The role of secondary outcomes in multivariate meta-analysis.

Univariate meta-analysis concerns a single outcome of interest measured across a number of independent studies. However, many research studies will have also measured secondary outcomes. Multivariate meta-analysis allows us to take these secondary outcomes into account, and can also include studies where the primary outcome is missing.

Model-based sensitivity analysis for outcome reporting bias in the meta analysis of benefit and harm outcomes.

Outcome reporting bias occurs when outcomes in research studies are selectively reported, the selection being influenced by the study results. For benefit outcomes, we have shown how risk assessments using the Outcome Reporting Bias in Trials risk classification scale can be used to calculate bias-adjusted treatment effect estimates. This paper presents a new and simpler version of the benefits method, and shows how it can be extended to cover the partial reporting and non-reporting of harm outcomes.

Borrowing of strength and study weights in multivariate and network meta-analysis.

Multivariate and network meta-analysis have the potential for the estimated mean of one effect to borrow strength from the data on other effects of interest. The extent of this borrowing of strength is usually assessed informally. We present new mathematical definitions of 'borrowing of strength'.

Generalized t-statistic for two-group classification.

In the classic discriminant model of two multivariate normal distributions with equal variance matrices, the linear discriminant function is optimal both in terms of the log likelihood ratio and in terms of maximizing the standardized difference (the t-statistic) between the means of the two distributions. In a typical case-control study, normality may be sensible for the control sample but heterogeneity and uncertainty in diagnosis may suggest that a more flexible model is needed for the cases. We generalize the t-statistic approach by finding the linear function which maximizes a standardized difference but with data from one of the groups (the cases) filtered by a possibly nonlinear function U.

A model-based correction for outcome reporting bias in meta-analysis.

It is often suspected (or known) that outcomes published in medical trials are selectively reported. A systematic review for a particular outcome of interest can only include studies where that outcome was reported and so may omit, for example, a study that has considered several outcome measures but only reports those giving significant results. Using the methodology of the Outcome Reporting Bias (ORB) in Trials study of (Kirkham and others, 2010.

Confidence intervals for random effects meta-analysis and robustness to publication bias.

The DerSimonian-Laird confidence interval for the average treatment effect in meta-analysis is widely used in practice when there is heterogeneity between studies. However, it is well known that its coverage probability (the probability that the interval actually includes the true value) can be substantially below the target level of 95 per cent. It can also be very sensitive to publication bias.

A robust P-value for treatment effect in meta-analysis with publication bias.

Publication bias is a major and intractable problem in meta-analysis. There have been several attempts in the literature to adapt methods to allow for such bias, but these are only possible if we are prepared to make strong assumptions about the underlying selection mechanism. We discuss the assumption that the probability that a paper is published may depend in some unspecified way on the P-value being claimed by that study.

Confidence intervals and P-values for meta-analysis with publication bias.

We study publication bias in meta-analysis by supposing there is a population (y, sigma) of studies which give treatment effect estimates y approximately N(theta, sigma(2)). A selection function describes the probability that each study is selected for review. The overall estimate of theta depends on the studies selected, and hence on the (unknown) selection function.

Publication bias affected the estimate of postoperative nausea in an acupoint stimulation systematic review.

Background And Objective: To assess the effect of publication bias and country effect on the results and conclusion of a systematic review of wrist P6 acupoint stimulation for the prevention of postoperative nausea and vomiting.

Methods: Reanalysis of a systematic review of 26 randomized trials comparing P6 acupoint stimulation with sham published in the Cochrane Database of Systematic Reviews using the Copas' sensitivity approach.

Results: If it is assumed that all studies that have ever been carried out are included, or that those selected for review are truly representative of all such studies, then the estimated relative risk (RR) for nausea was 0.

Sensitivity analysis for informative censoring in parametric survival models.

Most statistical methods for censored survival data assume there is no dependence between the lifetime and censoring mechanisms, an assumption which is often doubtful in practice. In this paper we study a parametric model which allows for dependence in terms of a parameter delta and a bias function B(t, theta). We propose a sensitivity analysis on the estimate of the parameter of interest for small values of delta.

A bound for publication bias based on the fraction of unpublished studies.

Publication bias in meta-analysis is usually modeled in terms of an accept/reject selection procedure in which the selected studies are the "published" studies and the rejected studies are the "unpublished" studies. One possible selection mechanism is to suppose that only studies that report an estimated treatment effect exceeding (or falling short of) some threshold are accepted. We show that, with appropriate choice of thresholds, this attains the maximum bias among all selection mechanisms in which the probability of selection increases with study size.

Meta-analysis for trend estimation.

Grouped dose measures, heterogeneity and publication bias are three major problems for meta-analysis in trend estimation. In this paper, we propose a model that allows for arbitrarily aggregated dose levels, and show that the resulting estimates and standard errors can be quite different from those given by the usual assigned value method. Based on fitting a model to the funnel plot, we discuss a method for random-effects sensitivity analysis that deals with the problems of heterogeneity and publication bias.

Meta-analysis, funnel plots and sensitivity analysis.

Publication bias is a major problem, perhaps the major problem, in meta-analysis (or systematic reviews). Small studies are more likely to be published if their results are 'significant' than if their results are negative or inconclusive, and so the studies available for review are biased in favour of those with positive outcomes. Correcting for this bias is not possible without making untestable assumptions.

Determining the efficacy of a pressure ulcer prevention program by collecting prevalence and incidence data: a unit-based effort.

Pressure ulcer prevention falls within the domain of nursing practice. When the results of a quality improvement survey indicated both an increase in the number of pressure ulcers and a higher prevalence than the national average, the nursing staff of a 500-bed Midwest hospital developed a pressure ulcer prevention program guided by the AHCPR guidelines. The literature supports collecting prevalence and incidence data as indicators of prevention program effectiveness, and the best indicator of the effectiveness of prevention strategies to reduce nosocomial pressure ulcers is incidence.

A sensitivity analysis for publication bias in systematic reviews.

There is no simple method of correcting for publication bias in systematic reviews. We suggest a sensitivity analysis in which different patterns of selection bias can be tested against the fit to the funnel plot. Publication bias leads to lower values, and greater uncertainty, in treatment effect estimates.

Reanalysis of epidemiological evidence on lung cancer and passive smoking.

Objective: To assess the epidemiological evidence for an increase in the risk of lung cancer resulting from exposure to environmental tobacco smoke.

Design: Reanalysis of 37 published epidemiological studies previously included in a meta-analysis allowing for the possibility of publication bias.

Main Outcome Measure: Relative risk of lung cancer among female lifelong non-smokers, according to whether her partner was a current smoker or a lifelong non-smoker.

Using regression models for prediction: shrinkage and regression to the mean.

The use of a fitted regression model in predicting future cases, either as a diagnostic tool or as an instrument for risk assessment is discussed. The regression to the mean effect implies that the future values of the response variable tend to be closer to the overall mean than might be expected from the predicted values. The extent of this shrinkage is studied for multiple and logistic regression models, and is found to be related to simple goodness-of-fit statistics of the original regression.

Using generalized linear models (GLMs) to model errors in motor performance.

Because of differences in design factors, experiments in human motor performance sometimes produce a wide range in variability or consistency in a subject's individual errors. These differences in variation often lead to heterogeneity in the variance-covariance matrices between group factors, which prohibits the use of repeated-measures (RM) ANOVA or MANOVA techniques to analyze the error data. Provided certain conditions are met, however, each subject's individual errors can be collapsed into the summary error measures, constant error (CE) and variable error (VE), which can still provide a more than adequate description of the subjects' performance.

Schizophrenia, bipolar disorder and depression. A discriminant analysis, using 'lifetime' psychopathology ratings.

Discriminant and canonical variate analyses were performed using 302 patients, on whom ratings of lifetime psychopathology and course of illness has been made. DSM-III diagnoses were used to form the criterion groups. Bipolar disorder emerged as a distinct grouping, but there are reasons for dissatisfaction with its definition.

Community care: does it reduce the need for psychiatric beds? A comparison of two different styles of service in three hospitals.

The admission pattern of under-65s during the first seven years of Kidderminster's District General Hospital Psychiatric Department was compared with the last seven years of the mental hospital (Powick Hospital) which it superseded in July 1978, and with its nearest mental hospital (Barnsley Hall Hospital). In Kidderminster the average length of patient's hospital stay was half that at Barnsley Hall. There were more admissions per head of population, more which lasted less than a week, and more patients with over six admissions to Kidderminster than Barnsley Hall.

Record linkage: statistical models for matching computer records.

"We wish to measure the evidence that a pair of records relates to the same, rather than different, individuals. The paper emphasizes statistical models which can be fitted to a file of record pairs known to be correctly matched, and then used to estimate likelihood ratios. A number of models are developed and applied to U.

The Facial Appearance Sorting Test (FAST): an aid to the selection of patients for rhinoplasty.

A simple test which requires a few minutes to administer and score is described as an aid to the selection of patients for rhinoplasty. The sorting of cards evaluating appearance is performed consistently over a period of time by individual subjects and by different groups of subjects. A numerical formula is proposed which allows for deviation from the common system of evaluating appearance in measuring support for an application for rhinoplasty.

Reshaping the psyche. The concurrent improvement in appearance and mental state after rhinoplasty.

Rhinoplasty patients and matched elective-surgery controls completed the Facial Appearance Sorting Test, the General Health Questionnaire, a Repertory Grid and the Masculinity/Femininity Scale. Rhinoplasty applicants perceived appearance similarly to, and downrated their own appearance to the same extent as, controls. Impaired appearance and psychiatric symptoms are integral parts of the 'rhinoplasty applicant syndrome', but the degree to which they occur is not positively correlated.