Scribd
Upload
36 views

Regression Formulas Quick Notes Simplified

Uploaded by

pooja2602patil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
36 views

Regression Formulas Quick Notes Simplified

Uploaded by

pooja2602patil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Topic Formula Description

Simple Linear Regression Model Yi = 0 + 1 Xi + ui The regression equation


Estimated Regression Equation i = 0 + 1 Xi Fitted values for the dependent variable
Slope Estimate ( 1) 1 = (Xi - X)(Yi - ) / (Xi - X)² Estimate of the slope of the regression line
Intercept Estimate ( 0) 0= - 1X Estimate of the intercept of the regression line
Residual (Error) ui = Yi - i Difference between actual and predicted values
Total Sum of Squares (SST) SST = (Yi - )² Total variability in the dependent variable
Explained Sum of Squares (SSR) SSR = ( i - )² Variability explained by the regression
Residual Sum of Squares (SSE) SSE = (Yi - i)² Unexplained variability
Relationship (SST, SSR, SSE) SST = SSR + SSE Breakdown of total variation
Coefficient of Determination (R²) R² = SSR/SST = 1 - SSE/SST Proportion of variance explained by the regressio
Error Variance (Residual Variance) s² = SSE / (n - 2)Variance of residuals (used for hypothesis testing and confide
Standard Error of 1 SE( 1) = s / (Xi - X)² Measures the precision of the estimated slope
Standard Error of 0 SE( 0) = s [1/n + X² / (Xi - X)²] Measures the precision of the estimated intercep
t-statistic for 1 t = 1 / SE( 1) Used for hypothesis testing on 1
Confidence Interval for 1 1 ± t( /2, n-2) × SE( 1) Range within which the true 1 lies
Gauss-Markov Theorem OLS estimators are BLUE Best Linear Unbiased Estimators under classical assum
F-statistic for Overall Fit F = [R² / k] / [(1 - R²) / (n - k - 1)] Tests overall significance of the regression
SST, SSR, SSE Relationship SST = SSR + SSE Relationship between total, explained, and residual va
Properties of OLS Estimators E( 0) = 0 and E( 1) = 1 OLS estimators are unbiased
Error Term Assumptions E(ui) = 0, Var(ui) = ², No Autocorrelation Classical linear regression assumptions

You might also like