How to conduct a meta-analysis using raw data?

Question

I think meta-analyses are a great way of exploring a hypothesis when available evidence is heterogeneous. Usually however when conducting a meta-analysis one puts aggregated data in a model, possibly losing information.

Therefore I am considering gathering data from published research from the authors in order to be able to conduct analysis on 'raw data' rather then aggregated data (my field is neuroscience/psychology/psychiatry).

Questions

• Where can I learn more about conducting such analyses?
• Are researchers typically willing to share their data?
• Would ethical guidelines preclude such data sharing?

Answer 1

As @Alexander already mentioned, you are looking for an approach that is called "individual participant/person/patient data meta-analysis" (IPD meta-analysis). He also refered to an article by Richard Riley, who has published a lot in this field. Please find below a collection of articles that I used for our advanced meta-analysis class:

• Cooper, H., & Patall, E. A. (2009). The relative benefits of meta-analysis conducted with individual participant data versus aggregated data. Psychological methods, 14(2), 165–176. doi:10.1037/a0015565

• Curran, P. J., & Hussong, A. M. (2009). Integrative data analysis: the simultaneous analysis of multiple data sets. Psychological methods, 14(2), 81–100. doi:10.1037/a0015914

• Lyman, G. H., & Kuderer, N. M. (2005). The strengths and limitations of meta-analyses based on aggregate data. BMC Medical Research Methodology, 5(1), 14.

• (already mentioned) Riley, R. D., Lambert, P. C., & Abo-Zaid, G. (2010). Meta-analysis of individual participant data: rationale, conduct, and reporting. BMJ, 340(feb05 1), c221-c221. doi:10.1136/bmj.c221

• Riley, R. D., Lambert, P. C., Staessen, J. A., Wang, J., Gueyffier, F., Thijs, L., & Boutitie, F. (2007). Meta-analysis of continuous outcomes combining individual patient data and aggregate data. Statistics in Medicine. doi:10.1002/sim.3165

• Simmonds, M. C., Higgins, J. P., Stewart, L. A., Tierney, J. F., Clarke, M. J., & Thompson, S. G. (2005). Meta-analysis of individual patient data from randomized trials: a review of methods used in practice. Clinical Trials, 2(3), 209–217.

• Stewart, L. A., & Tierney, J. F. (2002). To IPD or not to IPD? Advantages and disadvantages of systematic reviews using individual patient data. Evaluation and The Health Professions, 25(1), 76-97.

Answer 2

Yes. It can be a problem especially in scenarios where pharmaceutical clinical trials are involved and due to competition companies may not want to share their data. Nevertheless such studies have been carried out in recent years in such settings. Combining raw data when the studies involve the same endpoints and the populations are similar is probably better than using summary data. But I do think there are situations where summary statistics or even just sample size information along with p-values can be used. This very much depends on the studies and the goals of the meta-analysis. In my experience the hardest part of meta analysis studies is deciding which studies should be included and which must be left out.