Hypothesis and statistical foundation


You’ve asked yourself: Is this idea innovative? Does it fit within the department or division’s research focus? Is it relevant to potential sponsors? Do I have an exploratory/descriptive or a confirmatory research question? Does the scientific importance outweigh the risks to human subjects? Is it publishable? And so on.

Research projects should be designed to answer a specific question, usually by testing a well-formed hypothesis, determining whether or not there exists a cause-and-effect relationship between observed phenomena.

Research questions are the link between the problem at which the project is aimed, the study design, the results, and the conclusions. Because research questions are the backbone of research projects, considerable care needs to be taken in choosing and developing research questions.

A particularly common type of theory in health sciences is that within a given population with a particular health problem (P), a particular intervention (I) relative to a comparison condition (C) increases the chance of beneficial outcomes (O) in particular settings (S). Each of the components of such theories may be a parameter that can be tested as a research hypothesis, the results of which can be summarized and evaluated before accepting or revising such theory (see www.prisma-statement.org for the way in which clearly defining PICOS facilitates cumulative research). 


  • Reduce the research question to one or more individual hypotheses, each of which may be tested.
  • State the hypothesis(es) clearly for potential sponsors of the research.

If you have any questions about formulating an effective research question, the various options in research design, defining the population group, or selecting suitable outcome metrics, you can ask for a consultation appoint with the Department of Epidemiology and Data Science (EDS) location AMC and location VUmc.

Sample size

Make a detailed estimate of the number of subjects that you think you will be able to find for your study:

  • How common is this clinical picture?
  • How many patients are seen each year for each hospital with such symptoms?
  • How many would meet your inclusion and exclusion criteria?
  • How many suitable subjects would consent to an invitation to participate in your study?
  • Are there competing studies underway?
  • How many subjects would you expect to drop out during the study?

Sample size calculations are usually performed to determine the number of participants needed to detect a clinically relevant treatment effect. Pre-study calculation of the required sample size is warranted in the majority of quantitative studies. Also in objective research sample size calculations or power calculations can be of use, to determine how many cases or controls you need or how large the groups must be to detect meaningful differences.

Calculating the sample size in the design stage of the study is increasingly becoming a requirement for grant applications and when seeking ethical committee approval for a research project.

Most importantly is to contact our biostatisticians for assistance.

Would you like greater insight into the number of patients that meet your inclusion and exclusion criteria? You can request this information from the Research Data Platform (RDP) of the Department of Business Intelligence.

Statistical Analysis Plan

A Statistical Analysis Plan (SAP) is a document that defines in detail the necessary techniques and methodologies involving statistical analyses in both fundamental research and clinical trials. The SAP includes, among other things, a detailed overview of the statistical techniques that will be used to analyse outcomes (and vice versa an intervention effect); explanations of the randomisation techniques used, if applicable; further delineation of the research population(s), who form the target group(s) for the (primary) analyses; a description of how missing values will be dealt with or what steps will be taken if the data collection deviates from the protocol; and a discussion of any subgroup analyses.

You are advised to write an SAP as early in the process as possible and in any case well before data collection is completed. The SAP will make it clear that the investigators drew up their research plan without prior knowledge of the data. For a blind randomised trial, investigators must finalise the SAP before the blinding is revealed.

Along with the research protocol, the SAP places a clinical study on an important scientific foundation. In combination with the data management plan, the SAP also safeguards data integrity.

 Statisticians from the Department of Epidemiology and Data Science (EDS) have developed a template for drawing up an SAP. If you would like support in writing an SAP, please contact the Statistics Helpdesk location AMC and location VUmc.

There is also a module about the Statistical Analysis Plan included in the e-learning course Research Data Management, which can be accessed via the Learning Portal  (via Course Offerings > search: RDM