Marginal and association regression models for longitudinal binary data with drop‐outs: A likelihood‐based approach

Longitudinal data often contain missing observations, and it is in general difficult to justify particular missing data mechanisms, whether random or not, that may be hard to distinguish. The authors describe a likelihood‐based approach to estimating both the mean response and association parameters for longitudinal binary data with drop‐outs. They specify marginal and dependence structures as regression models which link the responses to the covariates. They illustrate their approach using a data set from the Waterloo Smoking Prevention Project They also report the results of simulation studies carried out to assess the performance of their technique under various circumstances.     

Robustness of testing the equality of two slopes in simple linear structural relationships

The usual test of the equality of two slopes in a simple structural relation-ship is the test formed from the normal approximation using the Fisher information matrix, assuming two explanatory variables are independent. This paper examines the robustness if the explanatory variables are, in fact, dependent. A more efficient estimator is derived for a matched pair situation.     

Seemingly unrelated regression on the autoregressive (Ar(p)) singular equation system

This paper studies the estimation of seemingly unrelated regressions (SUR) of singular equation systems with an autoregressive error process (AR(p)) for each equation.Parameter estimates of the autoregressive singular equation system are not generally invariant to the equation deleted. Under the model specification restriction on the autoregressive parameters, the invariance property is preserved, and this paper shows that a single equation generalized least squares (GLS) estimation for a general autoregressive error process is equivalent to the SURGLS estimation of the AR(p) singular equation system.     

Cognitive and interpersonal abilities related to the primary activities of R&D managers

This study attempted to identify the primary activities performed by R&D managers at different supervisory levels, and the cognitive and interpersonal ability requirements that underlie these activities. A task inventory containing 244 managerial tasks was completed by 117 R&D managers in nine organizations. The 48 tasks which managers rated as having spent the most time were factor analyzed, resulting in the identification of three primary activities: project management, personnel supervision, and strategic planning. Furthermore, these activities varied with supervisory level, with R&D managers performing a wider range of these activities with the progression from first-line to upper-level management.Thirty R&D managers later rated the degree to which 19 cognitive and interpersonal abilities were required for performing these primary activities. Strategic planning was rated as requiring significantly higher levels of oral expression, logical reasoning, originality, fluency of ideas, oral defense, and resistance to premature judgement than was required for the other two primary activities. Personnel supervision required a higher level of social sensitivity than was required for the other two activities. Project management required high levels of information ordering, oral fact- finding ability, problem sensitivity, and oral and written comprehension. Implications of the findings for understanding R&D managerial performance and personnel staffing functions are discussed.     

Racial differences in urban neighboring

Despite mixed expectations generated by existing theories and evidence, this analysis documents clear racial differences in urban neighboring behavior. Using data from a survey of Nashville, Tennessee, residents, we show that blacks interact with their neighbors more often than whites do, and in a greater variety of ways. The only noteworthy similarity between the two groups is the positive impact of neighboring on feelings of community affect. Overall, our results support the view that neighbor relations — like other kinds of informal participation — have helped blacks cope with constrained social opportunities and provided them with access to resources unavailable through formal institutional channels.Revised version of a paper presented at the annual meeting of the American Sociological Association, San Francisco, August 1989.     

Economic Reform in the Czech Republic: Economic Strain,Depression, Hostility,and the Difference Gender Makes*

The Czech Republic is changing rapidly and its current economic transformation is a strain on Czech families. In this study, the connection between economic strain and individual well-being is investigated via mailed questionnaires from 234 households in the Czech Republic. For Czech women, depression rises more with economic strain than does hostility, while Czech men become more hostile than depressed in the face of economic strain. For women, social support is a buffer between economic strain and hostility, whereas self-esteem is a buffer for depression. For men, both self-esteem and social support exacerbate hostility in the context of economic strain.     

Grounded Neural Networking: Modeling Complex Quantitative Data

The latest advances in artificial intelligence software (neural networking) have finally made it possible for qualitative researchers to apply the grounded theory method to the study of complex quantitative databases in a manner consistent with the postpositivistic, neopragmatic assumptions of most symbolic interactionists. The strength of neural networking for the study of quantitative data is twofold: it blurs the boundaries between qualitative and quantitative analysis, and it allows grounded theorists to embrace the complexity of quantitative data. The specific technique most useful to grounded theory is the Self‐Organizing Map (SOM). To demonstrate the utility of the SOM we (1) provide a brief review of grounded theory, focusing on how it was originally intended as a comparative method applicable to both quantitative and qualitative data; (2) examine how the SOM is compatible with the traditional techniques of grounded theory; and (3) demonstrate how the SOM assists grounded theory by applying it to an example based on our research.