James N. Morgan

Problems in the Analysis of Survey Data, and a Proposal

Abstract Most of the problems of analyzing survey data have been reasonably well handled, except those revolving around the existence of interaction effects. Indeed, increased efficiency in handling multivariate analyses even with non-numerical variables, has been achieved largely by assuming additivity. An approach to survey data is proposed which imposes no restrictions on interaction effects, focuses on Importance in reducing predictive error, operates sequentially, and is independent of the extent of linearity in the classifications or the order in which the explanatory factors are introduced.

Teaching the Use of Cost-Benefit Reasoning in Everyday Life

Our research shows that people can apply the cost-benefit rules of microeconomic theory to their everyday decisions. Two populations were examined: (a) people who had previously received extensive formal training in the rules and (b) naive subjects who were randomly assigned to receive brief training in the rules. Training affected reasoning and reported behavior in both populations. The results indicate that extremely general rules govern choices across a wide range of domains and that use of the cost-benefit rules can be improved through training.

The Anatomy of Income Distribution

HE purpose of this article is to improve T understanding of the meaning of survey data on income, and of inequality measures derived from such data. Where possible, the data are examined to see whether conceptual distinctions or difficulties make any important differences. Short-run fluctuations of income are less important than one might think in their effects on overall inequality measures. The presence of extra earners substantially reduces inequality. Less-than-full-year work increases inequality particularly among the very young and those over 45 years old. There remains some increase in inequality with age resulting from differentials in rates of advancement. Some difficulties in interpreting survey data in terms of the distribution of welfare require new data and new analysis, the main aspects of which are briefly sketched.

Age and Gender Differences in the Value of Productive Activities Four Different Approaches

The definition of personal productivity based on paid work is expanded to include many forms of unpaid work. The productivity of these forms of unpaid work is estimated empirically, using several economic approaches (an opportunity cost approach, a market price approach, and a value-added approach) and one noneconomic approach. Additionally, two methods of dealing with selection bias when estimating opportunity costs for nonemployed persons are compared. These different approaches all document the extent to which many of the activities (such as housework, formal volunteer work, or informal help to relatives and friends) that are often performed without pay by older Americans or women are actually productive because they produce goods and services to which a market value can be imputed. Using this expanded definition to describe the productive contribution of men and women at different ages provides a much needed correction to existing social statistics: Women contribute in major ways to U.S. productivity, as do older adults, although to a lesser degree. These findings challenge the stereotypic view of older Americans as unproductive and mere burdens on society. Data were from a 1986 cross-sectional survey of 3,617 adults representative of those 25 years old and older living in the coterminous United States.

Sense of Efficacy and Subsequent Change in Earnings-A Replication

This research investigates the relationship between contraceptive self-efficacy and contraceptive use, measured one year later, among adolescent boys and girls. Data are obtained from the two waves of the restricted use sample of the National ...

The Quantitative Study of Factors Determining Business Decisions

I. Personal interviews with a representative sample of business executives, 67; sampling, 69; interviewing, 70. — II. Study of industrial mobility, 72; advantages of Michigan location, 72; disadvantages of Michigan location, 76; qualitative information, 78; conclusions, 81. — III. Study of investment decisions, 82; the direct question of why, 83; correlation analysis, 86; detailed analysis of correlation cells, 88; summary, 89.

Education and Income

Introduction, 423. — The problem of method, 424. — Proposed procedures, 425. — Statistical method and source of data, 426. Explanatory factors in addition to education, 427. — Search for interaction effects, and more detail on education, 430. — Estimated lifetime earnings, 432. — Qualifications, 435. — Summary, 436.

The role of panel studies in research on economic behavior

The analytic and monetary costs and benefits of panel surveys are assessed in light of experiences from the Panel Study of Income Dynamics, an l&year panel swey on the economic status and behavior of the U.S. population. The analytic benefits of panel are for- midable, ranging from description of gross change to various analytic advantages of continuous and discrete time modelling. Analytic costs such as the conditioning of responses in subsequent participation or nonresponse bias are possible in panel surveys, but their effects can be minimized with proper data collection procedures and analytic adjustments. Surprisingly, the monetary costs of panel surveys are less than the costs of comparable repeated cross-sectional surveys.

The Achievement Motive and Economic Behavior

Recent developments in the psychology of personality and motivation promise to be of some real use in improving our ability to explain economic behavior. These have focused on a relatively few variables, variables which have been at least roughly measured and which are intended to explain the dynamics of behavior of reasonably normal individuals. At some point, presumably, it is advantageous to give up a little of the parsimony and elegance of economic theories about the behavior of consumers, workers, and businessmen, for improvement in ability to explain and predict that behavior.

The Role of Panel Studies in a World of Scarce Research Resources

A major development in social science research in the 1970s was the collection and analysis of several large-scale, nationally representative, longitudinal studies. Much has been learned from these studies because they provide more reliable information on changes in the objective and much more detailed point-in-time information than most existing cross-sectional studies and for much larger samples. As a result, they have also been viewed by analysts as better sources of cross-sectional information. However, because of their size and scope, they are seen as expensive ways of collecting data. As the size of the pie for social science funding shrinks, some feel that the value of the smaller-scale research projects foregone by funding panel data collection projects appears too great to warrant panel designs.