Suppose that the true data-generating process includes an intercept along with the variables X2 and X3. Suppose that you inadvertently leave X3 out of your estimated model and only include an intercept and X2. Suppose further that X2 and X3 is positively correlated with Y, and X2 and X3 are negatively correlated with each other. As a result, the estimated coefficient on X2 (when X3 is omitted) is generally going to be: unbiased. too big. too small, O leptokurtic.

Suppose that the true data-generating process includes an intercept along with the variables X2 and X3. Suppose that you inadvertently leave X3 out of your estimated model and only include an intercept and X2. Suppose further that X2 and X3 is positively correlated with Y, and X2 and X3 are negatively correlated with each other. As a result, the estimated coefficient on X2 (when X3 is omitted) is generally going to be: unbiased. too big. too small, O leptokurtic.

Managerial Economics: Applications, Strategies and Tactics (MindTap Course List)

14th Edition

ISBN:9781305506381

Author:James R. McGuigan, R. Charles Moyer, Frederick H.deB. Harris

Publisher:James R. McGuigan, R. Charles Moyer, Frederick H.deB. Harris

Chapter4: Estimating Demand

Section: Chapter Questions

Problem 4E

See similar textbooks

Similar questions

In general, what is true about the relationship between the Sum of Squared Residuals in the restricted and unrestricted model? a. SSRr = R-squared * SSRur b. SSRr < SSRur c. SSRr > SSRur d. SSRr = SSRur
tate whether the following statements are true or false with a brief explanation: a) Logit model is estimated by minimising the sum of the squares residuals of the model. b) In difference-in-differences analysis, the assumption of ‘parallel trends’ is generally testable. c) Suppose you have estimated a model Y = 0.2 – 0.7D + 2X + 0.4X*D. Y and X are continuous variables and D is a dummy variable. If D=1, the marginal effect of X on Y is always larger, and therefore the predicted Y is always larger, than in the case where D=0. d) The first order autoregressive model can be stationary or non-stationary. e) The bias in Instrumental Variables estimator depends on the number of observations.
Consider the following multiple regression Price=118.9+0.594BDR+23.5Bath+0.195Hsize+0.004Lsize+0.095Age−48.5Poor, R2=0.75, SER=41.5 (22.7) (2.56) (8.56) (0.017) (0.00049) (0.315) (10.7) The numbers in parentheses below each estimated coefficient are the estimated standard errors. A detailed description of the variables used in the data set is available here . Suppose you wanted to test the hypothesis that BDR equals zero. That is, H0: BDR=0 vs H1: BDR≠0 Report the t-statistic for this test. The t-statistic is ________ (Round your response to three decimal places)
TRUE OR FALSE. A model with heterosdasticity problem most likely has insignificant parameter estimates.
Consider the regression model Yi = β0 + β1X1i + β2X2i + β3(X1i * X2i) +ui. a. ΔY>/ΔX1 = β1 + β3X2 (effect of change in X1, holding X2 constant).b. ΔY/ΔX2 = β2 + β3X1 (effect of change in X2, holding X1 constant).c. If X1 changes by ΔX1 and X2 changes by ΔX2, then ΔY =(β1+β3X2)ΔX1 + (β2 + β3X1)ΔX2 + β3ΔX1ΔX2.
The following ACF plots were produced for raw data of monthly sales of two different variables, A and B. a) Explain which variable is likely to be easier to forecast. b) Explain how your answer to part a) would change if these were residuals of an ARIMA model instead of “raw data of monthly sales”.
Suppose that an economist has been able to gather data on the relationship between demand and price for a particular product. After analyzing scatterplots and using economic theory, the economist decides to estimate an equation of the form Q= aPb, where Q is quantity demanded and P is price. An appropriate regression analysis is then performed, and the estimated parameters turn out to be a = 1000 and b = - 1.3. Now consider two scenarios: (1) the price increases from $10 to $12.50; (2) the price increases from $20 to $25. a. Do you predict the percentage decrease in demand to be the same in scenario 1 as in scenario 2? Why or why not? b. What is the predicted percentage decrease in demand in scenario 1? What about scenario 2? Be as exact as possible.
If the t ratio for the slope of a simple linear regression equation is equal to 1.614 and the critical values of the t distribution at the 1% and 5% levels of significance, respectively, are 3.499 and 2.365, then the slope is not significantly different from zero. significantly different from zero at both the 1% and the 5% levels. significantly different from zero at the 1% level but not at the 5% level. significantly different from zero at the 5% level but not at the 1% level. please show how you come up with the answer , do not just guess !!!
Please no written by hand The assumption of normally distributed errors means that... A. errors can be ignored when doing regression modelling. B. the OLS estimators can also be assumed to be normally distributed since they are a linear functions of the errors. C. the OLS estimators can also be assumed to be normally distributed since they are BLUE. D. the OLS estimators can also be assumed to be normally distributed since they are minimum variance. E. the regression model will not be subject to specification error.
According to Environmental Kuznets curve, it is expected that there is an Inverse-U shape relationship between pollution and real income such that the following quadratic functional form (regression model) must be specified: Y = a1 + a2 X + a3 X² + u where the variables Y and X represent respectively air pollution (CO2) and real income (RGDP). u is the random error. a) Suppose a researcher wants to investigate the relationship between pollution and real income by defining a linear functional form such as Y = B1+ B2 X+e. Show technically how you test whether quadratic form or linear form is the correct model specification using Ramsey's Reset test. b) Suppose R² is found 0.75 from quadratic form, 0.55 from linear form and 0.73 from the auxiliary regression. Given n=35, carry out Reset test and interpret the result. c) Suppose you found out that the correct specification is the quadratic regression. In this case, would estimating the linear functional form result in an unbiased estimate…
A realtor was investigating the price of real estate based on the size of the house in square feet x1 and if the house was within walking distance of an "A" rated public school. The indicator variable is defined as x = 1 if the house is within walking distance of an "A" rated public school and x = 0 if the house is NOT within walking distance of an "A" rated public school. If there was interaction in the regression problem, an appropriately fit regression model would have…? a) A different slope and different y-intercept for those within walking distance and those not. b) A different y-intercept for those that were within walking distance and those that were not; the slope would not change. c) A different slope, but not a different y-intercept for those within walking distance and those not. d) Cannot be determined
In a regression problem with 1 output variable and with a total number of 100 possible input variables, what is the number of all possible models with three input variables?