Question

Please include screenshots of all output generated and all lines of code that you run. It's also enough to just copy-paste the code. Please use the built-in dataset of nlsw 88.

1. Build a model to explain hourly wage Find the most relevant variables and explain why some of the possible explanatory variables are not relevant. Then, discuss in detail all of the findings of the final model that you have chosen.
2. Build a model to explain the usual number of hours worked. Find the most relevant variables and explain why some of the possible explanatory variables are not relevant. Then, discuss in detail all of the findings of the final model that you have chosen.
3. Take the model that you have developed in step 1. Find at least one linear restriction that makes sense to test. Explain why. Reparameterize your model, write it down here. Then test your linear restriction and explain your findings.
4. Take the model that you have developed in step 2. Find at least one linear restriction that makes sense to test. Explain why. Reparameterize your model, write it down here. Then test your linear restriction and explain your findings.
5. Take all of the explanatory variables in the model that you have chosen for step 1 , and perform Goldfeld-Quandt tests on them manually. Explain and list your findings.
6. Take all of the explanatory variables in the model that you have chosen for step 2, and perform Goldfeld-Quandt tests on them manually. Explain and list your findings

Answer 1

To explore the relationship between the year and the percentage of workers paid hourly rates, a scatter plot is drawn, and a regression line is estimated. This is followed by computing the correlation coefficient to evaluate the significance of the relationship.

Step-by-step explanation:

To analyze the relationship between year and percent of workers paid hourly rates, one would begin by constructing a scatter plot with the year as the independent variable and the percent of workers paid hourly rates as the dependent variable. Upon visual inspection of this scatter plot, one can determine if there seems to be a certain trend or correlation between these variables. The significance of the y-intercept in this context depends on whether it is reasonable to expect a percent value when the year is zero, which is historically meaningless in most cases.

To formally quantify the relationship, a least-squares regression line is calculated, commonly written in the form ŷ = a + bx, where ŷ is the predicted value of the dependent variable, a is the y-intercept, and b is the slope of the line. Once the line is calculated, one can compute the correlation coefficient to assess the strength and direction of the relationship. A significant correlation coefficient suggests a strong relationship between the years and the percent of the hourly paid workers.