This post is also available in: Deutsch

The statistical evaluation of the collected data is still missing to complete the master’s thesis or the research article. Should you use the t-test or the Mann-Whitney U test? Or work your way through a statistics book? Here we present a small selection of useful sources.

For Beginners

“How to lie with statistics” (reprint, the original was written in 1954) is the most widely read statistics book. It deals with errors that can occur during data collection and explains how not to present data. It is therefore still very topical. It is also written in an extremely entertaining way, but it is not very helpful when writing a paper.

Huff, D. (1992). How to lie with statistics (reprinted in Penguin Books). Penguin Books.

“Medizinische Statistik für Dummies” explains the basic concepts, the most important study types, descriptive statistics and the most important tests and clears up a few misconceptions.

Rauch, G., Burkholder, I., Neumann, K., Grittner, U., Herrmann, C., & Kruppa, J. (2019). Medizinische Statistik für Dummies (1. Auflage). Wiley-VCH Verlag GmbH & Co. KGaA.

“Discovering statistics using IBM SPSS statistics” is a must for anyone who is looking for help in choosing the right tests and at the same time wants to learn how to use the IBM SPSS statistics software. Not only the examples are very helpful, but also the explanations on how to present and describe the results correctly.

Field, A. (2019). Discovering statistics using IBM SPSS statistics (5th edition). SAGE.

“Basics & Clinical Biostatistics” explains the basics of statistics in relation to clinical studies, as well as study types or the presentation of data in tables and graphs.

White, S. (2020). Basic & Clinical Biostatistics (5th ed.). McGraw-Hill Education LLC.

The Methodenberatung of UZH offers a decision tree to guide one to the right statistical test.

For advanced users

The British Medical Journal’s “Statistics notes” series provides entertaining discussions on statistical topics using examples from published research articles.

A frequently asked question is how to correctly and completely describe and present statistical analyses in scientific articles. This is where the “SAMPL Guidelines” provide answers.

Lang T, Altman D. Basic statistical reporting for articles published in clinical medical journals: the SAMPL Guidelines. In: Smart P, Maisonneuve H, Polderman A (eds). Science Editors’ Handbook, European Association of Science Editors, 2013.

The “JAMA Guide to Statistics and Methods” uses articles from JAMA to explain various advanced statistical methods, such as logistic regression, multiple imputation, mediation analysis or cost-effectiveness analysis. Each chapter discusses why and how each method is used, its limitations and how to interpret the results.

Lewis, R., & Livingston, E. (2020). JAMA guide to statistics and methods. McGraw-Hill.