Comparing alternative models: log vs Cox proportional hazard?

Health economists often use log models (based on OLS or generalized linear models) to deal with skewed outcomes such as those found in health expenditures and inpatient length of stay. Some recent studies have employed Cox proportional hazard regression as a less parametric alternative to OLS and GLM models, even when there was no need to correct for censoring. This study examines how well the alternative estimators behave econometrically in terms of bias when the data are skewed to the right. Specifically we provide evidence on the performance of the Cox model under a variety of data generating mechanisms and compare it to the estimators studied recently in Manning and Mullahy (2001). No single alternative is best under all of the conditions examined here. However, the gamma regression model with a log link seems to be more robust to alternative data generating mechanisms than either OLS on ln(y) or Cox proportional hazards regression. We find that the proportional hazard assumption is an essential requirement to obtain consistent estimate of the E(y|x) using the Cox model.     

The retiree health care question: to prefund or not to prefund?

Some experts say it's possible to control FAS No. 106 expense and liability by prefunding. Others say prefunding is an impractical solution for most companies.     

Unsolicited GP advice against smoking: to give or not to give?

This article discusses whether general practitioners (GPs) should give unsolicited antismoking advice to patients who smoke. Patient preferences and GP advice-giving are discussed with particular reference to professional roles. It is suggested that giving unsolicited advice against smoking at nearly every encounter is a competitive rather than collaborative behavior. General practitioners should ascertain patients' readiness for change before offering to help produce individualized agreements of joint benefit on change. Three strategies for negotiation--bridging, trading, and logrolling--are discussed.     

Computational methods in medical decision making: to screen or not to screen?

Screening for a disease such as cancer is often regarded as a beneficial and successful strategy for reducing mortality. However, as with any clinical treatment or intervention, benefit cannot be assumed, and screening can entail both costs and harms, so the screening as a 'treatment' must undergo evaluation. An evaluation requires a definition of the treatment 'benefit', design of studies to measure that benefit with as little bias and variance as possible, and the development of methods for estimating the potential benefit. In screening studies, the factors most central to the evaluation are unobservable (e.g. earliest point in time at which disease becomes detectable, or 'preclinical'; time at which disease might have been detected in the absence of screening; test sensitivity). Thus, screening programs should be evaluated on scenarios in which these factors are varied, to ensure the robustness of the estimated benefit under a variety of circumstances. This article describes the importance of computational methods and simulations to assess the benefit of screening programs, particularly for cancer, based on randomized screening trials, with special attention to benefit time, lead time, and bias due to length-biased sampling.     

To QC or not to QC: the key to a consistent laboratory?

A limiting factor in every embryology laboratory is its capacity to grow 'normal' embryos. In human in vitro fertilisation (IVF), there is considerable awareness that the environment of the laboratory itself can alter the quality of the embryos produced and the industry as a whole has moved towards the implementation of auditable quality management systems. Furthermore, in some countries, such as Australia, an established quality management system is mandatory for clinical IVF practice, but such systems are less frequently found in other embryology laboratories. Although the same challenges of supporting consistent and repeatable embryo development are paramount to success in all embryology laboratories, it could be argued that they are more important in a research setting where often the measured outcomes are at an intracellular or molecular level. In the present review, we have outlined the role and importance of quality control and quality assurance systems in any embryo laboratory and have highlighted examples of how simple monitoring can provide consistency and avoid the induction of artefacts, irrespective of the laboratory's purpose, function or species involved.     

Breast cancer in Canada: To screen or not to screen?

Lomas (1988) and Sabatier (1987) have suggested models by which to examine the roles that values, scientific knowledge, institutions, and the learning process play in the formulation of both national and clinical health-care policies. Utilizing their frameworks, this article offers an explanation for the development of high-volume screening mammography policies in Canada, despite the suggested inefficacy of screening technologies for 'unavoidable' illnesses such as carcinoma in the breast. The preliminary results of Canada's National Breast Screening Study further complicate this tissue. Inappropriate framing of the 'problem' in the policy-making process, by actors highly influenced by societal values and scientific evidence, is identified as the reason for present and planned policies and practices contradicting the first principles of health-policy analysis.