Hello, if you have any need, please feel free to consult us, this is my wechat: wx91due
ECON 104
Assignment 3
In this assignment you will estimate the effects of the Minimum Legal Drinking Age (MLDA) on alcohol consumption. The figures and tables you create will be used when you write your second paper. The dataset ”NHIS.csv” is a sample drawn from the National Health Interview Sample Adult Files 1997-2007. It includes the following vari- ables: HS diploma, Hispanic, White, Black, uninsured, employed, married, working lw, go
- ing school, male
, days 21 (days to 21st birthday, with negative values for days prior to turn-
ing 21), drinks alcohol (indivual reports that they drink alcohol), AGE yrs
, perc days drink
(percent of days on which they report drinking). Each row on the dataset is a record for an individual.
1. Determine what bin width to use for your age profile of whether or not people drink alcohol (variable name: drinks alcohol). Please attach a panel with graphs (4 or more)
for various choices of bin width. Why did you pick the one you did?
Please include your code.
2. Determine what range of age to include in your age profile of whether or not people drink alcohol (variable name: drinks alcohol). Please attach a panel with graphs (4 or
more) for various choices of range. Why did you pick the one you did
Please include your code.
3. Determine what range of alcohol consumption levels (vertical axis) to use in your age profile of whether or not people drink alcohol (variable name: drinks alcohol). Please
attach a panel with graphs (4 or more) for various choices of the range of drinks alcohol
.Why did you pick the one you did?
Please include your code.
4. Create a table of regression estimates of the increase in the proportion of people who drink with different order polynomials going from least to most flexible. What is the range of estimates you found for the effect of the MLDA on the proportion of people who drink?
5. Create a carefully labeled figure of the first stage relationship between the MLDA and whether or not people drink alcohol (variable name: drinks alcohol) with the
range and bin width choices you made in questions 1-3. Superimpose the fitted values from the regression specification in question 4 that you feel best fits the data. Which specification did you choose and why? Please include your code.
6. Overall, is the evidence consistent with the MLDA reducing the proportion of people who drink? What is magnitude of the reduction for your preferred specification?