Statistics Cheat Sheet

There are two types of statistics: descriptive and inferential. When using inferential statistics a sample is taken from the population. This is a smaller group that approximates the entire population. Care must be taken to avoid sample bias, where there is an unequal chance of groups within the population from being selected.
 * Descriptive statistics summarises and describes data
 * Inferential statistics takes a sample and extrapolates to draw conclusions about a population

Random Sampling: every member of a population has an equal chance of selection, which is done so by randomly selecting individuals from the population with no exclusions. The larger the sample the smaller the uncertainty.

Random Assignment: assigning a sample to cohorts randomly (as opposed to, say, taking the first 20 for group A, the second 20 for group B, etc.). This can be more important in research than achieving a random sample - for example when performing medical testing for a hypothetical population.

Stratified Sampling: the population is divided into strata, each of which must be represented in the sample in the same proportion as they are in the population. This is more likely to be representative of the population than random sampling.

Variance is the average squared distance from the mean. The denominator has one deducted from it in the case of a sample mean.

Standard deviation is the square root of the variance.

When performing a study there are two types of variable: independent and dependant. Variables may be qualitative or quantitative, continuous or discrete.
 * Independent variables are those manipulated by a researcher
 * Dependent variables are those monitored by the researcher to indicate the effect of the independent variable.