Great challenges with few subjects: Statistical strategies for neuroscientists

▶ Neuroscience is one of the most heavily experimental fields of biological and medical research but data are often derived from repeated measurements and stimulus type presentations with a limited number of subjects. ▶ To make better use of already collected data and to guide future experimental design and analysis, we provide an introduction to a group of diverse and powerful statistical approaches which have proven to be useful in other fields of biological research. ▶ These approaches are termed the 5 Ms; M1: meta-analysis M2: mixed-effects modeling, M3: multiple imputation, M4: model averaging, and M5: Markov chain Monte Carlo (MCMC). ▶ Taken together, these approaches represent a robust statistical toolbox whose elements shall alleviate analytical constraints generated by limits on sample sizes, repeated subject use, and incomplete replicates of experimental manipulation.