News / Blog: Glossary / Lexicon

What is multicollinearity?

Multicollinearity is a statistical phenomenon in which there is variable correlation between multiple variables in a model. It occurs when two or more variables are highly correlated with each other, which can lead to bias in estimates. Multicollinearity can affect the precision of estimates and make it more difficult to determine the individual effects of a variable on the model outcome.

What is resampling?

Resampling is a method for studying the stability of statistics and estimates based on an existing data set. It is used to validate the behavior of estimates by recombining known data to produce new data. This allows the robustness and variance of certain estimates to be determined.

What is a parameter?

A parameter is a value or argument passed to a function, algorithm, or programming language to achieve a specific behavior or result. Parameters help increase the flexibility of the function, algorithm, or programming language by allowing the same program to be executed with different input values to achieve different results.

What is a random variable?

A random variable is a variable whose value is random for an outcome from an experiment or other process. Random variables can take on discrete, continuous, or combined values. Examples of random variables are the number of copies of a certain book that a publisher sells, the number of students who receive a certain course grade, or the number of goals that a certain soccer team scores during a season.

What is a correlation?

A correlation is a mathematical relationship between two variables that reflects the changes between the variables. A correlation can be positive or negative. A positive correlation means that when one variable increases, the other variable also increases and vice versa. A negative correlation means that when one variable increases, the other variable decreases and vice versa.