# Computer Based Problems using Stata – IT Assignment

## Stata Assignment Help

Using the posted data set WAGE2.DTA, consider the model where the return to education depends upon the amount of work experience, i.e.

(a) Show that the return to another year of education, holding exper Öxed, is equal to

(b) State the null hypothesis that the return to education does not depend on the level of experience.
(c) Estimate the model above and test the null hypothesis in (b) against the stated alternative.

(b) Using the equation from (a), what is the ìoptimalî high school size? Show your work.

(c) Is this analysis representative of the academic performance of ALL high school seniors? Explain (think about the selection issue and the types of students we observe in the data).

(d) Now Önd the ìoptimalî high school size using ln(sat) as the dependent variable. Is your answer here much di§erent that what you obtained in part (b)? Show your work.

3. Using the posted data set BWGHT2_SMALL.DTA, and answer the following (note, the analyst made an error when coding the data, so wherever you see 9 for npvis, you need to recode that as 9):

(a) Estimate the equation

and report the results. Is the quadratic term statistically signiÖcant at conventional levels?
(b) Show that, based on the model in part (a), the number of prenatal visits that maximizes lbwght (the optimal level) is estimated to be about 23. How many women in the sample had at least 23 prenatal visits.

(c) Does it make sense that birth weight is actually predicted to decline after 23 visits? Explain?

(d) Now add motherís age (mage) to the model, using the quadratic functional form. Holding npvis Öxed, at what motherís age is the birth weight of the child maximized? What fraction of women in the sample are older than this ìoptimalîage?

4. Using the posted data set WAGE1.DTA, estimate a model where you regress wage on educ, exper, and tenure and answer the following:
(a) Estimate the equation

and then plot a histogram of the residuals. To do this, Örst estimates the model and predict the residuals. Suppose you save your residuals as uhat. The Stata command plot those residuals against a normal curve is:

hist uhat, normal

(b) Repeat part (a), but with ln(wage) as the dependent variable.

(c) Do you think assumption (A6) is better satisÖed for the level-level model or the log-level model? Explain