Basic↦Statistic Methodology↦Data Collection↦Predictor Variable
What is it? Why is it important?
In studies:
- An outcome (or dependent variable), is a variable that researchers want to investigate (i.e. understand, explain, or predict)
- A predictor (or independent variable), is a variable that potentially has an effect on the outcome variable
When addressing a research question, researchers study the association between an outcome of interest and one (or several) predictor(s).
For example
A researcher interested in understanding the variation in exam results, may build a statistical model to examine the relationship between exam results (the outcome), and the time used to prepare for the exam, including the socio-economic status of participants (predictors)
What do I need to do?
As a SP-INV, think about the different predictors that may affect your study outcome. Which predictor(s) would you consider relevant to be included in your analysis?
When selecting predictor(s) of interest consider:
- The scientific rational: Clinical knowledge and previously published work may help you to define the most relevant predictor(s)
- Practical aspects and feasibility: Both outcome and predictor(s) are variables that are somehow measured. Assess available resources needed to collect the required data (e.g. material, time, money).
The number of potential predictors may be infinite. However, the number of predictors that can be included in a statistical analysis is limited.
The number of predictors to be included in the analysis depends on the number of observed outcomes (see examples under more)
More
Example of variable type and its effect on the number of observed outcomes:
- Continuous outcome (e.g. blood pressure): The number of outcomes depend on the number of study participants and assessments per participant (e.g. blood pressure can be measured several times at 3, 6 and 12 months)
- Binary outcome (e.g. death): The number of outcomes depend on the number of participants and the frequency of the outcome (e.g. death is expected in 10% of participants)
Increasing the number of observed outcomes is often challenging, and it is therefore important to focus on predictors of interest that are relevant to your research question.
Where can I get help?
Your local CTU↧ can support you with experienced staff regarding this topic
Basel, Departement Klinische Forschung, CTU, dkf.unibas.ch
Lugano, Clinical Trials Unit, CTU-EOC, www.ctueoc.ch
Bern, Clinical Trials Unit, CTU, www.ctu.unibe.ch
Geneva, Clinical Research Center, CRC, crc.hug.ch
Lausanne, Clinical Research Center, CRC, www.chuv.ch
St. Gallen, Clinical Trials Unit, CTU, www.kssg.ch
Zürich, Clinical Trials Center, CTC, www.usz.ch
References
ICH Topic E9 – see in particular
- 2.2.6 Surrogate Variables