代写Problem Set 5, Econ 120C代做留学生Matlab编程
- 首页 >> Database作业Problem Set 5, Econ 120C
The debate regarding crime and guns is of course long running. The book 'More Guns, Less Crime: Understanding Crime and Gun Control Laws' by Lott (American Enterprise Institute) loudly made the claim that ëshallílaws reduce crime based on correlation analysis. In this prob- lem set, we will evaluate the claim and see whether we can shoot down the ëMore Guns, Less Crimeíhypothesis (Ayres and Donohue III in the Stanford Law Review (2003)). The book received high ratings at Amazon.com and there are many customer reviews (see https://www.amazon. com/More-Guns-Less-Crime-Understanding/dp/0226493660). Everybody has something to say about this issue. Letís see what we can conclude from econometric analysis.
The questions are based on the dataset handguns.dta, which you can download from the class page. The data consists of data from 50 States plus DC for each year from 1977 to 1999. The data we will be analyzing are crimes rates for various crime deÖnitions provided by the Bureau of Justice Statistics (https://bjs.ojp.gov/). The variables are described in the Stata data set. The main causal factor we will be focussing on is a dummy variable for whether or not the state allows widespread carrying of concealed weapons. The variable shall is equal to 1 for states which have ëshall issueílaws, which means that licenses must be given to all applicants who are citizens, mentally competent, and have not been convicted of a felony (A state shall issue the license).
For additional background, see Empirical Exercise E10.1 in Stock and Watson, page 344. NOTE: the data on the class page contains more variables than that on the textbookís page. You may also want to read
http://en.wikipedia.org/wiki/More_Guns,_Less_Crime#Shall_issue_laws or
https://ianayres.yale.edu/sites/default/files/files/Ayres_Donohue_article.pdf
Note: you do not need to submit your Stata output. However, please submit your Stata do or log Öle (print it into pdf and include it in your answers).
I. We will examine the e§ect of shall on rates of violent crime, murder rates and robberies. To this end, run regressions of the logs of each of these variables on shall (including an intercept) with the robust option. Report the results in a table with a column for each regression and the values and their standard errors in rows. That is, Öll in the following table:
Dependent Var = |
ln(vio) |
ln(mur) |
ln(rob) |
β(^)0 (intercept) |
6.13 |
|
|
|
(0.02) |
( ) |
( ) |
β(^)1 (shall) |
-0.443 |
|
|
|
(0.048) |
( ) |
( ) |
R2 |
0.09 |
|
|
(a) What is the effect of 'shall' laws on each of the crime rates. Are the e§ects large statisti- cally? Explain (hint: look at the t-statistic).
To get started, you can first download the file 'handguns.dta' from the course page and then use the following commands in your Stata do file. A do file is a text file that contains a sequence of Stata commands. If you do not feel like using a semicolon ';' to end a command, you can remove the line ''#delimit ;'' and the semicolon at the end of each command.
clear
clear matrix
#delimit ;
set more off;
capture log close;
cd D:;
log using shall.log, replace;
use handguns.dta;
desc;
summarize;
gen log_vio=log(vio);
gen log_mur=log(mur);
gen log_rob=log(rob);
/************ Question I *******/
reg log_vio shall, r;
reg log_mur shall, r;
reg log_rob shall, r;
II. Now we will control for a number of variables. First, it is well understood that demographic variables play a role. Many have argued socioeconomic variables also play a part. Most also would at least hope that jail is a deterrent. Run the above regressions but now add the variables incarc_rate, density, pop, pm1029, and avginc to the regression. That is,
Yit = β 0 + β1 shall it + β2Wit + u it
where Yit is log of a crime rate (log(vio), log(mur), or log(rob))and Wit contains all the control variables listed above.
Report the results in a table given below.
(a) What is the e§ect of the 'shall' laws now?
(b) Is the di§erence between the results here and in the results from Question (I) large in a practical sense? (hint: check whether the percentage point dropped is large or not from a practical sense. For example, I would argue that a drop of more than 5% is large from a practical sense).
Dependent Var = |
ln(vio) |
ln(mur) |
ln(rob) |
β(^)0 (intercept) |
|
-0.17 |
|
|
( ) |
(0.29) |
( ) |
β(^)1 (shall) |
|
-0.309 |
|
|
( ) |
(0.037) |
( ) |
R2 |
|
0.55 |
|
Note: incarc_rate, density, pop, pm1029, and avginc should be included in the regression, but you do not have to report their coe¢ cients.
III. One omitted variable from the above analysis is di§erences in laws and law enforcement across states and time. We want to understand how this might a§ect our ability to estimate the causal e§ect of ëshallí. Recall the omitted variable bias formula:
β(^)1 ! β 1 + cov(shall; u) :
Stronger laws would hopefully deter crime, especially crimes that are more rational in nature like roberries, and perhaps violence. In this sense, we would expect that stronger laws would be associated with less crime and hence lower values for u:
(a) Typically ëshallílaws are pushed using law and order arguments
[read: http://en.wikipedia.org/wiki/Law_and_order_(politics)]. States with a larger ëlaw and orderíconstituency would have stronger laws and would be more likely to have ëshallílaws. What does this suggest the sign of cov(shall; u)? (Hint: do the states with a larger ëlaw and orderí constituency tend to have lower or higher u? I would argue that the states with a larger ëlaw and orderíconstituency tend to have lower u; that is, lower crime rate after controlling for the variables given in QII).
(b) If there is a bias in β(^)1 (the coe¢ cienton shall), which direction is it?
IV. Since we have a panel data set, we are able to control for omitted variables that are constant overtime. We want to run the same regressions (i.e., use the same control variables) as in question II, but now add state Öxed e§ects. Do this for each of the three dependent variables we have examined, and construct three tables (one for each dependent variable). In each table, report the coe¢ cient on ëshallí along with its standard error and test for whether state e§ects should be included.
Each table should look like the following (with the entries added instead of the XXís, of course).
Dep=ln(violence) |
1 |
2 |
Shall |
XX(XX) |
XX(XX) |
State Fixed Effects? |
No |
Yes |
F test for state effects |
- |
XX |
(a) Describe the effect of controlling for state e§ects on the coe¢ cient estimate for the e§ect of ëshallílaws on crime (does the estimated coe¢ cient on ëShallíbecome smaller? Is the estimated coe¢ cient close to zero? Is the coe¢ cient estimate still statistically signiÖcant at the usual level, say 5%?)
(b) In the regression without the state e§ects, the state e§ects can be regarded as the omitted variables. Does the result in (a) suggest that the state e§ect may be correlated with ìShallî?
(c) What is the statistical evidence that state dummy variables should be included? (Hint: Test the null hypothesis that all coe¢ cients on statedummy* are zeros)
(d) Do these results suggest that the arguments in QIII are correct?
Stata issues:
The command tab state, generate(statedummy) will take a variable in your data set called state, which has a number for each state and construct dummy variables named statedummy1 through to the highest number statedummy51 where statedummy1=1 for state equal to 1 and zero otherwise, statedummy2=1 for state equal to 2 and zero otherwise, etc.
The following code can be used to produce the required table
tab state, gen(statedummy);
/* column 1 in the table */
reg log_vio shall incarc_rate density pop pm1029 avginc, r;
/* column 2 in the table */
reg log_vio shall incarc_rate density pop pm1029 avginc statedummy*, r; testparm statedummy
Note: testparm provides a useful alternative to test that permits a data variable list, allowing the use of standard Stata notation, including the wild card ë*í.