New method prevents biased weightings in clinical trials meta-analyses
The article compares methods for estimating standard deviations from sample ranges. It shows that unbiased estimators are available for both the population standard deviation and the sample standard deviation. The researchers recommend their preferred methods for accurate estimation. They also introduce a Taylor series method for calculating inverse-variance weights from sample ranges, which reduces bias compared to the commonly used method of taking the inverse of estimated variance. This new method is especially useful for small samples like clinical trials in meta-analyses.