Meta-analysis statistics

A particular situation where bias may be important is in statistical meta-analysis, where statistical estimates are combined across studies. When estimates from individual studies may be averaged arithmetically, it is better to average unbiased estimates (Rao 1973, Section 3a). In case of biases that are consistent across studies, an arithmetic average would have a bias of the same sign, regardless of the number of studies included in the analysis. The average of biased estimates could fail to be consistent (in the statistical sense). 

Methods of statistical meta-analysis may be useful for combining information across studies. There are 2 principal varieties of meta-analytic estimation (Normand 1995). In a hxed-effects analysis the observed variation among estimates is attributable to the statistical error associated with the individual estimates. An important step is to compute a weighted average of unbiased estimates, where the weight for an estimate is computed by means of its standard error estimate. In a random-effects analysis one allows for additional variation, beyond statistical error, making use of a htted random-effects model. 

There is some USEPA precedent for use of statistical meta-analysis in a regulatory context, including the recent meta-analysis of organophosphate-related acetylcholinesterase inhibition data and meta-analysis of epidemiological studies on effects of 2nd hand tobacco smoke exposure. Warren-Hicks and Moore (1998) provide some discussion of the potential applicability of meta-analysis to ecological risk assessments. 

Different types of evidence can be ranked in term of importance when decisions about clinical interventions are made (Figure 19.1).13,14 For example, the confidence from randomized controlled trials gives stronger evidence for treatment effects than open studies. Moreover, apparently conflicting results between studies may be compatible when a statistical meta-analysis of the data has been performed. This chapter will give a brief summary of evidence on the treatment effects of common dry skin disorders with urea-formulations. Furthermore, data on the influence of urea on the skin barrier function will be reviewed. 

Barak Y, Swartz M, Shamir E, Stein D, Weizman A. Vitamin E (alpha-tocopherol) in the treatment of tardive dyskinesia a statistical meta-analysis. Ann Clin Psychiatry 1998 10(3) 101-5. 

Emilien G, Maloteaux JM, Seghers A, Charles G. Lithium compared to valproic acid and carbamazepine in the treatment of mania a statistical meta-analysis. Eur Neuropsychopharmacol. 1996 6 245-52. 

Before presenting oin discussion, we present a brief and select overview of some relevant literature. Peto (1987) discusses some foimdational issues in systematic reviews of randomized trials for rare outcomes, in particular the need for such reviews and considerations of heterogeneity of the treatment effect. Hammad et al. (2011) present a thorough overview of the issues associated with the secondary use of randomized trials to evaluate safety. Bradbum et al. (2007) evaluate statistical meta-analysis methods for rare events. Kaizer et al. (2006) present an interesting example of a hierarchical Bayesian method for meta-analysis of safety. Crowe et al. (2009) provide recommendation for a premarket safety program. 

For cost and demand data, we use the cost-benefit assessment performed by the Washington State Institute for Public Policy (WSIPP) (Lee et al. 2012). Using a statistical meta-analysis approach, the report estimates monetary values of benefifs and costs of various prevenfion programs. Moreover, it provides not only measures of juvenile justice buf... 

Tannins represent a class of plant secondary metabolites and are produced by plants in their intermediary metabolism. Tannins are considered to be a promising group of substances to decrease methane (CH ) emission from ruminants by dietary means. However, there is no common agreement whether tannins generally decrease CH formation in vivo or not and to which extent (Beauchemin et al., 2008). Therefore, research on this particular topic is needed to summarize and to quantify the tannin effects on CH production from ruminants and its associated variables. The objective of this study was to estimate the relationship between dietary tannin levels and CH emission from ruminant animals by compiling available literature data of respective experiments using a statistical meta-analysis approach. 

The analysis of the data assembled in the database was made by a statistical meta-analysis approach (St-Pierre, 2001 Sauvant et al, 2008). Experiments were treated as random effects whereas tannin levels were treated as fixed effects using the following model ... 

When the CAST collaborative group performed a meta-analysis of 1ST, CAST, and MAST-I, the trend seen in CAST and 1ST toward a beneficial effect of aspirin on the rate of death or dependency reached the threshold for statistical significance. Early aspirin therapy (160-300 mg/day) conferred an absolute reduction in the rate of recurrent ischemic stroke by 0.7% (7 per 1000 patients treated) (p < 0.001) and reduced the rate of death or dependency by 1.3% (13 per 1000 patients treated) (2p = 0.007). Aspirin caused about 2 hemorrhagic strokes among every 1000 patients treated, but prevented about 11 other strokes or deaths in hospital. 

A recent meta-analysis evaluated patients at doses of 15 and 30 mg daily. Patients were analyzed for periods of 2 to 24 weeks. The majority of patients enrolled were female, and more than 80% of the patients evaluated received adjunctive modification in lifestyle. An average weight loss of 3.6 kg (7.9 lbs) was demonstrated for patients treated with phentermine compared with placebo. Although modest in amount, this value was statistically significant.37... 

One meta-analysis reviewed patients receiving doses of 75 mg daily during periods of 6 to 52 weeks. Similar to study characteristics for phentermine, the majority of patients enrolled were female, and all patients implemented adjunctive lifestyle modifications. The average additional weight loss observed was 3 kg (6.6 lbs) compared with diet and exercise alone, resulting in a borderline statistically significant difference.37... 

Cochrane Library. The Cochrane Library [44] includes The Cochrane Database of Systematic Reviews, a collection of regularly updated, systematic reviews of the effects of health care. It is maintained by contributors to the Cochrane Collaboration. Cochrane reviews are reviews mainly of randomized controlled trials. To minimize bias, evidence is included or excluded on the basis of explicit quality criteria. Data are often combined statistically, with meta-analysis, to increase the power of the findings of numerous studies, each too small to produce reliable results individually. Database of Abstracts of Reviews of Effectiveness is also included. It consists of critical assessments and structured abstracts of good systematic reviews published elsewhere. The Cochrane Controlled Trials Register with bibliographic information on controlled trials and other sources of information on the science of reviewing research and evidence-based health care are part of the Cochrane Library. It is commercially available on CD-ROM or the Internet. 

The article that follows is a controversial one. It reaches a controversial conclusion - that much of the therapeutic benefit of antidepressant medications actually derives from placebo responding. The article reaches this conclusion by utilizing a controversial statistical approach - meta-analysis. And it employs meta-analysis controversially - by meta-analysing studies that are very heterogeneous in subject selection criteria, treatments employed, and statistical methods used. Nonetheless, we have chosen to publish the article. We have done so because a number of the colleagues who originally reviewed the manuscript believed it had considerable merit, even while they recognized the clearly contentious conclusions it... 

To answer this question, the regulators conducted their own meta-analysis of some of the data in their files. Their results were very similar to ours. They agreed that the average observed difference in improvement between drug and placebo is only about two points on the Hamilton scale, and their data also showed that most of the drug response could be explained as a placebo effect. Nevertheless, they argued that they had shown that the drugs were better than placebos, not only statistically, but clinically as well. 

When our most recent - and most definitive - meta-analysis was published, the headlines in many newspapers blazoned that antidepressants don t work .1 The Daily Telegraph headline phrased it more specifically, clarifying that antidepressants are no better than dummy pills ,2 but even this headline was not entirely accurate. What our analyses actually showed was that antidepressants work statistically better than placebos, but that this statistical difference was not clinically meaningful. It was too small a difference to be of much importance in the life of a severely depressed person. 

There are now common practices in the analysis of safety data, though they are not necessarily the best. These are discussed in the remainder of this chapter, which seeks to review statistical methods on a use-by-use basis and to provide a foundation for the selection of alternatives in specific situations. Some of the newer available methodologies (meta-analysis and Bayesian approaches) should be kept in mind, however. 

Meta-analysis aims to increase the statistical power of the available evidence by combining the results of smaller trials together using specific statistical methods. The validity of the meta-analysis will depend on the quality of the evidence on which it is based and how homogeneous or comparable the samples are. Combining very heterogeneous study populations can lead to bias. 

A meta-analysis is the statistical procedure for combining data from multiple studies. When the effect (or effect size) is consistent from one study to the next, a meta-analysis can be used to... 

In simple terms, meta-analysis is the practice of using statistical methods to combine and quantify the outcomes of a series of studies in a single, pooled analysis. What is crucial in this definition is the emphasis on the use of statistical methods. In most biomedical research, the scientific review has a lengthy history and is still widely used. However, insofar that it does not utilise statistical methods for pooling results, and tends to summarise more in qualitative rather than quantitative terms it cannot be regarded as meta-analysis. 

With regard to relevant statistical methodologies, it is possible to dehne 2 situations, which can be termed a meta-analysis context and a shrinkage estimation context. Similar statistical models, in particular random-effects models, may be applicable in both situations. However, the results of such a model will be used somewhat differently. 

Traditionally, one did a review of those studies writing a narrative about them and drawing conclusions based on the subjective evaluation of this information by the reviewer. A different way to write review articles, named meta-analysis, was introduced into clinical medicine by Chalmers. It has been defined as a systematic review of studies that uses quantitative statistical procedures to combine, synthesize, and integrate information across these studies . What this methodology does is take a group of... 

Intermittent claudication appears to benefit from ginkgo therapy many studies demonstrate improved walking distance and decreased pain. One meta-analysis of eight studies documented statistically significant improvement but questioned its clinical relevance. In some studies, the high doses (240 mg) appeared more effective. 

---