Introduction to Econometrics

The statistical analysis of economic (and related) data

1/2/3-1

Brief Overview of the Course

Economics suggests important relationships, often with policy
implications, but virtually never suggests quantitative
magnitudes of causal effects.
What is the quantitative effect of reducing class size on
student achievement?
How does another year of education change earnings?
What is the price elasticity of cigarettes?
What is the effect on output growth of a 1 percentage
point increase in interest rates by the Fed?
What is the effect on housing prices of environmental
improvements?
1/2/3-2

This course is about using data to measure causal effects.

Ideally, we would like an experiment
owhat would be an experiment to estimate the effect of
class size on standardized test scores?
But almost always we only have observational
(nonexperimental) data.
oreturns to education
ocigarette prices
omonetary policy
Most of the course deals with difficulties arising from using
observational to estimate causal effects
oconfounding effects (omitted factors)
osimultaneous causality
1/2/3-3

ocorrelation does not imply causation

1/2/3-4

In this course you will:

Learn methods for estimating causal effects using
observational data
Learn some tools that can be used for other purposes, for
example forecasting using time series data;
Focus on applications theory is used only as needed to
understand the whys of the methods;
Learn to evaluate the regression analysis of others this
means you will be able to read/understand empirical
economics papers in other econ courses;
Get some hands-on experience with regression analysis in
your problem sets.
1/2/3-5

Review of Probability and Statistics

(SW Chapters 2, 3)
Empirical problem: Class size and educational output
Policy question: What is the effect on test scores (or some

other outcome measure) of reducing class size by one

student per class? by 8 students/class?
We must use data to find out (is there any way to answer
this without data?)

1/2/3-6

The California Test Score Data Set

All K-6 and K-8 California school districts (n = 420)
Variables:
5PthP grade test scores (Stanford-9 achievement test,
combined math and reading), district average
Student-teacher ratio (STR) = no. of students in the
district divided by no. full-time equivalent teachers

1/2/3-7

Initial look at the data:

(You should already know how to interpret this table)

This table doesnt tell us anything about the relationship

between test scores and the STR.
1/2/3-8

Do districts with smaller classes have higher test scores?

Scatterplot of test score v. student-teacher ratio

what does this figure show?

1/2/3-9

We need to get some numerical evidence on whether districts

with low STRs have higher test scores but how?
1.

2.

3.

Compare average test scores in districts with low STRs

to those with high STRs (estimation)
Test the null hypothesis that the mean test scores in
the two types of districts are the same, against the
alternative hypothesis that they differ (hypothesis
testing)
Estimate an interval for the difference in the mean test
scores, high v. low STR districts (confidence
interval)
1/2/3-10

Initial data analysis: Compare districts with small (STR <

20) and large (STR 20) class sizes:
Class Average score (
Size
Y)
Small
Large

657.4
650.0

Standard
deviation
(sBYB)
19.4
17.9

238
182

1. Estimation of = difference between group means

2. Test the hypothesis that = 0
3. Construct a confidence interval for

1/2/3-11

1. Estimation
Ysmall Ylarge =

1
nsmall

nsmall

Y
i 1

1
nlarge

nlarge

Y
i 1

= 657.4 650.0
= 7.4
Is this a large difference in a real-world sense?
Standard deviation across districts = 19.1
Difference between 60PthP and 75PthP percentiles of test
score distribution is 667.6 659.4 = 8.2
This is a big enough difference to be important for school
reform discussions, for parents, or for a school
committee?
1/2/3-12

2. Hypothesis testing
Difference-in-means test: compute the t-statistic,
t

Ys Yl
ss2
ns

sl2
nl

Ys Yl

SE (Ys Yl )

(remember this?)

where SE(Ys Yl ) is the standard error of Ys Yl , the

subscripts s and l refer to small and large STR districts,
ns
1
2
2
s

(
Y

Y
)
and s
(etc.)

i
s
ns 1 i 1

1/2/3-13

Compute the difference-of-means t-statistic:

Size
small
large

sBYB
19.4
17.9

Y
657.4
650.0
t

Ys Yl
ss2
ns

sl2
nl

657.4 650.0
19.42
238

17.92
182

n
238
182

7.4

1.83 = 4.05

|t| > 1.96, so reject (at the 5% significance level) the null
hypothesis that the two means are the same.

1/2/3-14

3. Confidence interval
A 95% confidence interval for the difference between the
means is,
(Ys Yl ) 1.96SE(Ys Yl )
= 7.4 1.961.83 = (3.8, 11.0)
Two equivalent statements:
1. The 95% confidence interval for doesnt include 0;
2. The hypothesis that = 0 is rejected at the 5% level.

1/2/3-15

What comes next

The mechanics of estimation, hypothesis testing, and
confidence intervals should be familiar
These concepts extend directly to regression and its
variants
Before turning to regression, however, we will review
some of the underlying theory of estimation, hypothesis
testing, and confidence intervals:
why do these procedures work, and why use these
rather than others?
So we will review the intellectual foundations of
statistics and econometrics
1/2/3-16

Review of Statistical Theory

1.
2.
3.
4.

The probability framework for statistical inference

Estimation
Testing
Confidence Intervals

The probability framework for statistical inference

(a) Population, random variable, and distribution
(b) Moments of a distribution (mean, variance, standard
deviation, covariance, correlation)
(c) Conditional distributions and conditional means
(d)
Distribution of a sample of data drawn randomly from a
population: YB1B,, YBnB
1/2/3-17

(a) Population, random variable, and distribution

Population
The group or collection of all possible entities of interest

(school districts)
We will think of populations as infinitely large ( is an
approximation to very big)

Random variable Y
Numerical summary of a random outcome (district
average test score, district STR)

1/2/3-18

Population distribution of Y
The probabilities of different values of Y that occur in the
population, for ex. Pr[Y = 650] (when Y is discrete)
or: The probabilities of sets of these values, for ex. Pr[640
Y 660] (when Y is continuous).

1/2/3-19

(b) Moments of a population distribution: mean, variance,

standard deviation, covariance, correlation
mean = expected value (expectation) of Y
= E(Y)
= BYB
= long-run average value of Y over repeated
realizations of Y
variance = E(Y BYB)P2P
= Y2
= measure of the squared spread of the
distribution
standard deviation =

variance = BYB
1/2/3-20

Moments, ctd.
3

E Y Y

skewness =
Y3

= measure of asymmetry of a distribution

skewness = 0: distribution is symmetric
skewness > (<) 0: distribution has long right (left) tail
4

E Y Y

kurtosis =
Y4

= measure of mass in tails

= measure of probability of large values
kurtosis = 3: normal distribution
skewness > 3: heavy tails (leptokurtotic)
1/2/3-21

1/2/3-22

2 random variables: joint distributions and covariance

Random variables X and Z have a joint distribution
The covariance between X and Z is
cov(X,Z) = E[(X BXB)(Z BZB)] = BXZB
The covariance is a measure of the linear association
between X and Z; its units are units of X units of Z
cov(X,Z) > 0 means a positive relation between X and Z
If X and Z are independently distributed, then cov(X,Z) = 0
(but not vice versa!!)
The covariance of a r.v. with itself is its variance:

1/2/3-23

cov(X,X) = E[(X BXB)(X BXB)] = E[(X BXB)P2P] =

X2

1/2/3-24

The covariance between Test Score and STR is negative:

so is the correlation
1/2/3-25

The correlation coefficient is defined in terms of the

covariance:

corr(X,Z) =

cov( X , Z )
XZ

= rBXZB
var( X ) var( Z ) X Z

1 corr(X,Z) 1
corr(X,Z) = 1 mean perfect positive linear association
corr(X,Z) = 1 means perfect negative linear association
corr(X,Z) = 0 means no linear association

1/2/3-26

The correlation coefficient measures linear association

1/2/3-27

(c) Conditional distributions and conditional means

Conditional distributions
The distribution of Y, given value(s) of some other
random variable, X
Ex: the distribution of test scores, given that STR < 20
Conditional expectations and conditional moments
conditional mean = mean of conditional distribution
= E(Y|X = x) (important concept and notation)
conditional variance = variance of conditional distribution
Example: E(Test scores|STR < 20) = the mean of test
scores among districts with small class sizes
The difference in means is the difference between the
means of two conditional distributions:
1/2/3-28

Conditional mean, ctd.

= E(Test scores|STR < 20) E(Test scores|STR 20)
Other examples of conditional means:
Wages of all female workers (Y = wages, X = gender)
Mortality rate of those given an experimental treatment (Y
= live/die; X = treated/not treated)
If E(X|Z) = const, then corr(X,Z) = 0 (not necessarily vice
versa however)
The conditional mean is a (possibly new) term for the
familiar idea of the group mean

1/2/3-29

(d) Distribution of a sample of data drawn randomly

from a population: YB1B,, YBnB
We will assume simple random sampling
Choose and individual (district, entity) at random from the
population
Randomness and data
Prior to sample selection, the value of Y is random
because the individual selected is random
Once the individual is selected and the value of Y is
observed, then Y is just a number not random
The data set is (YB1B, YB2B,, YBnB), where YBiB = value
of Y for the iPthP individual (district, entity) sampled
1/2/3-30

Distribution of YB1B,, YBnB under simple random

sampling
Because individuals #1 and #2 are selected at random, the
value of YB1B has no information content for YB2B. Thus:
oYB1B and YB2B are independently distributed
oYB1B and YB2B come from the same distribution, that
is, YB1B, YB2B are identically distributed
oThat is, under simple random sampling, YB1B and YB2B
are independently and identically distributed (i.i.d.).
oMore generally, under simple random sampling,
{YBiB}, i = 1,, n, are i.i.d.

1/2/3-31

This framework allows rigorous statistical inferences about

moments of population distributions using a sample of data
from that population
1. The probability framework for statistical inference
2. Estimation
3. Testing
4. Confidence Intervals
Estimation
Y is the natural estimator of the mean. But:
(a) What are the properties of Y ?
(b) Why should we use Y rather than some other estimator?
YB1B (the first observation)
maybe unequal weights not simple average
1/2/3-32

 median(YB1B,, YBnB)
The starting point is the sampling distribution of Y

1/2/3-33

(a) The sampling distribution of Y

Y is a random variable, and its properties are determined by
the sampling distribution of Y
The individuals in the sample are drawn at random.
Thus the values of (YB1B,, YBnB) are random
Thus functions of (YB1B,, YBnB), such as Y , are random:
had a different sample been drawn, they would have taken
on a different value
The distribution of Y over different possible samples of
size n is called the sampling distribution of Y .
The mean and variance of Y are the mean and variance of
its sampling distribution, E(Y ) and var(Y ).
The concept of the sampling distribution underpins all of
econometrics.
1/2/3-34

The sampling distribution of Y , ctd.

Example: Suppose Y takes on 0 or 1 (a Bernoulli random
variable) with the probability distribution,
Pr[Y = 0] = .22, Pr(Y =1) = .78
Then
E(Y) = p1 + (1 p)0 = p = .78

Y2 = E[Y E(Y)]2 = p(1 p) [remember this?]

= .78(1.78) = 0.1716
The sampling distribution of Y depends on n.
Consider n = 2. The sampling distribution of Y is,
Pr(Y = 0) = .222 = .0484
Pr(Y = ) = 2.22.78 = .3432
Pr(Y = 1) = .782 = .6084
1/2/3-35

The sampling distribution of Y when Y is Bernoulli (p = .78):

1/2/3-36

Things we want to know about the sampling distribution:

What is the mean of Y ?
oIf E(Y ) = true = .78, then Y is an unbiased estimator
of
What is the variance of Y ?
oHow does var(Y ) depend on n (famous 1/n formula)
Does Y become close to when n is large?
oLaw of large numbers: Y is a consistent estimator of
Y appears bell shaped for n largeis this generally
true?
oIn fact, Y is approximately normally distributed
for n large (Central Limit Theorem)
1/2/3-37

The mean and variance of the sampling distribution of Y

General case that is, for Yi i.i.d. from any distribution, not
just Bernoulli:
1 n
1 n
1 n
mean: E(Y ) = E( Yi ) = E (Yi ) = Y = Y
n i 1
n i 1
n i 1
Variance:

var(Y ) = E[Y E(Y )]2

= E[Y Y]2
1

= E Y
i Y
n i 1

= E (Yi Y )
n i 1

1/2/3-38

var(Y ) = E (Yi Y )
n i 1

so

1 n
1 n

= E (Yi Y ) (Y j Y )

n i 1
n j 1

1 n n
= 2 E (Yi Y )(Y j Y )
n i 1 j 1
1 n n
= 2 cov(Yi , Y j )
n i 1 j 1
1
= 2
n

Y
i 1

Y2
=
n
1/2/3-39

Mean and variance of sampling distribution of Y , ctd.

E(Y ) = Y

Y2
var(Y ) =
n
Implications:
1.
2.

Y is an unbiased estimator of Y (that is, E(Y ) = Y)

var(Y ) is inversely proportional to n
the spread of the sampling distribution is
proportional to 1/ n
Thus the sampling uncertainty associated with Y is
proportional to 1/ n (larger samples, less
uncertainty, but square-root law)
1/2/3-40

The sampling distribution of Y when n is large

For small sample sizes, the distribution of Y is complicated,
but if n is large, the sampling distribution is simple!
1. As n increases, the distribution of Y becomes more tightly
centered around Y (the Law of Large Numbers)
2. Moreover, the distribution of Y Y becomes normal (the
Central Limit Theorem)

1/2/3-41

The Law of Large Numbers:

An estimator is consistent if the probability that its falls
within an interval of the true population value tends to one
as the sample size increases.
If (Y1,,Yn) are i.i.d. and Y2 < , then Y is a consistent
estimator of Y, that is,
Pr[|Y Y| < ] 1 as n
p

which can be written, Y Y

p

(Y Y means Y converges in probability to Y).

Y2
(the math: as n , var(Y ) =
0, which implies that Pr[|Y
n
Y| < ] 1.)
1/2/3-42

The Central Limit Theorem (CLT):

If (Y1,,Yn) are i.i.d. and 0 < Y2 < , then when n is large
the distribution of Y is well approximated by a normal
distribution.
Y2
Y is approximately distributed N(Y,
) (normal
n
distribution with mean Y and variance Y2 /n)
n (Y Y)/Y is approximately distributed N(0,1)
(standard normal)
Y E (Y ) Y Y
That is, standardized Y =
=
is
Y / n
var(Y )
approximately distributed as N(0,1)
The larger is n, the better is the approximation.
1/2/3-43

Sampling distribution of Y when Y is Bernoulli, p = 0.78:

1/2/3-44

Same example: sampling distribution of

Y E (Y )
var(Y )

1/2/3-45

Summary: The Sampling Distribution of Y

For Y1,,Yn i.i.d. with 0 < Y2 < ,
The exact (finite sample) sampling distribution of Y has
mean Y (Y is an unbiased estimator of Y) and variance

Y2 /n
Other than its mean and variance, the exact distribution of
Y is complicated and depends on the distribution of Y (the
population distribution)
When n is large, the sampling distribution simplifies:
p

o Y Y (Law of large numbers)

Y E (Y )
o
is approximately N(0,1) (CLT)
var(Y )
1/2/3-46

(b) Why Use Y To Estimate Y?

Y is unbiased: E(Y ) = Y
p

Y is consistent: Y Y
Y is the least squares estimator of Y; Y solves,
n

min m (Yi m ) 2
i 1

so, Y minimizes the sum of squared residuals

optional derivation (also see App. 3.2)
n
n
d n
d
2
2
(Yi m ) =
(Yi m ) = 2 (Yi m )

dm i 1
i 1 dm
i 1

Set derivative to zero and denote optimal value of m by m:

n
n
1 n
Y = m = nm or m = Yi = Y

n i 1
i 1
i 1
1/2/3-47

Why Use Y To Estimate Y, ctd.

Y has a smaller variance than all other linear unbiased
1 n
estimators: consider the estimator, Y aiYi , where
n i 1
{ai} are such that Y is unbiased; then var(Y ) var( Y )
(proof: SW, Ch. 17)
Y isnt the only estimator of Y can you think of a time
you might want to use the median instead?

1/2/3-48

1.
2.
3.
4.

The probability framework for statistical inference

Estimation
Hypothesis Testing
Confidence intervals

Hypothesis Testing
The hypothesis testing problem (for the mean): make a
provisional decision, based on the evidence at hand, whether
a null hypothesis is true, or instead that some alternative
hypothesis is true. That is, test
H0: E(Y) = Y,0 vs. H1: E(Y) > Y,0 (1-sided, >)
H0: E(Y) = Y,0 vs. H1: E(Y) < Y,0 (1-sided, <)
H0: E(Y) = Y,0 vs. H1: E(Y) Y,0

(2-sided)
1/2/3-49

Some terminology for testing statistical hypotheses:

p-value = probability of drawing a statistic (e.g. Y ) at least as
adverse to the null as the value actually computed with your
data, assuming that the null hypothesis is true.
The significance level of a test is a pre-specified probability
of incorrectly rejecting the null, when the null is true.
Calculating the p-value based on Y :
act
Pr
[|
Y

|
Y
Y ,0 |]
p-value = H 0
Y ,0

where Y act is the value of Y actually observed (nonrandom)

1/2/3-50

Calculating the p-value, ctd.

To compute the p-value, you need the to know the
sampling distribution of Y , which is complicated if n is
small.
If n is large, you can use the normal approximation (CLT):
act
Pr
[|
Y

|
Y
Y ,0 |],
p-value = H 0
Y ,0

= PrH 0 [|

Y Y ,0

Y / n

||

Y act Y ,0

Y / n

|]

Y Y ,0 Y act Y ,0
||
|]
= PrH 0 [|
Y
Y
probability under left+right N(0,1) tails
where Y = std. dev. of the distribution of Y = Y/ n .
1/2/3-51

Calculating the p-value with Y known:

For large n, p-value = the probability that a N(0,1) random

variable falls outside |(Y act Y,0)/ Y |
In practice, Y is unknown it must be estimated
1/2/3-52

Estimator of the variance of Y:

n
1
2
(
Y

Y
)
sY2 =
= sample variance of Y

i
n 1 i 1

Fact:
p

If (Y1,,Yn) are i.i.d. and E(Y4) < , then sY2 Y2

Why does the law of large numbers apply?
Because sY2 is a sample average; see Appendix 3.3
Technical note: we assume E(Y4) < because here the
average is not of Yi, but of its square; see App. 3.3

1/2/3-53

Computing the p-value with Y2 estimated:

act
p-value = PrH 0 [| Y Y ,0 || Y Y ,0 |],

= PrH 0 [|
PrH 0 [|

Y Y ,0

Y / n

Y Y ,0
sY / n

||
||

Y act Y ,0

Y / n

Y act Y ,0
sY / n

|]
|] (large n)

so
act
Pr
[|
t
|

|
t
|]
p-value = H 0

( Y estimated)

probability under normal tails outside |tact|

where t =

Y Y ,0
sY / n

(the usual t-statistic)

1/2/3-54

What is the link between the p-value and the significance

level?
The significance level is prespecified. For example, if the
prespecified significance level is 5%,
you reject the null hypothesis if |t| 1.96
equivalently, you reject if p 0.05.
The p-value is sometimes called the marginal
significance level.
Often, it is better to communicate the p-value than simply
whether a test rejects or not the p-value contains more
information than the yes/no statement about whether the
test rejects.
1/2/3-55

At this point, you might be wondering,...

What happened to the t-table and the degrees of freedom?
Digression: the Student t distribution
If Yi, i = 1,, n is i.i.d. N(Y, Y2 ), then the t-statistic has the
Student t-distribution with n 1 degrees of freedom.
The critical values of the Student t-distribution is tabulated in
the back of all statistics books. Remember the recipe?
1. Compute the t-statistic
2. Compute the degrees of freedom, which is n 1
3. Look up the 5% critical value
4. If the t-statistic exceeds (in absolute value) this
critical value, reject the null hypothesis.
1/2/3-56

Comments on this recipe and the Student t-distribution

1.
The theory of the t-distribution was one of the early
triumphs of mathematical statistics. It is astounding, really:
if Y is i.i.d. normal, then you can know the exact, finitesample distribution of the t-statistic it is the Student t. So,
you can construct confidence intervals (using the Student t
critical value) that have exactly the right coverage rate, no
matter what the sample size. This result was really useful in
times when computer was a job title, data collection was
expensive, and the number of observations was perhaps a
dozen. It is also a conceptually beautiful result, and the
math is beautiful too which is probably why stats profs
love to teach the t-distribution. But.
1/2/3-57

Comments on Student t distribution, ctd.

2.
If the sample size is moderate (several dozen) or large
(hundreds or more), the difference between the tdistribution and N(0,1) critical values are negligible. Here
are some 5% critical values for 2-sided tests:
degrees of freedom
(n 1)
10
20
30
60

5% t-distribution
critical value
2.23
2.09
2.04
2.00
1.96
1/2/3-58

Comments on Student t distribution, ctd.

3.
So, the Student-t distribution is only relevant when the
sample size is very small; but in that case, for it to be
correct, you must be sure that the population distribution of
Y is normal. In economic data, the normality assumption is
rarely credible. Here are the distributions of some
economic data.
Do you think earnings are normally distributed?

Suppose you have a sample of n = 10 observations

from one of these distributions would you feel
comfortable using the Student t distribution?

1/2/3-59

1/2/3-60

Comments on Student t distribution, ctd.

4. You might not know this. Consider the t-statistic testing
the hypothesis that two means (groups s, l) are equal:
Ys Yl
Ys Yl
t 2 2
ss
SE (Ys Yl )
sl
ns

nl

Even if the population distribution of Y in the two groups

is normal, this statistic doesnt have a Student t
distribution!
There is a statistic testing this hypothesis that has a
normal distribution, the pooled variance t-statistic see
SW (Section 3.6) however the pooled variance t-statistic
is only valid if the variances of the normal distributions
are the same in the two groups. Would you expect this to
be true, say, for mens v. womens wages?
1/2/3-61

The Student-t distribution summary

The assumption that Y is distributed N(Y, Y2 ) is rarely
plausible in practice (income? number of children?)
For n > 30, the t-distribution and N(0,1) are very close (as
n grows large, the tn1 distribution converges to N(0,1))
The t-distribution is an artifact from days when sample
sizes were small and computers were people
For historical reasons, statistical software typically uses
the t-distribution to compute p-values but this is
irrelevant when the sample size is moderate or large.
For these reasons, in this class we will focus on the largen approximation given by the CLT
1/2/3-62

1.
2.
3.
4.

The probability framework for statistical inference

Estimation
Testing
Confidence intervals

Confidence Intervals
A 95% confidence interval for Y is an interval that contains
the true value of Y in 95% of repeated samples.
Digression: What is random here? The values of Y1,,Yn and
thus any functions of them including the confidence
interval. The confidence interval it will differ from one
sample to the next. The population parameter, Y, is not
random, we just dont know it.
1/2/3-63

Confidence intervals, ctd.

A 95% confidence interval can always be constructed as the
set of values of Y not rejected by a hypothesis test with a 5%
significance level.
Y Y
Y Y
{ Y:
1.96} = {Y: 1.96
1.96}
sY / n
sY / n
sY
sY
= {Y: 1.96
Y Y 1.96
}
n
n
sY
sY
= {Y (Y 1.96
, Y + 1.96
)}
n
n
This confidence interval relies on the large-n results that Y is
p

approximately normally distributed and sY2 Y2 .

1/2/3-64

Summary:
From the two assumptions of:
(1) simple random sampling of a population, that is,
{Yi, i =1,,n} are i.i.d.
(2) 0 < E(Y4) <
we developed, for large samples (large n):
Theory of estimation (sampling distribution of Y )
Theory of hypothesis testing (large-n distribution of tstatistic and computation of the p-value)
Theory of confidence intervals (constructed by inverting
test statistic)
Are assumptions (1) & (2) plausible in practice? Yes

1/2/3-65

Lets go back to the original policy question:

What is the effect on test scores of reducing STR by one
student/class?
Have we answered this question?

1/2/3-66