Suppose we have estimated , where is earnings, is experience, and for females, for males. If we had coded the dummy as for females and for males, the new estimated coefficients (in the same order) would have been
Tap an option to check your answer.
4 marks, −1EconometricsDummy variables and functional formsDummy variables and the dummy variable trapModerateabout 2 min
DSE 2018 Question 27: Dummy variables and functional forms
Answer and worked solution
Checking your account…
Plain-text version
Suppose we have estimated y = 10 + 1.5x + 4D, where y is earnings, x is experience, and D = 0 for females, 1 for males. If we had coded the dummy as -1 for females and 1 for males, the new estimated coefficients (in the same order) would have been (A) 12, 1.5, -2 (B) 12, 1.5, 2 (C) 14, 1.5, -4 (D) 10, 1.5, 4
Dummy variables and functional forms has come up 20 times in 6 exams since 2011.
What this question tests
This question is on Dummy variables and the dummy variable trap, part of Dummy variables and functional forms in Econometrics.
Using 0-1 variables for categories, how to read their coefficients, and the trap of too many.
TestStop has 10 past-paper questions on this subtopic.
Similar questions from other papers
- The estimated energy demand is given in the Equation below, where, ŷₜ is the estimated value of the log of energy demand at time t. The numbers in the parentheses are…
- Let Yₜ be the value of Y in year t. The natural logarithmic value of Yₜ is regressed on t. A simple linear regression yields the statistically significant estimates of…
- The following table provides different statistical model specifications along with the elasticity of yₜ with respect to xₜ. Which one of the following options is…
- If a variable has 'm' categories, we can run the regression using:
- ANCOVA models include regressors that are:
Question from the DSE 2018 paper. Solutions are TestStop's own. Not affiliated with or endorsed by any examination authority.