ECON213 Name:
Midterm 1
Absolutely no late midterms will be accepted. You may hand it in early if you like.
Midterms are to be completed independently (no corroborating with other students), and to be emailed as a PDF.
Ensure all questions are answered clearly. You must include the following statement at the beginning of
your midterm submission to acknowledge that your clearly understand the rules and consequences of
the take home midterm:
““I, [name], understand that this midterm is to be completed independently. I have asked noquestions to any other human, with the exception of the TA or the professor, regarding thismidterm. I understand that any suspicion of plagiarism or academic dishonesty will result in azero grade for this midterm.
This statement and my name act as an understanding and compliance of the terms.
Signed, [name].”
”You will be using data on single family homes sold in Lucas County, Ohio, between 1993-1998 as reported from the
county auditor (see house.dta on Latte). The file is in Stata data format, so use,
> library(foreign) > read.dta command, or > library(haven) > read dta command.
N.B. property assessment values are used to determine the amount of property tax the homeowner pays. See
http://co.lucas.oh.us/358/Real-Estate-Appraisal-and-Assessment for more details. The important thing about the
assessed value is that it is a completely deterministic process: the government takes publicly known features about
the house (ex. square footage, lot size, number of windows, zip code, etc.)–all of which are in the dataset–plugs
these into a formula, and the output is the assessed value (which is what property taxes are based on). There is
no error term, things like “outdated kitchen” have no effect on the assessed value, but certainly do on the market price.
One degree of latitude is approximately 69 miles; one degree of longitude (at about 40 degrees latitude) is ap-
proximately 53 miles.
Map of Lucas County, OH:
ECON213 Midterm 1 - Page 2 of 2
1. Data Inspection and Statistical Inference:
(a) How many variables and observations does the dataset contain? Which variables are dummy variables?
Which variables are categorical variables (more than 2 categories)?
(b) Show price, the dependent variable, as a histogram. Describe the distribution.
(c) Determine the relationship between sqft and price, and garage type and price.
(d) Show saledate as a histogram (because it is a time variable, declare how you want your bins divided,
hist(saldate, "break"), where break is days, weeks, months, or years). Is there any useful information
here?
2. Model Selection and Output
(a) Construct your model by theory and statistical inference. What are your determinants of sale price? Please
describe any variables added from external sources (cite!) or created as transformations of other variables.
Present your regressors in a table and explain why you include them (include what your expected effect of
each is on your price).
(b) Are there any variables missing from the dataset? Which ones may cause omitted variable bias?
(c) Run your regressions and diagnoses to determine if there are any OLS violations. Is heteroskedasticity
present? Demonstrate how you came to your conclusion. If heteroskedasticity is present, use robust standard
errors (> library(sandwich) > coeftest(regressionname, vcov=vcovHC(regressionname, type = ‘‘HC1’’))).
Are there any other clear patterns?
(d) What is your choice model(s). Defend your model selection. Present the results in a table. What corrections
did you make to your initial theorized model, and why did you select it/them?
(e) Interpret all your the coefficients (mainly dummy variables, and where you use natural log transformation,
or polynomials).
(f) Provide an explanation for any surprising or counterintuitive coefficients.














































学霸联盟