ECON W3412: Introduction to Econometrics

Chapter 12. Instrumental Variables Regression

(Part II)

Simon Lee

Department of Economics
Columbia University

Spring 2018

1 / 14
Outline

The General IV Regression Model

TSLS with a Single Endogenous Regressor

Checking Instrument Validity

2 / 14
The General IV Regression Model I

I So far we have considered IV regression with a single

endogenous regressor (X ) and a single instrument (Z ).
I We need to extend this to:
I multiple endogenous regressors (X1 , . . . , Xk ).
I multiple included exogenous variables (W1 , . . . , Wr ) or control
variables, which need to be included for the usual OV reason.
I multiple instrumental variables (Z1 , . . . , Zm ). More (relevant)
instruments can produce a smaller variance of TSLS: the R 2 of
the first stage increases, so you have more variation in X̂ .

3 / 14
The General IV Regression Model II

I In general, a parameter is said to be identified if di↵erent

values of the parameter produce di↵erent distributions of the
data.
I In IV regression, whether the coefficients are identified
depends on the relation between the number of instruments
(m) and the number of endogenous regressors (k).
I Intuitively, if there are fewer instruments than endogenous
regressors, we can’t estimate 1 , . . . , k .

4 / 14
The General IV Regression Model III

I The coefficients 1, . . . , k are said to be:

I exactly identified if m = k.
There are just enough instruments to estimate 1 , . . . , k .
I overidentified if m > k.
There are more than enough instruments to estimate
1 , . . . , k . If so, you can test whether the instruments are
valid (a test of the “overidentifying restrictions”) – we’ll return
to this later.
I underidentified if m < k.
There are too few instruments to estimate 1 , . . . , k . If so,
you need to get more instruments!

5 / 14
Outline

The General IV Regression Model

TSLS with a Single Endogenous Regressor

Checking Instrument Validity

6 / 14
TSLS with a Single Endogenous Regressor I

I Consider

Yi = 0+ 1 X1i + 2 W1i + . . . + 1 + r Wri + ui , i = 1, . . . , n.

I m instruments: Z1i , . . . , Zmi

I First stage
I Regress X1 on all the exogenous regressors: regress X1 on
W1 , . . . , Wr , Z1 , . . . , Zm , and an intercept, by OLS
I Compute predicted values X̂1i , i = 1, . . . , n
I Second stage
I Regress Y on X̂1 , W1 , . . . , Wr , and an intercept, by OLS
I The coefficients from this second stage regression are the
TSLS estimators, but SEs are wrong
I To get correct SEs, do this in a single step in your regression
software

7 / 14
TSLS with a Single Endogenous Regressor II

I Required Assumptions
I Instrument exogeneity: corr(Z1i , ui ) = 0, . . . , corr(Zmi , ui ) = 0.
I With one endogenous regressor X1i , the instrument relevance
condition is that (a) at least one instrument must enter the
population counterpart of the first stage regression, and (b)
the W ’s are not perfectly multicollinear.

8 / 14
Example: Demand for cigarettes, ctd.
Suppose income is exogenous (this is plausible – why?), and
we also want to estimate the income elasticity:

ln(Qicigarettes ) = b0 + b1ln( Pi cigarettes ) + b2ln(Incomei) + ui

We actually have two instruments:

Z1i = general sales taxi
Z2i = cigarette-specific taxi
• Endogenous variable: ln( Pi cigarettes ) (“one X”)
• Included exogenous variable: ln(Incomei) (“one W”)
• Instruments (excluded endogenous variables): general sales
tax, cigarette-specific tax (“two Zs”)
• Is b1 over–, under–, or exactly identified?
SW Ch. 12 12/30
 Example: Cigarette demand, one instrument
IV: rtaxso = real overall sales tax in state
Y W X Z
. ivreg lpackpc lperinc (lravgprs = rtaxso) if year==1995, r;

IV (2SLS) regression with robust standard errors Number of obs = 48

F( 2, 45) = 8.19
Prob > F = 0.0009
R-squared = 0.4189
Root MSE = .18957

------------------------------------------------------------------------------
| Robust
lpackpc | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
lravgprs | -1.143375 .3723025 -3.07 0.004 -1.893231 -.3935191
lperinc | .214515 .3117467 0.69 0.495 -.413375 .842405
_cons | 9.430658 1.259392 7.49 0.000 6.894112 11.9672
------------------------------------------------------------------------------
Instrumented: lravgprs
Instruments: lperinc rtaxso STATA lists ALL the exogenous regressors
as instruments – slightly different
terminology than we have been using S
------------------------------------------------------------------------------
• Running IV as a single command yields the correct SEs
• Use , r for heteroskedasticity-robust SEs
SW Ch. 12 13/30
 Example: Cigarette demand, two instruments
Y W X Z1 Z2
. ivreg lpackpc lperinc (lravgprs = rtaxso rtax) if year==1995, r;

IV (2SLS) regression with robust standard errors Number of obs = 48

F( 2, 45) = 16.17
Prob > F = 0.0000
R-squared = 0.4294
Root MSE = .18786

------------------------------------------------------------------------------
| Robust
lpackpc | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
lravgprs | -1.277424 .2496099 -5.12 0.000 -1.780164 -.7746837
lperinc | .2804045 .2538894 1.10 0.275 -.230955 .7917641
_cons | 9.894955 .9592169 10.32 0.000 7.962993 11.82692
------------------------------------------------------------------------------
Instrumented: lravgprs
Instruments: lperinc rtaxso rtax STATA lists ALL the exogenous regressors
as “instruments” – slightly different
terminology than we have been using S
------------------------------------------------------------------------------

SW Ch. 12 14/30
TSLS estimates, Z = sales tax (m = 1)
! cigarettes !
ln(Qi ) = 9.43 – 1.14 ln(Pi cigarettes ) + 0.21ln(Incomei)
(1.26) (0.37) (0.31)

TSLS estimates, Z = sales tax & cig-only tax (m = 2)

! cigarettes !
ln(Qi ) = 9.89 – 1.28 ln(Pi cigarettes ) + 0.28ln(Incomei)
(0.96) (0.25) (0.25)

• Smaller SEs for m = 2. Using 2 instruments gives more

information – more “as-if random variation”.
• Low income elasticity (not a luxury good); income elasticity
not statistically significantly different from 0
• Surprisingly high price elasticity

SW Ch. 12 15/30
Outline

The General IV Regression Model

TSLS with a Single Endogenous Regressor

Checking Instrument Validity

9 / 14
Checking Instrument Validity I

I We will focus on a single included endogenous regressor:

Yi = 0+ 1 X1i + 2 W1i + . . . + 1 + r Wri + ui , i = 1, . . . , n.

I First stage regression:

Xi = ⇡0 +⇡1 Z1i +. . .+⇡m Zmi +⇡m+1 W1i +. . .+⇡m+k Wki +ui .

I The instruments are relevant if at least one of ⇡1 , . . . , ⇡m are

nonzero.
I The instruments are said to be weak if all the ⇡1 , . . . , ⇡m are
either zero or nearly zero.
I Weak instruments explain very little of the variation in X ,
beyond that explained by the W ’s.

10 / 14
Checking Instrument Validity II

I If instruments are weak, the sampling distribution of TSLS

and its t-statistic are not (at all) normal, even with n large.
I To measuring the strength of instruments in practice, consider
the first stage regression (one X ): Regress X on
Z1 , . . . , Z m , W 1 , . . . , W k .
I The first-stage F -statistic tests the hypothesis that
Z1 , . . . , Zm do not enter the first stage regression.
I Weak instruments imply a small first stage F -statistic.

11 / 14
 An example: the sampling distribution of the TSLS
t-statistic with weak instruments

Dark line = irrelevant instruments

Dashed light line = strong instruments
SW Ch. 12 16/30
Checking Instrument Validity III

I Rule-of-thumb: If the first stage F -statistic is less than 10,

then the set of instruments is weak.
I If so, the TSLS estimator will be biased, and statistical
inferences (standard errors, hypothesis tests, confidence
intervals) can be misleading.
I Comparing the first-stage F to 10 tests for whether the bias
of TSLS, relative to OLS, is less than 10%. If F is smaller
than 10, the relative bias exceeds 10% – that is, TSLS can
have substantial bias.
I What to do if you have weak instruments?

12 / 14
Checking Instrument Validity IV

I How to check instrument exogeneity?

I It is not testable if the model is exactly identified (e.g. one
endogenous regressor with one instrument).
I If there are more instruments than endogenous regressors, it is
possible to test – partially – for instrument exogeneity.

13 / 14
Checking Instrument Validity V

I Testing overidentifying restrictions

I Intuition is as follows.
I Consider the simplest case:

Yi = 0 + 1 Xi + ui

I Suppose there are two valid instruments: Z1i , Z2i .

I Then you could compute two separate TSLS estimates.
I Intuitively, if these 2 TSLS estimates are very di↵erent from
each other, then something must be wrong: one or the other
(or both) of the instruments must be invalid.
I The J-test of overidentifying restrictions makes this
comparison in a statistically precise way.
I This can only be done if #Z ’s > #X ’s (overidentified).

14 / 14
 Application to the Demand for Cigarettes
(SW Section 12.4)

Why are we interested in knowing the elasticity of demand

for cigarettes?
• Theory of optimal taxation. The optimal tax rate is
inversely related to the price elasticity: the greater the
elasticity, the less quantity is affected by a given
percentage tax, so the smaller is the change in
consumption and deadweight loss.
• Externalities of smoking – role for government
intervention to discourage smoking
o Health effects of second-hand smoke? (non-monetary)
o monetary externalities
SW Ch. 12 17/30
Panel data set
• Annual cigarette consumption, average prices paid by end
consumer (including tax), personal income, and tax rates
(cigarette-specific and general statewide sales tax rates)
• 48 continental US states, 1985-1995

Estimation strategy
• We need to use IV estimation methods to handle the
simultaneous causality bias that arises from the interaction
of supply and demand.
• State binary indicators = W variables (control variables)
which control for unobserved state-level characteristics
that affect the demand for cigarettes and the tax rate, as
long as those characteristics don’t vary over time.

SW Ch. 12 18/30
Fixed-effects model of cigarette demand
ln(Qitcigarettes ) = ai + b1ln( Pitcigarettes ) + b2ln(Incomeit) + uit

• i = 1,…,48, t = 1985, 1986,…,1995

• corr(ln( Pitcigarettes ),uit) is plausibly nonzero because of
supply/demand interactions
• ai reflects unobserved omitted factors that vary across
states but not over time, e.g. attitude towards smoking
• Estimation strategy:
o Use panel data regression methods to eliminate ai
o Use TSLS to handle simultaneous causality bias
o Use T = 2 with 1985 – 1995 changes (“changes”
method) – look at long-term response, not short-term
dynamics (short- v. long-run elasticities)
SW Ch. 12 19/30
The “changes” method (when T=2)
• One way to model long-term effects is to consider 10-year
changes, between 1985 and 1995
• Rewrite the regression in “changes” form:
ln(Qicigarettes
1995
) – ln( Q cigarettes
i1985
)
= b1[ln( Pi1995
cigarettes cigarettes
) – ln( Pi1985 )]
+b2[ln(Incomei1995) – ln(Incomei1985)]
+ (ui1995 – ui1985)
• Create “10-year change” variables, for example:
10-year change in log price = ln(Pi1995) – ln(Pi1985)
• Then estimate the demand elasticity by TSLS using 10-year
changes in the instrumental variables
• This is equivalent to using the original data and including
the state binary indicators (“W” variables) in the regression
SW Ch. 12 20/30
 STATA: Cigarette demand

First create “10-year change” variables

10-year change in log price
= ln(Pit) – ln(Pit–10) = ln(Pit/Pit–10)

. gen dlpackpc = log(packpc/packpc[_n-10]); _n-10 is the 10-yr lagged value

. gen dlavgprs = log(avgprs/avgprs[_n-10]);
. gen dlperinc = log(perinc/perinc[_n-10]);
. gen drtaxs = rtaxs-rtaxs[_n-10];
. gen drtax = rtax-rtax[_n-10];
. gen drtaxso = rtaxso-rtaxso[_n-10];

SW Ch. 12 21/30
 Use TSLS to estimate the demand elasticity by using the
“10-year changes” specification
Y W X Z
. ivregress 2sls dlpackpc dlperinc (dlavgprs = drtaxso) , r;

IV (2SLS) regression with robust standard errors Number of obs = 48

F( 2, 45) = 12.31
Prob > F = 0.0001
R-squared = 0.5499
Root MSE = .09092

------------------------------------------------------------------------------
| Robust
dlpackpc | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
dlavgprs | -.9380143 .2075022 -4.52 0.000 -1.355945 -.5200834
dlperinc | .5259693 .3394942 1.55 0.128 -.1578071 1.209746
_cons | .2085492 .1302294 1.60 0.116 -.0537463 .4708446
------------------------------------------------------------------------------
Instrumented: dlavgprs
Instruments: dlperinc drtaxso
------------------------------------------------------------------------------
NOTE:
- All the variables – Y, X, W, and Z’s – are in 10-year changes
- Estimated elasticity = –.94 (SE = .21) – surprisingly elastic!
- Income elasticity small, not statistically different from zero
- Must check whether the instrument is relevant…
SW Ch. 12 22/30
 Check instrument relevance: compute first-stage F
. reg dlavgprs drtaxso dlperinc;

Source | SS df MS Number of obs = 48

-------------+------------------------------ F( 2, 45) = 23.86
Model | .191437213 2 .095718606 Prob > F = 0.0000
Residual | .180549989 45 .004012222 R-squared = 0.5146
-------------+------------------------------ Adj R-squared = 0.4931
Total | .371987202 47 .007914621 Root MSE = .06334
------------------------------------------------------------------------------
dlavgprs | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
drtaxso | .0254611 .0037374 6.81 0.000 .0179337 .0329885
dlperinc | -.2241037 .2119405 -1.06 0.296 -.6509738 .2027664
_cons | .5321948 .031249 17.03 0.000 .4692561 .5951334
------------------------------------------------------------------------------

. test drtaxso;
( 1) drtaxso = 0 We didn’t need to run “test” here!
With m=1 instrument, the F-stat is
F( 1, 45) = 46.41 the square of the t-stat:
Prob > F = 0.0000 6.81*6.81 = 46.41

First stage F = 46.5 > 10 so instrument is not weak

Can we check instrument exogeneity? No: m = k
SW Ch. 12 23/30
 Cigarette demand, 10 year changes – 2 IVs
Y W X Z1 Z2
. ivregress 2sls dlpackpc dlperinc (dlavgprs = drtaxso drtax) , vce(r);

Instrumental variables (2SLS) regression Number of obs = 48

Wald chi2(2) = 45.44
Prob > chi2 = 0.0000
R-squared = 0.5466
Root MSE = .08836

------------------------------------------------------------------------------
| Robust
dlpackpc | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
dlavgprs | -1.202403 .1906896 -6.31 0.000 -1.576148 -.8286588
dlperinc | .4620299 .2995177 1.54 0.123 -.1250139 1.049074
_cons | .3665388 .1180414 3.11 0.002 .1351819 .5978957
------------------------------------------------------------------------------
Instrumented: dlavgprs
Instruments: dlperinc drtaxso drtax
------------------------------------------------------------------------------

drtaxso = general sales tax only

drtax = cigarette-specific tax only
Estimated elasticity is -1.2, even more elastic than using general
sales tax only!

SW Ch. 12 24/30
 First-stage F – both instruments
X Z1 Z2 W
. reg dlavgprs drtaxso drtax dlperinc ;

Source | SS df MS Number of obs = 48

-------------+------------------------------ F( 3, 44) = 51.36
Model | .289359873 3 .096453291 Prob > F = 0.0000
Residual | .082627329 44 .001877894 R-squared = 0.7779
-------------+------------------------------ Adj R-squared = 0.7627
Total | .371987202 47 .007914621 Root MSE = .04333

------------------------------------------------------------------------------
dlavgprs | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
drtaxso | .013457 .0030498 4.41 0.000 .0073106 .0196033
drtax | .0075734 .0010488 7.22 0.000 .0054597 .009687
dlperinc | -.0289943 .1474923 -0.20 0.845 -.3262455 .2682568
_cons | .4919733 .0220923 22.27 0.000 .4474492 .5364973
------------------------------------------------------------------------------

. test drtaxso drtax;

( 1) drtaxso = 0
( 2) drtax = 0
F( 2, 44) = 75.65 75.65 > 10 so instruments aren’t weak
Prob > F = 0.0000
With m>k, we can test the overidentifying restrictions…
SW Ch. 12 25/30
 Test the overidentifying restrictions
. predict e, resid; Computes predicted values for most recently
estimated regression (the previous TSLS regression)
. reg e drtaxso drtax dlperinc; Regress e on Z’s and W’s

Source | SS df MS Number of obs = 48

-------------+------------------------------ F( 3, 44) = 1.64
Model | .037769176 3 .012589725 Prob > F = 0.1929
Residual | .336952289 44 .007658007 R-squared = 0.1008
-------------+------------------------------ Adj R-squared = 0.0395
Total | .374721465 47 .007972797 Root MSE = .08751

------------------------------------------------------------------------------
e | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
drtaxso | .0127669 .0061587 2.07 0.044 .000355 .0251789
drtax | -.0038077 .0021179 -1.80 0.079 -.008076 .0004607
dlperinc | -.0934062 .2978459 -0.31 0.755 -.6936752 .5068627
_cons | .002939 .0446131 0.07 0.948 -.0869728 .0928509
------------------------------------------------------------------------------
. test drtaxso drtax;
( 1) drtaxso = 0 Compute J-statistic, which is m*F,
( 2) drtax = 0 where F tests whether coefficients on
the instruments are zero
F( 2, 44) = 2.47 so J = 2 ´ 2.47 = 4.93
Prob > F = 0.0966 ** WARNING – this uses the wrong d.f. **

SW Ch. 12 26/30
 The correct degrees of freedom for the J-statistic is m–k:
• J = mF, where F = the F-statistic testing the coefficients on
Z1i,…,Zmi in a regression of the TSLS residuals against
Z1i,…,Zmi, W1i,…,Wmi.
• Under the null hypothesis that all the instruments are
exogeneous, J has a chi-squared distribution with m–k
degrees of freedom
• Here, J = 4.93, distributed chi-squared with d.f. = 1; the 5%
critical value is 3.84, so reject at 5% sig. level.
• In STATA:
. dis "J-stat = " r(df)*r(F) " p-value = " chiprob(r(df)-1,r(df)*r(F));
J-stat = 4.9319853 p-value = .02636401

J = 2 × 2.47 = 4.93 p-value from chi-squared(1) distribution

Now what???

SW Ch. 12 27/30
Tabular summary of these results:

SW Ch. 12 28/30
How should we interpret the J-test rejection?
• J-test rejects the null hypothesis that both the instruments
are exogenous
• This means that either rtaxso is endogenous, or rtax is
endogenous, or both!
• The J-test doesn’t tell us which!! You must exercise
judgment…
• Why might rtax (cig-only tax) be endogenous?
o Political forces: history of smoking or lots of smokers
political pressure for low cigarette taxes
o If so, cig-only tax is endogenous
• This reasoning doesn’t apply to general sales tax
• ⇒ use just one instrument, the general sales tax

SW Ch. 12 29/30
 The Demand for Cigarettes:
Summary of Empirical Results

• Use the estimated elasticity based on TSLS with the general

sales tax as the only instrument:
Elasticity = -.94, SE = .21
• This elasticity is surprisingly large (not inelastic) – a 1%
increase in prices reduces cigarette sales by nearly 1%.
This is much more elastic than conventional wisdom in the
health economics literature.
• This is a long-run (ten-year change) elasticity. What would
you expect a short-run (one-year change) elasticity to be –
more or less elastic?

SW Ch. 12 30/30