Individual Participant Data (IPD)

Over the past few years, evidence synthesis has become essential to investigate and improve the generalizability of medical research findings. This strategy often involves a meta-analysis to formally summarize quantities of interest, such as relative treatment effect estimates. The use of meta-analysis methods is, however, less straightforward in prognosis research because substantial variation exists in research objectives, analysis methods and the level of reported evidence. We present a gentle overview of statistical methods that can be used to summarize data of prognostic factor and prognostic model studies. We discuss how aggregate data, individual participant data, or a combination thereof can be combined through meta-analysis methods. Recent examples are provided throughout to illustrate the various methods.

To determine the course of serological tests in subjects with chronic T. cruzi infection treated with antitrypanosomal drugs. We conducted a systematic review and meta-analysis using individual participant data. Survival analysis and Cox proportional hazards regression model with a random effect to adjust for covariates were applied. The protocol was registered at www.crd.york.ac.uk/PROSPERO (CRD42012002162). We included 27 studies (1296 subjects) conducted in eight countries. The risk of bias was low for all domains in 17 studies (63.0%). We assessed 913 subjects (149 seroreversion events, 83.7% censored data) for ELISA, 670 subjects (134 events, 80.0% censored) for IIF, and 548 subjects (99 events, 82.0% censored) for IHA. A higher probability of seroreversion was observed in subjects aged 1-19 years compared to adults at a shorter time span. The chance of seroreversion also varied according to the country where the infection might have been acquired. For instance, the pooled adju...

There is increasing interest in cumulative approaches to science, in which instead of analyzing the results of individual papers separately, we integrate information qualitatively or quantitatively. One such approach is meta-analysis, which has over 50 years of literature supporting its usefulness, and is becoming more common in cognitive science. However, changes in technical possibilities by the widespread use of Python and R make it easier to fit more complex models, and even simulate missing data. Here we recommend the use of mega-analyses (based on the aggregation of data sets collected by independent researchers) and hybrid meta-mega-analytic approaches, for cases where raw data is available for some studies. We illustrate the three approaches using a rich test-retest data set of infants' speech processing as well as synthetic data. We discuss advantages and disadvantages of the three approaches from the viewpoint of a cognitive scientists contemplating their use, and limitations of this article, to be addressed in future work.