Econometrics 301 – HW3
Analysis Question Assignment: What are the components that decide the abortion fee throughout the 50 states within the USA?
To review this, use the dataset (uploaded on LMS). The variables used within the Assessment are as follows:
State: Identify of the State (50 US States)
ABR: Abortion fee, variety of abortions per thousand ladies aged 15-44 in 1992.
Faith: The % of a state’s inhabitants that’s Catholic, Southern Baptist, Evangelical, or Mormon.
Value: The typical value charged in 1993 in non-hospital amenities for an abortion at 10 weeks with native anesthesia (weighted by the variety of abortions carried out in 1992)
Funds: A variable that takes worth of 1 if state funds can be found to be used to pay for an abortion below most circumstances, zero in any other case.
Legal guidelines: A variable that takes worth of 1 if a state enforces a legislation that restricts a minor’s entry to abortion, zero in any other case
Educ: The % of a state’s inhabitants that’s 25-years or older with a highschool diploma (or equal), 1990.
Earnings: disposable earnings per capita, 1992.
Picket: The proportion of respondents that reported experiencing picketing with bodily contact or blocking of sufferers
Question Assignment:
a) Estimate the next fashions utilizing lm( ) command. Contemplating the potential thread posed by heteroscedasticity drawback, use the heteroscedasticity-consistent strong errors.
?ABR?_i = ?_1 + ?_2 Faith + e_i
?ABR?_i = ?_1 + ?_2 Faith + ?_3 Value + e_i
?ABR?_i = ?_1 + ?_2 Faith + ?_3 Value + ?_4 Legal guidelines + ?_5 Funds + e_i
?ABR?_i = ?_1 + ?_2 Faith + ?_3 Value + ?_4 Legal guidelines + ?_5 Funds + ?_6 Educ + ?_7 Earnings + ?_8 Picket + e_i
b) Calculate the fitted values and residuals for every mannequin.
c) Plot the residuals of every mannequin. Do you assume the heteroscedasticity is an issue for our regression mannequin. We’ve got solely 50 observations on this dataset. What’s the limitation(s) of utilizing the heteroscedasticity-consistent strong errors?
d) Calculate the SER and R^2 utilizing the data you obtained in b) and confirm that the abstract(lm( )) offers the identical SER and R^2.
e) What’s the F-test outcomes for every mannequin? What does F-test inform us concerning the general significance of our fashions?
f) What’s adjusted R-squared means? Do you assume the R^2 and adjusted-R^2 values is comparable to one another?
g) How the R^2 worth modifications with the brand new variables from Mannequin 1-to-Four.
h) Do now we have the precise to be suspicious about omitted varible bias?
Analysis Question Assignment: What are the components that decide the hourly wages?
To review this, use the dataset (uploaded on LMS). The variables used within the Assessment are as follows:
Wage: Hourly wage in dollars (CPS, 1995)
Feminine: Gender, coded 1 for feminine, zero for male
Nonwhite: Race, coded 1 for nonwhite staff, zero for white staff
Union: Union standing, coded 1 if a union job, zero in any other case
Training: Training (in years)
Exper: Potential work expertise (in years)
Question Assignment:
a) Estimate the next regression mannequin:
?Wage?_i = ?_1 + ?_2 Feminine+ ?_3 Nonwhite+ ?_4 Union + ?_5 Exper + e_i
Interpret the coefficients. Are there any insignificant coefficients?
b) As an alternative of utilizing wage, use log(wage) to estimate the regression mannequin:
?Log(Wage?_i) = ?_1 + ?_2 Feminine+ ?_3 Nonwhite+ ?_4 Union + ?_5 Exper + e_i
How the regression consequence has modified? How the interpretation of the coefficients modified? Do you assume it’s a good suggestion to make use of the logarithm of wage as a substitute of wages.
c) Now, assume that each years of education and years of expertise will increase the log(wage) with a lowering fee. How would you modify the Mannequin 2. When you write down the regression mannequin, estimate the mannequin parameters. Do you assume the coefficients satisfies your expectations?
d) Think about Mannequin 2. Now estimate the regression with month-to-month wages assuming that people work for eight hours in a day, and 22 days in a month. Then, take the logarithm of the month-to-month wages and estimate the regression mannequin once more. Interpret the coefficients.
e) What occurs should you mistakenly add “White” to the regression mannequin which is coded 1 if the employee is white, zero in any other case. Clarify the dummy variable entice intimately.
—
Econometrics 301 – HW3 Analysis Question Assignment: What components affect the abortion fee in the US’ 50 states?
Use the dataset to research this (uploaded on LMS). The next are the variables that had been used within the Assessment:
State: What’s the identify of the state? (50 US States)
ABR stands for abortion fee, which is outlined because the variety of abortions per thousand ladies aged 15 to 44 in 1992.
The variety of Catholics, Southern Baptists, Evangelicals, and Mormons in a state’s inhabitants.
The typical price of an abortion at 10 weeks with native anesthetic in non-hospital establishments in 1993. (weighted by the variety of abortions carried out in 1992)
Funds: A variable that takes the worth 1 if state funds can be found for utilization in most cases to pay for an abortion, and zero in any other case.
Legal guidelines: A variable that’s 1 if a state has enacted a laws limiting a minor’s entry to abortion, and zero in any other case.
Educ: In 1990, the proportion of a state’s inhabitants aged 25 or older who had a highschool diploma (or equal).
Earnings: per capita disposable earnings in 1992.
Picket: The proportion of responders who mentioned they’ve been subjected to picketing that included bodily contact or affected person blockage.
Question Assignment:
a) Utilizing the lm() software, estimate the next fashions. Use the heteroscedasticity-consistent strong errors to deal with the potential situation provided by the heteroscedasticity drawback.
?ABR? i =?_1 +?_2?ABR? i =?_1 +?_2?ABR? i e i + faith
?ABR? i =?_1 +?_2 Faith +?_3 Value + e i?ABR? i =?_1 +?_2 Faith +?_3 Value + e i?ABR? i
?ABR? i =?_1 +?_2 Faith +?_3 Value +?_4 Value +?_5 Value +?_6 Value +?_7 Value +?_8 Value +?_9 Value +?
e i = Four legal guidelines +?_5 funds
?ABR? i =?_1 +?_2 +?_3 +?_4 +?_5 +?_6 +
2 Faith +?_3 Value +? Four? 5? 6? 7? eight?
?_5 Funds + Four Legal guidelines =
6 Educ +?
Picket + e i = eight
b) For every mannequin, calculate the fitted values and residuals.
c) Plot every mannequin’s residuals. Do you assume the heteroscedasticity in our regression mannequin is an issue? This dataset has solely 50 observations. What are the drawbacks of adopting strong errors which are heteroscedasticity-consistent?
d) Utilizing the data from b), calculate the SER and R2, and examine that abstract(lm()) returns the identical SER and R2.
g) What are the outcomes of the F-test for every mannequin? What does the F-test inform us about our fashions’ general significance?
f) What does the time period “adjusted R-squared” imply? Do you imagine the R2 and adjusted-R2 figures are comparable?
g) How the R2 worth modifications because the variety of variables in Mannequin 1 to Four will increase.
h) Is it cheap to be cautious about omitted variable bias?
What components affect hourly pay, in response to the analysis Question Assignment?
Use the dataset to research this (uploaded on LMS). The next are the variables that had been used within the Assessment:
Wage: Greenback hourly wage (CPS, 1995)
Gender is coded 1 for feminine and zero for male.
Nonwhite: Race; nonwhite staff are coded 1; white staff are coded zero.
Union standing is coded 1 if the job is a union job and zero if it’s not.
Training is basically essential (in years)
Exper: Chance of gaining work expertise (in years)
Question Assignment:
a) Create a regression mannequin that appears like this:
?Wage? i =?_1 +?_2 Feminine+? three Nonwhite+? Four Union + e i
Calculate the coefficients. Are there any coefficients that are not important?
b) To estimate the regression mannequin, as a substitute of utilizing wage, use log(wage):
?Log(Wage? i) =?_1 +?_2 Feminine+? three Nonwhite+? Four Union + e i
What has modified within the regression consequence? What modified within the which means of the coefficients? Do you imagine utilizing the wage logarithm as a substitute of wages is a good suggestion?
c) Now think about that the log(wage) will increase at a lowering fee as each years of education and years of expertise enhance. What modifications would you make to the Mannequin 2? Estimate the mannequin parameters after you’ve got written out the regression mannequin. Do you imagine that the coefficients meet your expectations?
d) Take into consideration Mannequin 2. Now calculate the regression utilizing month-to-month pay, assuming that folks work eight hours per day for 22 days per 30 days. Then, utilizing the logarithm of month-to-month wages, recalculate the regression mannequin. Calculate the coefficients.
e) What occurs should you add “White” to the regression mannequin accidentally, which is coded 1 if the employee is white and zero in any other case. Clarification of the dummy variable entice.
