where cov(Z, v) Suppose we have the following causal model Y = 3 +5Z+v, 0. However, a precise measure of Z is not available. Instead, we have a noisy measure X of Z, that is, X = Z + w with var(w) > 0. Suppose the error w is a classical measurement error so that cov(w, Z) = cov(w, v) = 0. What can you conclude about the limit of the OLS estimator, namely B = cov(X, Y)/var(X)? 3₁₁ = 0 B < 5 3* = 5 B < 0 OB₂ > 5 B > 0 O =

where cov(Z, v) Suppose we have the following causal model Y = 3 +5Z+v, 0. However, a precise measure of Z is not available. Instead, we have a noisy measure X of Z, that is, X = Z + w with var(w) > 0. Suppose the error w is a classical measurement error so that cov(w, Z) = cov(w, v) = 0. What can you conclude about the limit of the OLS estimator, namely B = cov(X, Y)/var(X)? 3₁₁ = 0 B < 5 3* = 5 B < 0 OB₂ > 5 B > 0 O =

ENGR.ECONOMIC ANALYSIS

14th Edition

ISBN:9780190931919

Author:NEWNAN

Publisher:NEWNAN

Chapter1: Making Economics Decisions

Section: Chapter Questions

Problem 1QTC

See similar textbooks

Similar questions

A regression analysis of company profits and the amount of money the company spent on advertising produced a R² = 0.72. Which of these is TRUE? 1. This model can correctly predict the profit for 72% of companies. II. 72% of the variance in company profit can be accounted for by the model. III. On average, companies spend about 72% of their profits on advertising. OA. None OB. I and III OC. II only OD. III only OE. I only
6
Suppose you want to estimate the following model y = Bo + Biz + B₂z + 1₂ where z is likely to be correlated with both z and y. You have cross-sectional data on z. y. and z. You do not observe z but only an imperfect measurement that we call g. g = az+w, where w is just random noise. Your friend, Federico, argues that if you want to estimate 3₁ you should not include g in your estimation as it will just add noise. Is Federico's argument right or wrong? Explain.
Consider the following unobserved effects model: Yit =B₁ it1 + ... +ßkxitk + ai + Uit You plan on using fixed effects to estimate the model. Suppose you have a panel data set consisting of 10 individuals over 6 years. However, you are missing the last 3 years of data for the third, ż = 3, individual in your data set. Your panel data set has total observations. Suppose the reason individual i is missing data for certain time periods (called attrition) is correlated with the idiosyncratic error, uit. Recall that a; is assumed to be uncorrelated with the idiosyncratic error, Uit. This correlation cause the fixed effects estimators to be biased.
If in the study results obtained a demand and supply model for ties and suits: Demand for tie: Qdt = 410 – 5Pt – 2Ps Supply of tie: Qst = – 60 + 3Pt Demand for suit: Qds= 295 – Pt – 3Ps Supply of suit: Qss=–120 + 2Ps Based on the estimation results, then: a. Determine the general equilibrium price of a tie and suit b. What is the type of relationship between a tie and a suit? Explain your argument
A5
Let wage denote hourly wages, educ denote years of education, and define the dummy variable: if educ > 12 D = if educ < 12 i.e. we can think of D as a dummy variable indicating graduation from high school. Suppose we want to test the null hypothesis that the marginal return to education for every year after high school is the same as the marginal return to education for each year before high school (against the alternative that they are different). Which model and test would accomplish this goal? O a. Estimate wage = B1 + B2 educ + ß3 D + e and test Ho : ß3 = B2 against H1 : ß3 # B2. O b. Estimate wage = ß1 + B2educ + ß3 D + e and test Ho : ß3 = 0 against H1 : ß3 # 0. Estimate wage = B1 + B2educ + B3(educ + D) + e and test Ho : ß3 = 62 against H1 : B3 # B2. O d. Estimate wage = B1 + B2educ + B3(D × (educ – 11)) + e and test Ho : ß3 = B2 against H : B3 # B2. c. O e. Estimate wage = Bi + B2educ + ß3(D × (educ – 11)) + e and test Ho : ß3 = 0 against H1 : ß3 + 0.
Explain whether the empirical evidence supports the claim that “investors are solely concerned with mean and variance”
The following model studies human welfare using the General Social Survey in the US: happy = 0.014 + 0.209regattend + 0.103occattend + 0.027income + 0.009educ +0.003 female where happy is a dummy variable equal to one if a person is happy, and 0 otherwise: regattend is a dummy variable equal to one if a person regularly attends church, and 0 otherwise: occattend is a dummy variable equal to one if a person occasionally attends church, and 0 otherwise; income is family income in tens of thousands: educ is years of schooling: female = 1 if female. = 0 otherwise Interpret the impact of religion on happiness.
.A researcher is collecting individual data by asking visitors in a train station in a medium sized town to fill in a questionnaire. It takes nearly 30 minutes to complete the survey questions. To encourage higher participation rate, the researcher provides a small financial incentive that is enough to buy a sandwich. The researcher wants to use this sample to make predictions about effect of using social media on health among the residents of the town. a. Explain the random sampling assumption, that is one of the Gauss-Markov assumptions for linear regressions. b. Do you think this assumption is satisfied in the sample collected by the researcher? c. What are the possible consequences of violation of random sampling assumption for predictions based on this sample?
Taubman et al., (2014) used data collected in the Portland, OR metro area to study the Impact Medicaid on emergency department (ED) use. The figure below shows the percent of respondents who have been to the ED at all (left hand side of the figure) and the average number of ED visits (right hand side of the figure). The dark blue bars represent the mean for the control group, and the light blue bars add in the "Medicaid" effect found in the paper. The black "capped" bar represents the confidence interval for the Medicaid effect. Percent with Any Visits 50 €30 20 10 O Any O O Any and Total ED Use Emergency Department Data Control Mean Control Mean plus Medicaid Effect Cl for Medicaid Effect The results above imply that the price elasticity of demand for emergency department use is Number of Visits perfectly inelastic not perfectly inelastic perfectly elastic
Consider the following scenario. A sports economist has collected data to test the relationship between shot quality and points per game for a sample of NBA players. The data is a panel dataset comprised of 2,000 NBA players with season-level performance statistics over the past 50 NBA seasons. The sports economist is worried that the player's primary playing position might be correlated with both shot quality and points per game, and position is easy to measure. However, historical changes in analytics have influenced the types of shots players across the league have taken over time, and these changes are generally difficult to quantify. To address the potential omitted variable bias that could arise because of this, the economist should include in their regression: Time fixed effects O Neither time nor entity fixed effects Both time and entity fixed effects O Entity fixed effects