手法を比較

	Whiteの不均一分散検定	ヘテロスケダスティシティのブルシュ・パガン検定	最小二乗法 (OLS) 回帰
分野	計量経済学	計量経済学	計量経済学
系統	Regression model	Regression model	Regression model
提唱年	1980	1979	2019
提唱者	Halbert White	Trevor Breusch & Adrian Pagan	Wooldridge (textbook treatment); classical least squares
種類	General test for heteroskedasticity	Lagrange-multiplier test for heteroskedasticity	Linear regression
原典	White, H. (1980). A heteroskedasticity-consistent covariance matrix estimator and a direct test for heteroskedasticity. Econometrica, 48(4), 817–838.	Breusch, T. S., & Pagan, A. R. (1979). A simple test for heteroscedasticity and random coefficient variation. Econometrica, 47(5), 1287–1294.	Wooldridge, J. M. (2019). Introductory Econometrics: A Modern Approach (7th ed.). Cengage Learning. ISBN: 978-1337558860
別名	White's general heteroskedasticity test, White değişen varyans testi	BP test, Breusch-Pagan-Godfrey test, Lagrange multiplier test for heteroskedasticity, Breusch-Pagan değişen varyans testi	ordinary least squares, classical linear regression, linear regression, en küçük kareler regresyonu
関連	3	3	5
概要	The White test, introduced by Halbert White in 1980, is a general test for heteroskedasticity that makes no assumption about its functional form. It regresses the squared OLS residuals on the regressors, their squares, and their cross-products, so it can detect heteroskedasticity related to any of these terms. The same 1980 paper introduced the heteroskedasticity-consistent ('White') standard errors that are the standard remedy when the test rejects.	The Breusch-Pagan test, introduced by Trevor Breusch and Adrian Pagan in 1979, is a Lagrange-multiplier test for heteroskedasticity — the condition where the variance of a regression's errors changes with the explanatory variables. It works by regressing the squared OLS residuals on candidate variables and checking whether they explain any of the residual variation, signalling that the constant-variance assumption is violated.	Ordinary Least Squares is the classical linear regression method that explains a continuous outcome as a linear combination of predictors. It estimates the coefficients by minimising the sum of squared residuals, and under the Gauss-Markov assumptions these estimates are the best linear unbiased estimator (BLUE).