Contents
What should be the sample size of a binary model?
When developing prediction models for binary or time-to-event outcomes, a well known rule of thumb for the required sample size is to ensure at least 10 events for each predictor parameter
When is the sample size is too small?
Overfitting notably occurs when the sample size is too small. In particular, when the number of candidate predictor parameters is large relative to the number of participants in total (for continuous outcomes) or to the number of participants with the outcome event (for binary or time-to-event outcomes).
How is the effective sample size for a continuous outcome determined?
In a development dataset, the effective sample size for a continuous outcome is determined by the total number of study participants.
Why do you need a sample size for prediction?
Fundamentally, the sample size must allow the prediction model’s intercept to be precisely estimated, to ensure that the developed model can accurately predict the mean outcome value (for continuous outcomes) or overall outcome proportion (for binary or time-to-event outcomes).
Which is a standard tool to determine the relationship between variables?
A standard tool for determining whether variables are related to an individual’s probability that Y i = 1 is the logistic regression model: That is, we fit a regression model to the log-odds that Y i = 1, conditional on the predictors.
What should the sample size be for a prediction model?
The sample size of the development dataset must be large enough to develop a prediction model equation that is reliable when applied to new individuals in the target population.
How many participants are needed to achieve the same margin of error?
To achieve the same margin of error with outcome proportions of 0.1 and 0.2, at least 139 and 246 participants, respectively, are required. Calculation of sample size required for precise estimation of the overall outcome probability in the target population