Regression methods for high dimensional multicollinear data

To compare their performance on high dimensional data, several regression methods are applied to data sets in which the number of exploratory variables greatly exceeds the sample sizes. The methods are stepwise regression, principal components regression, two forms of latent root regression, partial least squares, and a new method developed here. The data are four sample sets for which near infrared reflectance spectra have been determined and the regression methods use the spectra to estimate the concentration of various chemical constituents, the latter having been determined by standard chemical analysis. Thirty-two regression equations are estimated using each method and their performances are evaluated using validation data sets. Although it is the most widely used, stepwise regression was decidedly poorer than the other methods considered. Differences between the latter were small with partial least squares performing slightly better than other methods under all criteria examined, albeit not by a statistically significant amount.     

Bayesian prediction for small areas using sur models

Sample surveys are usually designed and analyzed to produce estimates for larger areas and/or populations. Nevertheless, sample sizes are often not large enough to give adequate precision for small area estimates of interest. To circumvent such difficulties, borrowing strength from related small areas via modeling becomes essential. In line with this, we propose a hierarchical multivariate Bayes prediction method for small area estimation based on the seemingly unrelated regressions (SUR) model. The performance of the proposed method was evaluated through simulation studies.     

An implicit function based procedure for analyzing maximum likelihood estimates from nonidentically distributed data

A methodology is presented for gaining insight into properties — such as outlier influence, bias, and width of confidence intervals — of maximum likelihood estimates from nonidentically distributed Gaussian data. The methodology is based on an application of the implicit function theorem to derive an approximation to the maximum likelihood estimator. This approximation, unlike the maximum likelihood estimator, is expressed in closed form and thus it can be used in lieu of costly Monte Carlo simulation to study the properties of the maximum likelihood estimator.     

Book review

State-Space Models with Regime Switching by Chang-Jin Kim and Charles R. Nelson. Pp. 250. Cambridge, Massachnsetts: MIT Press, 1999. ($40.00 cloth) WEB INFOR~UATION: http://mitpress.mit.edu/book-home.tcl?isbn=0262l123.     

Bunk Bed Injuries in College Students

Abstract

We surveyed 1,431 college seniors to investigate the frequency and severity of injury after falls from bed. This data was analyzed along with data obtained from both the Consumer Product Safety Commission and the armed forces. We found that falls from bed are common in young adults and that injuries are more likely to occur with falls from bunk or loft beds than from standard beds (p = 0.025). Falls were most common when students were climbing out of bed or were startled awake. Alcohol use was implicated in 36% of the falls. We recommend that the heights of nonstandard beds for students be lowered, that alarms and phones be placed within easy reach, and that sturdy, fixed devices be used to descend. Intoxicated individuals should be placed on standard beds or lower.     

Variables Affecting Readiness to Benefit From Career Interventions

This article identifies and briefly describes the broad range of variables that may influence clients’ readiness to benefit from career interventions. The article also discusses consequences of low readiness for effective use of career interventions and addresses implications for practice as well as for future research. Variables contributing to low readiness for effective use of career interventions include personal characteristics and circumstances; knowledge of self, options, and decision making; and prior experience with career interventions. Consequences of low readiness for using career interventions include premature disengagement, negative perception of skills and interests, selective acquisition of incomplete information, premature choice foreclosure, protracted exploration, dependent decision‐making style, and poor evaluation of options.     

Growth curve analysis of complete and incomplete longitudinal data

Growth curve analysis is reviewed for both complete and incomplete data structures. Specific attention is paid to the incomplete data model of Kleinbaum and its applicability to the mixed longitudinal study. Design considerations and efficiency for various incomplete longitudinal studies are also discussed.     

REVISITING KEY ISSUES ABOUT COLLECTIVE BEHAVIOR,ORGANIZING, AND ROLE ENACTMENT

This article addresses the benefits of using a structural code and a role analysis framework for conducting organizational research in the context of a disaster. In the present article, I apply that code and framework to Thomas Forrest's earlier analysis of a organization, the Interfaith Emergency Center (IEC), that emerged during the Detroit civil disturbance of 1967. Kreps' structural code is applied to the same set of interviews and documents that constituted the database for Forrest's original case study (Disaster Research Center data archives). I first document the origins and restructuring of the IEC using the structural code. I then perform a role level analysis that builds on Bosworth and Kreps' three dimensional framework. That framework addresses the expectational, relational, and behavioral dimensions of role enactment. Revisiting Forrest's original study results in a more theoretically rich analysis of how and why the IEC emerged in the way that it did during the emergency period.