Practice Problems for Test 1
Econ 3200  Introduction to Econometrics
Spring 2010
Cornell University
Prof. Molinari
This practice problems have two parts totaling 100 points. I will maintain the same structure for
the Test 1 that I am preparing for your class. The exam will be a CLOSED BOOK exam. However,
useful formulas will be provided on pages 4+. Calculators are permitted °but graphing calculators
are prohibited. You will have 75 minutes
to complete the exam. SHOW ALL your work as partial
credit will be given. Answers without explanations might NOT be given (full) credit even if they
are correct.
Part I: Short Answer (20 points, 4 points each)
In a few sentences, brie±y de²ne/describe the following. Use formulas if you think they will make
your answers more precise, but a formula without a written explanation is not an acceptable answer.
a) Convergence in Probability (i.e.
p
lim
)
b) Least Squares Estimator
c) Con²dence Interval (nonrejection region)
d) Unbiased Estimator
e) Gauss Markov Theorem
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Part II: 2 Long Questions, 80 Points (40 points each)
1. (40 points) All else equal, we would expect people with greater ability to earn higher wages.
A common but crude measure of ability is results of IQ tests.
This question explores the
relationship between IQ test scores and hourly wages.
Let
ln(
wage
)
denote the natural
logarithm of hourly wages. Let
ln(
IQ
)
denote the natural logarithm of IQ. Using a random
sample of 935 people, the following regression model estimates were obtained using OLS.
(Standard errors for each estimate are given in parentheses.)
ln(
wa
b
ge
i
)
=
°
1
:
87
+
0
:
75 ln(
IQ
i
)
R
2
= 0
:
067
(0
:
42)
(0
:
091)
Assume for now that Assumptions SLR.1SLR.5 hold.
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '08
 NEILSEN
 Econometrics, Least Squares, Normal Distribution, Regression Analysis, regression model, Yi

Click to edit the document details