Fourth, we have to match our ambitions in research questions with the effective sample size that is available. When the sample size is very small, we should only ask relatively simple questions, while more complex questions can be addressed with larger sample sizes. A question such as: “What are the most important predic- tors in this prediction problem” is actually more complex than a question such as “What are the predictions of the outcome given this set of predictors” (Chap. 11). Table 1.1 lists questions on predictors (known or determined from the data?), func- tional form (known or determined from the data?), and regression coefficients (known or determined from the data?) and the consequence for the required sample size in a study
If you want to change selection, open document below and click on "Move attachment"
- (no access) - BOOK_steyerberg_Clinical prediction models.pdf, p31
|status||not read|| ||reprioritisations|
|last reprioritisation on|| ||suggested re-reading day|
|started reading on|| ||finished reading on|