Layman’s abstract for paper on meta‐analysis of quantile intervals from different studies with an application to a pulmonary tuberculosis data

Each week, we will be publishing layman’s abstracts of new articles from our prestigious portfolio of journals in statistics. The aim is to highlight the latest research to a broader audience in an accessible format.

The article featured today is from Statistics in Medicine, with the full article now available to read here.

Ozturk, OBalakrishnan, NMeta‐analysis of quantile intervals from different studies with an application to a pulmonary tuberculosis dataStatistics in Medicine2020; 4519-4537.

Quite often, at the completion of many clinical studies, statistical results are published in the form of confidence intervals whose end points are some specific ordered values observed in the data.  Such confidence intervals do not require any specific assumption on the distribution. For example, intervals may be constructed from data set generated asymmetric and skewed distributions, but they are proper confidence intervals that give correct coverage probabilities for the true quantile of the characteristic under study. These confidence intervals do not require normality assumption and are referred to as distribution-free confidence intervals.

The natural question that arises then is, if such intervals are available as final statistical results from many different clinical studies, how one can pool these results.  To be specific, one may desire a meta-analysis procedure to propose a specific confidence interval for the true quantile based on the confidence intervals available from all the independent studies that possesses some desirable and optimal properties. Such a specific meta-analysis procedure is proposed in this paper and its efficiency and probabilistic performance are demonstrated through simulations.  A pulmonary tuberculosis diagnosis study from China is finally used illustrate the proposed methodology by constructing a meta-analysis confidence interval for the median patient delay characteristic.


More Details