Heteroscedasticity in a regression model violates one of the classical assumptions that the error term has constant variance. If heteroscedasticity is ignored, the Ordinary Least Squares (OLS) estimator remains unbiased but becomes inefficient.
Step 1: Heteroscedasticity does not lead to bias in the OLS estimators, meaning that the estimators remain unbiased.
Step 2: However, the estimators are no longer efficient because heteroscedasticity leads to incorrect standard errors, making the estimates less reliable.
Step 3: Conclusion.
Thus, the OLS estimators are unbiased but inefficient in the presence of heteroscedasticity.
Final Answer: (C) It will be unbiased but inefficient