Suppose we have estimated the regression model,
Let be the fitted value of for each . Now, we estimate the artificial model,
to test against : is wrong. Choose the correct statement.
Tap an option to check your answer.
Suppose we have estimated the regression model,
Let be the fitted value of for each . Now, we estimate the artificial model,
to test against : is wrong. Choose the correct statement.
Tap an option to check your answer.
Checking your account…
Suppose we have estimated the regression model, yᵢ = β₁ + β₂ xᵢ₂ + ⋯ + β_K x_(iK) + eᵢ Let ŷᵢ be the fitted value of yᵢ for each i. Now, we estimate the artificial model, yᵢ = β₁ + β₂ xᵢ₂ + ⋯ + β_K x_(iK) + γ₁ ŷᵢ² + γ₂ ŷᵢ³ + vᵢ to test H₀: γ₁ = γ₂ = 0 against H₁: H₀ is wrong. Choose the correct statement. (A) H₁ can be equivalently rewritten as H₁: γ₁ ≠ 0 and γ₂ ≠ 0. (B) An F-test cannot be appropriate for testing H₀. (C) This test is called the Gauss Markov Theorem. (D) Rejection of H₀ suggests that there can be omitted variables.
Also written as: Suppose we have estimated the regression model, y_i = beta_1 + beta_2 x_(i2) +... + beta_K x_(iK) + e_i Let y_hat_i be the fitted value of y_i for each i. Now, we estimate the artificial model, y_i = beta_1 + beta_2 x_(i2) +... + beta_K x_(iK) + gamma_1 y_hat_i^2 + gamma_2 y_hat_i^3 + v_i to test H_0: gamma_1 = gamma_2 = 0 against H_1: H_0 is wrong. Choose the correct statement.
Misspecification and measurement error has come up 11 times in 4 exams since 2011.
This question is on Irrelevant variables and functional-form misspecification, part of Misspecification and measurement error in Econometrics.
The cost of including a variable that does not belong, and of using the wrong functional form.
TestStop has 7 past-paper questions on this subtopic.
Question from the UoH 2020 paper. Solutions are TestStop's own. Not affiliated with or endorsed by any examination authority.