Statistics for radiology

Case contributed by Dr Matt A. Morgan

Statistics for radiology

Normal distribution with standard deviations. 

Type I error. The means of sets of sample data from a population are normally distributed. If the mean of an experimental data set falls outside a certain preset point (usually 0.05), we decide that it is not likely to be within a normal variation of sample means. We reject the null hypothesis.

Alpha and beta error. Alpha error is the area in the tail of the sample mean distributions, bounded by the critical value. Beta error is in the tail of the experimental data set means, bounded by the critical value. This is the likelihood that we would accidentally say there was no difference between the two populations when there actually was.

Creating a confidence interval, part 1: establishing the lower bound.

Creating a confidence interval, part 2: adding the upper bound.

The chi-squared test, used to test association between categorical variables.

Kappa: a nonparametric test for assessing interobserver variability.

Case Discussion

Non-case. Diagrams to illustrate radiology statistics.

How to use cases

You can use Radiopaedia cases in a variety of ways to help you learn and teach.

Creating your own cases is easy.

Updating… Please wait.

 Unable to process the form. Check for errors and try again.

 Thank you for updating your details.