What Are The Properties Necessary For OLS To Be The Best Lin

What are the properties necessary for OLS to be the Best Linear Unbiased Estimator? (List and describe)

The Ordinary Least Squares (OLS) estimator is a fundamental method in econometrics used for estimating the parameters of a linear regression model. For OLS to be considered the Best Linear Unbiased Estimator (BLUE), several key properties and assumptions must be satisfied. These properties underpin the validity and efficiency of the OLS estimates, ensuring they are both unbiased and have the smallest variance among all linear unbiased estimators.

Firstly, the assumption of linearity states that the relationship between the dependent and independent variables must be linear in parameters, meaning the model can be expressed as a linear combination of the predictors. Next is the assumption of random sampling, which ensures that the data are representative and that the sample observations are independent and identically distributed (iid). This is crucial for the statistical properties of the estimators to hold.

One of the most critical assumptions is the zero conditional mean assumption, which stipulates that the expected value of the error term, given any values of the independent variables, is zero (E[ε|X]=0). This ensures that the regressors are uncorrelated with the error term, a requirement for unbiasedness. Moreover, the assumption of homoscedasticity requires that the variance of the error term is constant across all levels of the independent variables. This assumption affects the efficiency of the estimates and the validity of standard errors for hypothesis testing.

Another important property is the absence of perfect multicollinearity, which requires that the independent variables are not perfectly linearly related. Perfect multicollinearity makes it impossible to uniquely estimate the coefficients. Additionally, the error terms should be uncorrelated across observations (no autocorrelation) and the errors should be normally distributed if hypothesis testing about coefficients is to be valid, particularly in small samples.

Under these assumptions, the Gauss-Markov theorem guarantees that the OLS estimator is the Best Linear Unbiased Estimator, meaning it provides the most precise (minimum variance) linear unbiased estimates of the coefficients among all such estimators. Failing to meet these assumptions, such as when errors are heteroscedastic or correlated, can lead to biased, inconsistent, or inefficient estimates, thereby invalidating statistical inference.

References

• Greene, W. H. (2018). Econometric Analysis (8th ed.). Pearson.
• Wooldridge, J. M. (2016). Introductory Econometrics: A Modern Approach (6th ed.). Cengage Learning.
• Hamilton, J. D. (1994). Time Series Analysis. Princeton University Press.
• Stock, J. H., & Watson, M. W. (2015). Introduction to Econometrics (3rd ed.). Pearson.
• Kennedy, P. (2008). A Guide to Econometrics (6th ed.). Wiley-Blackwell.
• Brooks, C. (2014). Introductory Econometrics for Finance. Cambridge University Press.
• Verbeek, M. (2017). A Guide to Modern Econometrics (5th ed.). Wiley.
• Angrist, J. D., & Pischke, J.-S. (2009). Mostly Harmless Econometrics. Princeton University Press.
• Newey, W. K., & West, K. D. (1987). A Simple, Positive Semi-definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix. Econometrica, 55(3), 703–708.
• Heckman, J. J. (1979). Sample Selection Bias as a Specification Error. Econometrica, 47(1), 153–161.