A note on estimating regression coefficients with missing data

In this note, we consider the problem of estimating regression coefficients when there are missing observations of some explanatory variables. Following Dagenais (1973), Gourieroux and Monfort (1981), and Conniffe (1983a, 1983b), we assume auxiliary relationships exist among explanatory varibles. Several estimatprs and their interrelationships are discussed. We begin with the model of Gourieroux and

Monfort (1981)     

Effects of Category Order on Answers in Mail and Telephone Surveys1

Abstract Past research suggests that mail surveys encourage a primacy effect, which is a tendency to choose the first answers from a list, whereas telephone surveys encourage a recency effect, a tendency to choose the last answers from a list. This paper summarizes results from 82 new experiments conducted in 12 separate surveys in seven states. Only four of 33 mail survey comparisons exhibited significant primacy effects, while five of 26 experiments in telephone surveys exhibited recency effects. In addition, only three of 23 cross-method comparisons produced a significant primacy/recency effect in the expected manner. The conclusion is that the prevalence of primacy and recency effects has been over-estimated by past research and a new theoretical approach that takes into account multiple causation is needed for examining these effects.     

log-logistic survival estimation based on failure-censored data

Approximations of the Bayesian estimators of the survival function based on the censored data of the log-logistic distribution are obtained under squared-error and log-odds squared-error loss functions. A numerical example is presented. Through a Monte Carlo simulation study, the behavior of the approximations found by Tierney & Kadane and Lindley are compared with a method suggested by Weiss & Howlader.     

Socialization of emotion: Pathway to preschoolers' emotional and social competence

Aspects of 47 preschoolers'emotional competence—their patterns of emotional expressiveness and reactions to others' emotion displays—were observed in two settings, with mother and with peers, and their general social competence was rated by their preschool teachers. Intrapersonal and interpersonal (i.e., socialization correlates of children's emotional competence were identified, and a causal model incorporating direct and indirect influences on social competence was evaluated. Maternal patterns of expressiveness, reactions to children's emotion displays, and self-reported affective environment were associated with children's emotional competence in the preschool. Children's emotional competence with mother predicted their emotional competence in the preschool somewhat less strongly, suggesting that emotional competence may differ according to the interpersonal relationship studied. Taken as a whole, findings reassert the importance of the domain of emotional expression to the development of social competence.Reprint requests can be sent to the author, Department of Psychology, George Mason University, 4400 University Drive, Fairfax, VA 22030. Grateful acknowledgment goes to the mothers and children who so clearly expressed and reacted to emotions; thanks also are due to Christine Alban, Joanne Ayyash, Michael Casey, Elizabeth Couchoud, Huynh Dung, Merlina Hemingway, Soueang Lay, Vanna Nguyen, Emilianne Slayden and Kimberly Sproul, as well as the director and teachers of the Project for the Study of Young Children. An earlier version of this material was presented at the 1991 Biennial Meetings of the Society for Research in Child Development, Seattle, WA. University support from Grants #2-10150, 2-10176 and 2-10073 also made the research possible.     

Values and Vegetarianism: An Exploratory Analysis1

The American diet has changed substantially over the last few decades. These changes provide a test for social theory and have substantial effects on the demand for various food products, thus impacting U.S. agriculture. In this paper a rapidly growing dietary choice—vegetarianism—is explored. Prevalence of various forms of vegetarianism is estimated in a representative sample of a suburban population and factors that influence choice of a vegetarian diet are examined. About 7 percent of the sample report they are vegetarians. The prevalence of vegetarianism is not influenced by age, gender, or education, but individuals holding traditional values are less likely to be vegetarian than others. There also is some evidence mat individuals holding altruistic values are more likely than others to be vegetarians.