Apps

🧪 This platform is in early beta. Features may change and you might encounter bugs. We appreciate your patience!

Multicollinearity

Also Known As: Collinearity Ill-conditioned design matrix
Statistical Error ID: multicollinearity

Definition

Multicollinearity occurs when two or more independent variables in a regression model are highly correlated, making it difficult to isolate the individual effect of each variable. While the overall model fit may remain good, standard errors become inflated, coefficient estimates become unstable, and statistical significance tests become unreliable. Perfect multicollinearity makes estimation impossible entirely.

Examples

A model predicting house prices includes both square footage and number of rooms as independent variables. Since larger homes typically have more rooms, the two variables are highly correlated, and the model cannot reliably separate their individual contributions to price.

A nutrition study modeling cholesterol levels includes both daily saturated fat intake and daily red meat consumption as predictors. Since people who eat more red meat also consume more saturated fat, the two variables are tightly correlated, and the model cannot reliably determine which one independently drives cholesterol levels.

An economic model predicting consumer spending includes both household income and household wealth as separate independent variables. Because wealthier households also tend to have higher incomes, the two variables move together so closely that neither coefficient is statistically significant, even though spending clearly depends on financial resources.

Verification Steps
Verification Steps
Binary yes/no questions that an AI must answer to detect a reasoning pattern in a text.
Each of the 452 aspects has verification steps — simple yes/no questions designed to systematically detect whether a pattern appears in a text. For ad hominem: "Does the argument attack a person rather than their claim?" For false dichotomy: "Are only two options presented when more exist?" This ensures consistent, reproducible analysis.

Binary (yes/no) questions an LLM must answer to identify this aspect:

  1. 1

    Are two or more independent variables in the model highly correlated with each other?

    Type: binary
  2. 2

    Are the standard errors of the coefficients unusually large relative to the coefficient estimates?

    Type: binary
  3. 3

    Do coefficient estimates change dramatically when a variable is added or removed?

    Type: binary
  4. 4

    Is the analysis drawing conclusions about individual variable effects despite collinearity?

    Type: binary
Deep Dive
The expandable detail section on each aspect page with examples, psychology, and counter-strategies.
The Deep Dive section provides in-depth information about each aspect: a real-world example showing the pattern in action, an explanation of why it works psychologically, practical advice on how to counter it, alternative names, and links to related aspects.

Hierarchical Context