DataTerminology.comNEW
Regression technique modeling relationships by fitting an nth-degree polynomial to predictors.
DESCRIPTION
Polynomial regression augments linear models with higher-order terms to capture curvature. It remains linear in parameters and is fit via least squares. Proper degree selection and regularization mitigate overfitting. Centering and scaling improve numerical stability. It’s useful for trend modeling and simple nonlinear patterns. Spline or kernel methods may offer more flexible fits. Cross-validation helps choose polynomial degree.
ALTERNATIVE DEFINITIONS
Wikipedia
Polynomial regression is a form of regression analysis in which the relationship between the independent variable x and the dependent variable y is modeled as an nth degree polynomial.
Defines model form using nth-degree polynomial.
Penn State Statistics
Polynomial regression extends linear regression by adding polynomial terms to the model to account for curvature.
Positions polynomial regression as an extension of linear regression.
Minitab
Polynomial regression models curvature by including squared, cubed, and higher-order terms of the predictor.
Highlights modeling curvature using higher-order terms.
RELATED TERMS
Quadratic Term Cubic Term Model Overfitting Regularization Feature Engineering Design Matrix Cross-Validation Bias-Variance
COMPETING TERMS
Linear Model Spline Regression
RELATIONS
- Broader: Regression
KNOWLEDGE AREAS
TARGET AUDIENCE
Data Scientist AI Engineer Data Analyst
EXTERNAL SOURCES
- Wikipedia - Polynomial regression
- scikit-learn - Polynomial features generator
- Penn State Statistics - Course notes on polynomial regression
- Minitab - Guidance for polynomial models
TOP QUESTIONS
When should Polynomial Regression be used?
Use it when data shows curvature that a linear trend cannot capture, but complexity remains modest.
Category: Requirements
How to choose the polynomial degree in Polynomial Regression?
Use cross-validation, information criteria, or domain knowledge to balance fit and overfitting risk.
Category: Testing
What are common mistakes with Polynomial Regression?
Choosing an excessively high degree or skipping scaling, which leads to unstable estimates and overfitting.
Category: Mistakes
How is Polynomial Regression fit?
By linear regression on expanded polynomial features, typically via ordinary least squares.
Category: Definition
What is a hot topic around Polynomial Regression?
Comparisons with spline-based methods and regularized models for flexible yet robust fits.
Category: Topic
What’s the risk of using high-degree Polynomial Regression?
Runaway oscillations and poor generalization, especially near boundaries and with sparse data.
Category: Risk
What alternatives exist to Polynomial Regression?
Splines, kernel regression, and tree-based models often provide smoother or more adaptive fits.
Category: Alternatives
Why is Polynomial Regression still relevant?
It’s simple, interpretable, and effective for modest nonlinear trends with limited data.
Category: Relevancy
How to interpret coefficients in Polynomial Regression?
Coefficients indicate contributions of each power term; centering helps meaningful interpretation.
Category: Example