Statistical thinking for public health: Glossary

The mean is the average value. The population has a population mean, while we estimate a sample mean from our sample.

The sample variance is the average of the squared differences between values in our sample and the mean of our sample.

The standard deviation is the square root of the variance. It measures the spread of observations around the mean, in units of the original data.

Sample means are expected to differ from the population mean. We quantify the spread of estimated means around the population mean using the standard error.

95% of 95% confidence intervals are expected to capture the population mean. In practice, this means we are fairly confident that a 95% confidence interval will contain the population mean, but we do not know for sure.

Scatterplots allow us to visually check the linear association between two variables.

Pearson’s correlation coefficient allows us to quantify the size of a linear association.

We can predict the means, and calculate confidence intervals, of a continuous outcome variable grouped by a continuous explanatory variable. On a small scale, this is an example of a model.