Choice of the primary analysis in longitudinal clinical trials

Missing data, and the bias they can cause, are an almost ever‐present concern in clinical trials. The last observation carried forward (LOCF) approach has been frequently utilized to handle missing data in clinical trials, and is often specified in conjunction with analysis of variance (LOCF ANOVA) for the primary analysis. Considerable advances in statistical methodology, and in our ability to implement these methods, have been made in recent years. Likelihood‐based, mixed‐effects model approaches implemented under the missing at random (MAR) framework are now easy to implement, and are commonly used to analyse clinical trial data. Furthermore, such approaches are more robust to the biases from missing data, and provide better control of Type I and Type II errors than LOCF ANOVA. Empirical research and analytic proof have demonstrated that the behaviour of LOCF is uncertain, and in many situations it has not been conservative. Using LOCF as a composite measure of safety, tolerability and efficacy can lead to erroneous conclusions regarding the effectiveness of a drug. This approach also violates the fundamental basis of statistics as it involves testing an outcome that is not a physical parameter of the population, but rather a quantity that can be influenced by investigator behaviour, trial design, etc. Practice should shift away from using LOCF ANOVA as the primary analysis and focus on likelihood‐based, mixed‐effects model approaches developed under the MAR framework, with missing not at random methods used to assess robustness of the primary analysis. Copyright © 2004 John Wiley & Sons, Ltd.     

An introduction to econometric applications of empirical process theory for dependent random variables

This paper discusses some uses in econometrics of empirical process theory for dependent rendom variables. Examples considered include non-standard parametric hypotheses tests and semiparametric estimation. The application of bracketing functional limit results is discussed in some detail     

The historical decline of fertility in Eastern Europe

I test the hypothesis that the growth of autonomy was the factor responsible for the decline of marital fertility in eight Eastern European countries. By growth of autonomy I mean increased control over one's political, personal, religious, economic and reproductive life. This increased control was manifested in revolutions, democratic political reforms, nationalist movements and declining marital fertility. The political reforms were the result of the growth of autonomy but they also accelerated the dissemination of these new ideas among the populace contributing to further growth of autonomy. My hypothesis is generally supported by the historical data.     

Screening for patients with alcohol problems: severity of patients identified by the CAGE.

Primary care physicians are well situated to identify patients with substance abuse problems and motivate them to seek appropriate assistance, but active programs are the exception. A study in a community setting was undertaken to assess the CAGE (the first letters of key words in a series of four questions about drinking: cut down; annoyed; guilty; and eye-opener), instrument in the routine screening for alcohol problems in both new and established patients. The screening process identified subjects for a pilot evaluation of a motivational interview designed to encourage problem-solving behavior. This article focuses on the screening results and the use of the CAGE instrument. During June and July of 1990, 687 patients of two primary care physicians belonging to a large group practice were asked to complete a health questionnaire that included the CAGE. Those who responded affirmatively to at least two of the four CAGE questions were requested to participate in follow-up assessment of problems associated with alcohol and health. The type and severity of alcohol problems experienced by patients who scored positive on the CAGE are described. Prevalence of a positive score on the CAGE was 8.6 percent with males, smokers, and blue collar and unemployed persons being more likely to score positive. The positive predictive value was .68. Primarily, persons with moderate alcohol problems were identified. Results show that the CAGE instrument is a useful screening device for identifying those with mild to moderate substance abuse problems, increasing the opportunity for intervention prior to serious medical complications. The instrument is easily administered, and has demonstrated relatively high levels of sensitivity and specificity. When combined with assessment and motivational interviews, the CAGE shows promise in the secondary prevention of substance abuse and related health problems.     

Negotiating Role Definitions and the Working Consensus in Self-Work*

Definitions of social roles and the maintenance of a working consensus are two kinds of background expectations which are important for actors’accomplishment of self-work. Interactionists have traditionally assumed that these background expectations are unambiguously available to social actors as they negotiate situated meanings of selves and situations. Using data from dyadic role-play conversations, this study examines instances where interactants reference these expectations as ambiguous or problematic. The findings show that the situated meanings of role definitions and the working consensus are continually subject to potential negotiation. The implications of these findings for future research and theory on self-work in social interaction are discussed.     

EFFECTS OF A PREPAID NONMONETARY INCENTIVE ON RESPONSE RATES AND RESPONSE QUALITY IN A FACE-TO-FACE SURVEY

We conducted a randomized experiment on a face-to-face interviewsurvey in order to test the effects on response rates of a prepaidnonmonetary incentive. Results showed a statistically significantincrease in response rates, mostly through reduction in refusalrates, in the half sample that received the incentive (a gift-typeballpoint pen) as compared with a no incentive control group.The effect appears to be due to greater cooperation from incentiverecipients at the initial visit by an interviewer. Unexpectedly,the incentive group also showed a significantly higher rateof sample ineligibility, possibly due to easier identificationof vacant residences or nonexistent addresses. In addition,evidence suggests greater response completeness among respondingincentive recipients early in the interview, with no evidenceof increased measurement error due to the incentive.     

TESTING SPHERICITY UNDER A MIXTURE MODEL

The robustness of Mauchly's sphericity test criterion when sampling from a mixture of two multivariate normal distributions is studied. The distribution of the sphericity test criterion when the sample covariance matrix has a non-central Wishart density of rank one is derived in terms of Meijer's G-functions; its distribution under the mixture model is then deduced. The robustness is studied by computing actual significance levels of the test under the mixture model using the critical values under the usual normal model.     

Agency costs,property rights,and the evolution of labor unions

Collective bargaining requires that an agent represent workers. This paper examines the implications for the trade union movement of the resulting agency costs. Without transferable rights in the union, union members lack the means and incentive to bring forth the innovative agent controls common to the modern corporation. Considerations of the bargaining strengths of employers and employees, each represented by an agent, provide an explanation of the simultaneous decline of private sector union membership (corporate share holders have been more successful at lowering agency costs) and growth of public sector union representation (where the union official, a “double agent,” serves the interest of both employee and bureaucratic employer). The authors acknowledge the helpful remarks Donald L. Martin whose earlier research on property rights in unions inspired this effort. Don Bellante’s work was supported by a grant from the Research Committee of the College of Business Administration, University of South Florida.     

A note on inverse estimation in non-linear models

The problem of estimating the value of an x variable for a given proportion of an observed value of the y variable is consdered for a non-linear model. Asymptotic confidence limits are obtained and an application of the method is illustrated witreal data.