Prediction in dynamic models with time-dependent conditional variances

This paper considers forecasting the conditional mean and variance from a single-equation dynamic model with autocorrelated disturbances following an ARMA process, and innovations with time-dependent conditional heteroskedasticity as represented by a linear GARCH process. Expressions for the minimum MSE predictor and the conditional MSE are presented. We also derive the formula for all the theoretical moments of the prediction error distribution from a general dynamic model with GARCH(1, 1) innovations. These results are then used in the construction of ex ante prediction confidence intervals by means of the Cornish-Fisher asymptotic expansion. An empirical example relating to the uncertainty of the expected depreciation of foreign exchange rates illustrates the usefulness of the results. © 1992.

Missing data in randomized clinical trials for weight loss: scope of the problem, state of the field, and performance of statistical methods.

BACKGROUND: Dropouts and missing data are nearly-ubiquitous in obesity randomized controlled trails, threatening validity and generalizability of conclusions. Herein, we meta-analytically evaluate the extent of missing data, the frequency with which various analytic methods are employed to accommodate dropouts, and the performance of multiple statistical methods. METHODOLOGY/PRINCIPAL FINDINGS: We searched PubMed and Cochrane databases (2000-2006) for articles published in English and manually searched bibliographic references. Articles of pharmaceutical randomized controlled trials with weight loss or weight gain prevention as major endpoints were included. Two authors independently reviewed each publication for inclusion. 121 articles met the inclusion criteria. Two authors independently extracted treatment, sample size, drop-out rates, study duration, and statistical method used to handle missing data from all articles and resolved disagreements by consensus. In the meta-analysis, drop-out rates were substantial with the survival (non-dropout) rates being approximated by an exponential decay curve (e(-lambdat)) where lambda was estimated to be .0088 (95% bootstrap confidence interval: .0076 to .0100) and t represents time in weeks. The estimated drop-out rate at 1 year was 37%. Most studies used last observation carried forward as the primary analytic method to handle missing data. We also obtained 12 raw obesity randomized controlled trial datasets for empirical analyses. Analyses of raw randomized controlled trial data suggested that both mixed models and multiple imputation performed well, but that multiple imputation may be more robust when missing data are extensive. CONCLUSION/SIGNIFICANCE: Our analysis offers an equation for predictions of dropout rates useful for future study planning. Our raw data analyses suggests that multiple imputation is better than other methods for handling missing data in obesity randomized controlled trials, followed closely by mixed models. We suggest these methods supplant last observation carried forward as the primary method of analysis.

Implant healing in experimental animal models of diabetes.

Diabetes mellitus is becoming increasingly prevalent worldwide. Additionally, there is an increasing number of patients receiving implantable devices such as glucose sensors and orthopedic implants. Thus, it is likely that the number of diabetic patients receiving these devices will also increase. Even though implantable medical devices are considered biocompatible by the Food and Drug Administration, the adverse tissue healing that occurs adjacent to these foreign objects is a leading cause of their failure. This foreign body response leads to fibrosis, encapsulation of the device, and a reduction or cessation of device performance. A second adverse event is microbial infection of implanted devices, which can lead to persistent local and systemic infections and also exacerbates the fibrotic response. Nearly half of all nosocomial infections are associated with the presence of an indwelling medical device. Events associated with both the foreign body response and implant infection can necessitate device removal and may lead to amputation, which is associated with significant morbidity and cost. Diabetes mellitus is generally indicated as a risk factor for the infection of a variety of implants such as prosthetic joints, pacemakers, implantable cardioverter defibrillators, penile implants, and urinary catheters. Implant infection rates in diabetic patients vary depending upon the implant and the microorganism, however, for example, diabetes was found to be a significant variable associated with a nearly 7.2% infection rate for implantable cardioverter defibrillators by the microorganism Candida albicans. While research has elucidated many of the altered mechanisms of diabetic cutaneous wound healing, the internal healing adjacent to indwelling medical devices in a diabetic model has rarely been studied. Understanding this healing process is crucial to facilitating improved device design. The purpose of this article is to summarize the physiologic factors that influence wound healing and infection in diabetic patients, to review research concerning diabetes and biomedical implants and device infection, and to critically analyze which diabetic animal model might be advantageous for assessing internal healing adjacent to implanted devices.