David J. Weiss
Office: KH D3087
IntroductionTeaching Interests Articles On-line Research Interests
Fresh out of graduate school, I joined the CSULA Psychology Department in 1970. Early in my research career, I was interested in perceptual judgment. I withdrew from psychophysics after publishing a paper that argued against the possibility of finding a general psychophysical law (Weiss, D. J. (1981). The impossible dream of Fechner and Stevens. Perception, 10, 431-434.)
I have always maintained my interest in measurement, defending ordinal data (Weiss, D. J. (1986). The discriminating power of ordinal data. Journal of Social Behavior and Personality, 1, 381-389.) and insisting on a behavioral foundation for assessment of the effectiveness of programs designed to change health-related actions (Weiss, D. J., Walker, D. L., and Hill, D. (1988). The choice of a measure in a health-promotion study. Health Education Research: Theory and Practice, 3, 381-386.). Several new statistical procedures stemmed from my interest in health psychology, including one for incomplete studies (Elder, W. W., & Weiss, D. J. (1987). Snapshot: Analysis of variance with unequal numbers of scores per subject. Educational and Psychological Measurement, 47, 117-119.) and another for coping with attrition (Weiss, D. J. (1991). A behavioral assumption for the analysis of missing data: The use of implanted zeroes. Journal of Social Behavior and Personality, 6, 955-964.) A quantitative way to decide whether attrition can reasonably be attributed to chance was presented in Weiss, D. J. (1999). An analysis of variance test for random attrition. Journal of Social Behavior and Personality, 13, 433-438.
My empirical interests have evolved toward matters of social judgment. Harris and I tested a model of the way jurors might regard evidence in a rape trial (Harris, L. R., & Weiss, D. J. (1995). Judgments of consent in simulated rape cases. Journal of Social Behavior and Personality, 10, 79-90.) One of the key issues in this kind of research is how to induce people to share feelings or personal histories that they might consider embarrassing. Linden and I tested the random response method (Linden, L .E., & Weiss, D. J. (1991). An empirical assessment of the random response method of sensitive data collection. Journal of Social Behavior and Personality, 9, 823-836.) and Ong and I explored the role of anonymity (Ong, A. D., & Weiss, D. J. (2000). The impact of anonymity on responses to "sensitive" questions. Journal of Applied Psychology, 30, 1691-1708.). I have defended the use of deception as a valuable tool (Weiss, D. J. (2001). Deception by researchers is necessary and not necessarily evil. Behavioral and Brain Sciences, in press), although certainly there is some risk that frivolous deception will undermine the credibility of the research community in the eyes of the people who participate in our studies.
In 1998, I began a long-term collaborative project with my office-mate from graduate school, James Shanteau of Kansas State University. Shanteau is perhaps the world's leading expert on experts. Our goal is to derive performance-based measures of expertise. The methodology derives from analytic methods I first developed in an unpublished study of the growth of wine-tasting skill among students in my colleague David Fitzpatrick's course on sensory evaluation of wine (ah, the seventies!). An important application of this work is expertise exhibited by air traffic controllers, and we have been supported by the FAA.
The class that I teach most often is Psychology 302, our intermediate course in statistics. This course is required of all majors, and for good reason. One cannot hope to describe behavior without a language that includes probabilistic constructs. One of the special fascinations of our discipline is that the objects of study, people, exhibit tremendous variability in their actions. There is variation among different people, of course, but there is also variation within an individual's responses to the same situation. This makes describing the regularities in behavior a challenge.
I teach Psychology 302 using a lecture format, in which I present (lots of!) new information in each class. Following the class, there is a laboratory session guided by a graduate assistant. In the lab, students practice the techniques. During the first half of the course, the emphasis is on probability. Statistical inference is the global topic of the second half. The course grade is based solely on performance on the two exams. I have constructed a Web site to supplement the lecture and the textbook.
I also teach the statistics courses Psychology 414 and Psychology 515 annually. These courses focus on Analysis of Variance, my favorite statistical technique. I present lectures on experimental design as well as analytic techniques. In the classes, we use a set of statistical programs I have written, the CALSTAT series, that is very user-friendly and thereby allows students to focus on learning statistics rather than how to run a program. I also wrote the text for these classes (the same book is used in both). The course grade is based solely on performance on the two exams.
The graduate seminar, Psychology 504, that I teach annually is especially intended for students planning to do a thesis. As listed in the catalog (Advanced Experimental Methods), the course is slightly mis-titled. I call the course Advanced Research Methods to emphasize that we discuss other methodologies as well. Course topics include issues in the use of human subjects, theories and model construction, and validity of measures. Questionnaire construction is a major focus. Statistics instruction is not a part of this course. Each student presents a proposed experiment in any domain (ungraded) to the class and subsequently submits a written version (graded). This format allows students to experience a little of what happens in a scientific meeting. An important goal is for students to learn to give and absorb professional, constructive, criticism. The class Web site has information of value to all graduate students.
Human Sexuality, Psychology 542, is another graduate seminar that I teach regularly. In addition to my personal fascination with the domain, sexual behavior presents interesting methodological challenges to the researcher. Obtaining honest reports from people about their sexual feelings and behaviors is problematic, especially from members of sub-cultures for whom sex is a taboo topic. As a researcher in judgment, I am interested in the decisions people make about what to do and about what they choose to share with the researcher. I am tremendously impressed with the courage demonstrated by Masters and Johnson, the pioneer empirical workers in the field, and by Kinsey, who first tried to survey people about these private behaviors. The format of the seminar is similar to the one I employ in Psychology 504. The class Web site has some interesting links...
Occasionally I present an idiosyncratic version of Psychology 501, the graduate seminar in perception. My slant is the perception of people, social perception. Topics include eyewitness identification, the study of faces, stereotyping and prejudice, and cultural variations. I view all of these as judgmental issues. The format of the seminar is similar to that of Psychology 504.
Computer programming is the subject of Psychology
409. The goal of the course is
for each student to write a viable WINDOWS program of use to a psychologist.
We program in VISUAL BASIC.
This may be a teaching program, one for presenting stimuli/gathering responses from
subjects, or even a statistical program.
Other applications as proposed by students will also be considered.
No programming background is presumed. The grade is based on my subjective
evaluation of the program.
The following article(s) are available on-line.
Ong, A.D. and Weiss, D.J. The Impact of Anonymity on Responses to "Sensitive" Questions.
Research interests are among the following domains:
(1) How do people process information in making decisions? Can these decisions be described by simple algebraic models? Many of these studies employ functional measurement methodology.
(2) How can researchers peer inside people's heads? Are there techniques that allow us to explore events in their personal histories? Can we quantify their opinions?
(3) How can we measure expertise? James Shanteau of Kansas State University and I have proposed that two necessary characteristics of expert judgment are: (1) discriminating the various stimuli in the domain and (2) consistent treatment of similar stimuli. Measures of these characteristics are combined in a ratio called the CWS (Cochran-Weiss-Shanteau) index.
Within these domains, my students carry out research projects covering a wide range of topics. Recent examples include judgments about rape and child abuse, compliance with medical recommendations, the impact of physical attractiveness, and the revelation of sensitive information.
(4) The creation of statistical computer programs. Currently, programs are written in Visual BASIC, which generates Windows programs. The CALSTAT series includes easy-to-use programs for design and analysis of experimental data. The crowning glory of the series is the Functional Measurement program.
Representative Professional Activities
Date Publications/Presentations 1998 Rundall, C. S., & Weiss, D. J. Patients' anticipated compliance: A functional measurement analysis. Psychology, Health, & Medicine, 3, 261-274. 1999 Estrada, A. X., & Weiss, D. J. Attitudes of military personnel toward homosexuals. Journal of Homosexuality, 37, 83-97. 1999 Weiss, D. J. An analysis of variance test for random attrition. Journal of Social Behavior and Personality, 14, 433-438. 2000 Ong, A. D., & Weiss, D. J. The impact of anonymity on responses to "sensitive" questions. Journal of Applied Psychology, 30, 1691-1708. 2001 Weiss, D. J. Deception by researchers is necessary and not necessarily evil. Behavioral and Brain Sciences, in press.
|Ph.D. Psychology 1973|
|University of California, San Diego|
|San Diego, California|
|B.A. Psychology 1966|
|University of Pennsylvania|
|Course||Sect. No.||Title||Units||Day & Time||Room|
|Psy.302||01-02||Statistical Methods||5||MW 610-915pm||KHC4075|
|Psy. 409||01-02||Computer Techniques||4||MW 1050am-130pm||KHD3068|
|Psy. 515||01||Ad. Stat Methods||4||MW 420-600pm||KHD3068|