In statistical analysis, what is employed when data are ranked instead of presented in raw numerical form?

When data are ranked instead of being presented in raw numerical form, a rank-order correlation is employed. This type of correlation measures the strength and direction of the relationship between two variables based on their ranks. This method is particularly useful when the data do not meet the assumptions required for Pearson's correlation, such as being normally distributed or measured on an interval scale.

Rank-order correlation allows researchers to use ordinal data, which does not convey precise distances between points but does indicate a relative order. Common types of rank-order correlation include Spearman's rank correlation coefficient and Kendall's tau, both of which assess how well the relationship between two variables can be described by a monotonic function.

In contrast, descriptive statistics summarize and describe the characteristics of data but do not focus specifically on rank relationships. Regression analysis involves predicting the value of a dependent variable based on one or more independent variables, generally utilizing raw numerical data. Normalization refers to the process of adjusting values in a dataset to a common scale, which does not specifically involve ranking data.