
Reichardt, C. S., Trochim, W. M. K., & Cappelleri,
J. C. (1995). Reports of the death of regression-discontinuity analysis
are greatly exaggerated. Evaluation Review, 19, 39-63.
Reichardt, C. S. & Gollob, H. F. (1997). When
confidence intervals should be used instead of statistical tests, and
vice versa. In Harlow, L. L., Mulaik, S. A., & Steiger, J. H. (Eds).
What if there were no significance tests? (pp. 259-284). Hillsdale, NJ:
Reichardt, C. S. & Mark, M. M. (1998). Quasi-experimentation.
In Bickman, L. & Rog, D. J. (Eds.), Handbook of applied social research
methods. (pp. 193-228). Thousand Oaks, CA: Sage.
Reichardt, C. S. & Gollob, H. F. (in press).
Justifying the use and increasing the power of a t test for a randomized
experiment with a convenience sample. Psychological Methods.
Charles S. Reichardt
office: Frontier Hall,