Question

In: Statistics and Probability

There are two OLS regression specification Yi = aSexi + ui (1) Yi = b Malei...

There are two OLS regression specification

Yi = aSexi + ui (1)

Yi = b Malei + c Femalei + ui(2)

a, b, c, are constants.

Sexi = 1 if the person is Female, and 0 otherwise. Malei = 1 if Sexi = 0, Femalei = 1 if Sexi = 1, and both are 0 otherwise.

Why are neither regression(1) nor regression(2) directly tell you if the difference in Yi between Males and Females is statistically significant?

What would be an alternative and better regression specification, if using Sexi as the only variable? Please explain in details.

Solutions

Expert Solution

The way (1) has been formulated, we see that we can only test whether the effect of Female gender is significant, compariosn with Males is not possible as for an observation corresponding to male, we are assuming that it is just a random error, since the only coefficient sex_i, becomes zero. Hence, there's no way to test the equality.

We can't test for significance in model (2) either, as we are assuming Males and Females to be two different factors. This model is nothing but sum of two independent models like (1). In Model (1), we used an indicator for whether the gender is female. If we form another model with indicator whether the gender is make, then observe that model (2) is nothing but a combination of these models and hence suffer from the same sort of disadvantages.

We can modify model (1) to be able to test the significance as follows:

Note here we have added another subscript j, to account for replication (just to be formal). What we have added to the model is a mean effect . What 'a' now represents is the ADDITIONAL effect of the female gender over the mean effect. Thus, the effect of males and females are same if this additional effect is not significant. Thus, we can test

to test the same.


Related Solutions

1. Consider the model Ci= β0+β1 Yi+ ui. Suppose you run this regression using OLS and...
1. Consider the model Ci= β0+β1 Yi+ ui. Suppose you run this regression using OLS and get the following results: b0=-3.13437; SE(b0)=0.959254; b1=1.46693; SE(b1)=21.0213; R-squared=0.130357; and SER=8.769363. Note that b0 and b1 the OLS estimate of b0 and b1, respectively. The total number of observations is 2950.According to these results the relationship between C and Y is: A. no relationship B. impossible to tell C. positive D. negative 2. Consider the model Ci= β0+β1 Yi+ ui. Suppose you run this...
1. Consider the model Ci= β0+β1 Yi+ ui. Suppose you run this regression using OLS and...
1. Consider the model Ci= β0+β1 Yi+ ui. Suppose you run this regression using OLS and get the following results: b0=-3.13437; SE(b0)=0.959254; b1=1.46693; SE(b1)=0.0697828; R-squared=0.130357; and SER=8.769363. Note that b0 and b1 the OLS estimate of b0 and b1, respectively. The total number of observations is 2950. The number of degrees of freedom for this regression is A. 2952 B. 2948 C. 2 D. 2950 2. Consider the model Ci= β0+β1 Yi+ ui. Suppose you run this regression using OLS...
Consider the model Ci= β0+β1 Yi+ ui. Suppose you run this regression using OLS and get...
Consider the model Ci= β0+β1 Yi+ ui. Suppose you run this regression using OLS and get the following results: b0=-3.13437; SE(b0)=0.959254; b1=1.46693; SE(b1)=0.0697828; R-squared=0.130357; and SER=8.769363. Note that b0 and b1 the OLS estimate of b0 and b1, respectively. The total number of observations is 2950. The following values are relevant for assessing goodness of fit of the estimated model with the exception of A. 0.130357 B. 8.769363 C. 1.46693 D. none of these
Suppose that Yi=?0+?1Xi+ui and that E[ui|Xi] = 0 and therefore OLS is an unbiased estimator. a)...
Suppose that Yi=?0+?1Xi+ui and that E[ui|Xi] = 0 and therefore OLS is an unbiased estimator. a) Show that Zi=Xi is a valid instrument for Xi , i.e. it is both relevant and exogenous. b) Show that the 2SLS estimator of ?1 using Xi as an instrument for Xi is exactly equal to the OLS estimator of ?1 c) Let Zi=X2i and assume Xi is normally distributed N(?,?²). Is Zi exogenous? Is Zi relevant? Explain how the answer to these questions...
Consider the following regression model: Yi = αXi + Ui , i = 1, .., n...
Consider the following regression model: Yi = αXi + Ui , i = 1, .., n (2) The error terms Ui are independently and identically distributed with E[Ui |X] = 0 and V[Ui |X] = σ^2 . 1. Write down the objective function of the method of least squares. 2. Write down the first order condition and derive the OLS estimator αˆ. Suppose model (2) is estimated, although the (true) population regression model corresponds to: Yi = β0 + β1Xi...
3. Consider the simple linear regression Yi = 2Xi + ui for i = 1, 2,...
3. Consider the simple linear regression Yi = 2Xi + ui for i = 1, 2, . . . ,n. The ui are IID (0; 2 ). a. Derive OLS estimator of 2 and called it b 2 b. Find its variance c. Is b 2 unbiased, show it? d.What is the risk we run when we do not include an intercept in the regression? Do question d.
The regression model Yi = β0 + β1X1i + β2X2i + β3X3i + β4X4i + ui...
The regression model Yi = β0 + β1X1i + β2X2i + β3X3i + β4X4i + ui has been estimated using Gretl. The output is below. Model 1: OLS, using observations 1-50 coefficient std. error t-ratio p-value const -0.6789 0.9808 -0.6921 0.4924 X1 0.8482 0.1972 4.3005 0.0001 X2 1.8291 0.4608 3.9696 0.0003 X3 -0.1283 0.7869 -0.1630 0.8712 X4 0.4590 0.5500 0.8345 0.4084 Mean dependent var 4.2211 S.D. dependent var 2.3778 Sum squared resid 152.79 S.E. of regression 1.8426 R-squared 0 Adjusted...
Consider the simple linear regression: Yi = β0 + β1Xi + ui whereYi and Xi...
Consider the simple linear regression: Yi = β0 + β1Xi + ui where Yi and Xi are random variables, β0 and β1 are population intercept and slope parameters, respectively, ui is the error term. Suppose the estimated regression equation is given by: Yˆ i = βˆ 0 + βˆ 1Xi where βˆ 0 and βˆ 1 are OLS estimates for β0 and β1. Define residuals ˆui as: uˆi = Yi − Yˆ i Show that: (a) (2 pts.) Pn i=1...
Consider the instrumental variable regression model Yi = ?0 + ?1Xi + ?2Wi + ui where...
Consider the instrumental variable regression model Yi = ?0 + ?1Xi + ?2Wi + ui where Xi is correlated with ui and Zi is an instrument. Suppose that the first three assumptions in Key Concept 12.4 are satisfied. Which IV assumption is not satisfied when: (a) Zi is independent of (Yi , Xi , Wi)? (b) Zi = Wi? (c) Wi = 1 for all i? (d) Zi = Xi?
(i) Consider a simple linear regression yi = β0 + β1xi + ui Write down the...
(i) Consider a simple linear regression yi = β0 + β1xi + ui Write down the formula for the estimated standard error of the OLS estimator and the formula for the White heteroskedasticity-robust standard error on the estimated coefficient bβ1. (ii) What is the intuition for the White test for heteroskedasticity? (You do not need to describe how the test is implemented in practice.)
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT