Blog
RAND is introducing a new method of forecasting the outcomes of U.S. Presidential elections. Rather than repeatedly poll new random samples, this poll uses panel of 3,500 people who are asked the same questions every week. The results illustrate the effects of election season variables.
Journal Article
There is a bias-variance tradeoff at work in propensity score estimation; every step toward better balance usually means an increase in variance and at some point a marginal decrease in bias may not be worth the associated increase in variance.
Journal Article
This paper presents a five-point checklist to guide those who want to improve their performance reporting methods. The goal is to minimize the frequency and severity of misclassifying providers and avoid adverse unintended consequences of reporting.
Journal Article
Brian Stucky and Claudia Pereira review the book Measurement in Medicine: A Practical Guide.
Journal Article
The amount of additional heterogeneity in effect sizes is a crucial factor in determining when associations between quality and effect sizes can be detected.
Report
The methods employed, as well as those recommended for future studies, are applicable to any law enforcement agency interested in attracting and identifying high-quality applicants more efficiently.
Report
Describes a methodology for identifying areas where problem events are more pronounced and directing resources toward those areas.
Journal Article
Researchers develop the "generalized persistence" (GP) model, a Bayesian multivariate model for estimating teacher effects that accommodates longitudinal data that are not vertically scaled by allowing less than perfect correlation of a teacher's effects across test administrations.
Report
Explains the relationship between reliability measurement and misclassification for physician quality and cost measures in health care. Provides a method to calculate reliability and misclassification from data typically available to health plans.
Journal Article
Using a discrete time semi-Markov model, the authors develop an algorithm for nonparametric estimation of the distribution functions of sojourn times in a J state progressive disease model.
Journal Article
Interview time in personal network studies can be reduced by randomly sampling a smaller set of the alters named by the respondent and simulating the error that results when data are collected from the smaller group.
Report
This report documents the results obtained from the re-estimation of models apportioning travel to destination area types, distance band and travel mode for an important component of the UK National Travel Model (NTM).
Report
As part of an effort examining officer development in joint matters, the authors use data analysis and complex modeling to identify billets that provide and/or require joint experience and to assess the supply and demand of joint officers.
Journal Article
Previous studies have demonstrated both large gains in efficiency and reductions in bias by incorporating population information in regression estimation with sample survey data.
Journal Article
Contrary to previous conclusions, the authors find that respondents do not tend to overweight private information when updating beliefs.
Journal Article
Substance abuse treatment research is complicated by the pervasive problem of non-ignorable missing data-i.e. the occurrence of the missing data is related to the unobserved outcomes. Missing data frequently arise due to early client departure from treatment. Pattern-mixture models (PMMs) are often employed in such situations to jointly model the outcome and the missing data mechanism.
Journal Article
The authors studied the feasibility of using an internet-based panel survey to obtain timely and accurate population-based data on influenza vaccination.
Journal Article
Bayesian models coupled with optimizing a loss function provide an effective framework for computing non-standard inferences such as ranks. Inferences depend on the posterior distribution and should be guided by inferential goals. However, even optimal methods might not lead to definitive results and ranks should be accompanied by valid uncertainty assessments. The authors outline the Bayesian approach and use estimated Standardized Mortality Ratios (SMRs) in 1998-2001 from the United States Renal Data System (USRDS) as a platform to identify issues and demonstrate approaches.
Journal Article
The authors consider situations in which externally observable characteristics allow experts to quickly categorize individual households as likely or unlikely to contain a member of a rare target population.
RAND® is a registered trademark. Copyright © 1994-2013 RAND Corporation. Last Modified: January 29, 2011 Site Feedback »