Econ 371 Problem Set #1 Answer Sheet 2.1 In this question, you are asked to consider the random variable Y , which denotes the number of "heads" that occur when two coins are tossed. a. The first part of the question asks you to derive the probability dis
Econ 523, Spring 2007
Prof. Tom Hertz
Study Guide for Exam 2, part 2 (Chapters 12 & 13)
Chapter 12
In section 12.1 and 12.2, read up to page 428, including Eq. 12.4. That equation is what I
write as Cv(Y,Z)/Cv(X,Z).
You do not need to worry about the deta
Econ 523, Spring 2007
Prof. Tom Hertz
Study Guide for Exam 2 (Part 1: Chapters 6-9)
The exam covers chapters 6,7,8, 9, 12, and 13. Recall, however, that not all sections are
required. I dont think that re-reading each chapter in its entirety is a good use
Econ 783, Spring 2007
Tom Hertz
What Makes a Good IV Regression?
1) A vigorous defense of the validity of the instruments, on a priori grounds (i.e. based
on reasoning, not your results). Recall that the test is: does the instrument have any direct
correl
Econ 522, Fall 2006
Prof. Tom Hertz
Study Guide for Exam 2
The exam covers chapters 8, 9, 10, 12, 13, and 14. Recall, however, that not all sections are
required. I dont think that re-reading each chapter in its entirety is a good use of your time.
Here i
Econ 523, Spring 2007
Prof. Tom Hertz
Note on Degrees of Freedom Adjustments and Samples versus Populations
N? N-1? N-2? N-K-1?
Although it is true that in large datasets (like our sample of 935 workers) the difference between
N and N-2 is pretty trivial,
Econ 523, Fall 2007
Tom Hertz
Notes on Measurement Error
The key point here is that when we have noisy x-variables, i.e. variables that are measured
with some error, the regression coefficients associated with those variables will be attenuated
(smaller i
Econ 522, Spring 2007
Tom Hertz
Handout on Omitted Variables Bias
Suppose the true model is:
y 0 1 X 1 2 X 2 u
But we omit X2 in our regression, and generate estimates using only X1:
y 0 1 X 1
If we have data on both X2 and X1, we can run an ancillary reg
Econ 522, Fall 2006
Prof. Hertz
Notes on Creating Interaction Terms
We saw that creating interactions between variables can sometimes lead to strange estimates of
the direct effect of either or both variables. Suppose you have variables A and B, and you w
Discussion Section 4
ECON 139/239
2010 Summer Term II
1. Lets use the CollegeDistance.csv data again.
(a) An education advocacy group argues that, on average, a persons educational attainment would increase by approximately 0.15 years in distance to the n