The Grand Experiment Water supplied to households by competing private companies Sometimes different companies supplied households in same street In south London two main companies: –Lambeth Company (water supply from Thames Ditton, 22 miles upstream) –Southwark and Vauxhall Company (water supply from Thames)
In 1853/54 cholera outbreak Death Rates per 10000 people by water company –Lambeth10 –Southwark and Vauxhall150 Might be water but perhaps other factors Snow compared death rates in 1849 epidemic –Lambeth150 –Southwark and Vauxhall125 In 1852 Lambeth Company had changed supply from Hungerford Bridge
What would be good estimate of effect of clean water? 18491853/54Difference Lambeth15010-140 Vauxhall and Southwark 12515025 Difference-25140-165
This is basic idea of Differences-in-Differences Have already seen idea of using differences to estimate causal effects –Treatment/control groups in experimental data Often would like to find treatment and control group who can be assumed to be similar in every way except receipt of treatment This may be very difficult to do
A Weaker Assumption is.. Assume that, in absence of treatment, difference between treatment and control group is constant over time With this assumption can use observations on treatment and control group pre- and post- treatment to estimate causal effect Idea –Difference pre-treatment is normal difference –Difference pre-treatment is normal difference + causal effect –Difference-in-difference is causal effect
A Graphical Representation y Time Treatment Control Pre-Post- A B C
What is D-in-D estimate? Standard differences estimator is AB But normal difference estimated as CB Hence D-in-D estimate is AC Note: assumes trends in outcome variables the same for treatment and control groups This is not testable with two periods can get no idea of plausibility but can with more periods
Some Notation Define: μ it =E(y it ) Where i=0 is control group, i=1 is treatment Where t=0 is pre-period, t=1 is post-period Standard differences estimate of causal effect is estimate of: μ 11 -μ 01 Differences-in-Differences estimate of causal effect is estimate of: (μ 11 -μ 01 )-(μ 10 -μ 00 )
How to estimate? Can write D-in-D estimate as: (μ 11 -μ 10 )-(μ 01 -μ 00 ) This is simply the difference in the change of treatment and control groups so can estimate as:
This is simply differences estimator applied to the difference To implement this need to have repeat observations on the same individuals May not have this – individuals observed pre- and post-treatment may be different What can we do in this case?
In this case can estimate…. D-in-D estimate is estimate of β 3 – why is this?
A Comparison of the Two Methods Where have repeated observations could use both methods Will give same parameter estimates But will give different standard errors levels version will assume residuals are independent – unlikely to be a good assumption Can deal with this by: –Clustering –Or estimating differences version
Other Regressors Can put in other regressors as before Perhaps should think about way in which they enter the estimating equation E.g. if level of W affects level of y then should include ΔW in differences version
Differential Trends in Treatment and Control Groups Key assumption underlying validity of D-in- D estimate is that differences between treatment and control group would have remained constant in absence of treatment Can never test this With only two periods can get no idea of plausibility But can with more than two periods
An Example: Vertical Relationships and Competition in Retail Gasoline Markets, by Justine Hastings, American Economic Review, 2004 Interested in effect of vertical integration on retail petrol prices Investigates take-over in CA of independent Thrifty chain of petrol stations by ARCO (more integrated) Defines treatment group as petrol stations which had a Thrifty within 1 mile Control group those that did not Lots of reasons why these groups might be different so D-in-D approach seems a good idea
This picture contains relevant information… Can see D-in-D estimate of +5c per gallon Also can see trends before and after change very similar – D-in-D assumption valid
A Case which does not look so good…..Ashenfelters Dip Interested in effect of government- sponsored training (MDTA) on earnings Treatment group are those who received training in 1964 Control group are random sample of population as a whole
Things to Note.. Earnings for trainees very low in 1964 as training not working in that year – should ignore this year Simple D-in-D approach would compare earnings in 1965 with 1963 But earnings of trainees in 1963 seem to show a dip – so D-in-D assumption probably not valid Probably because those who enter training are those who had a bad shock (e.g. job loss)
Differences-in-Differences: Summary A very useful and widespread approach Validity does depend on assumption that trends would have been the same in absence of treatment Can use other periods to see if this assumption is plausible or not Uses 2 observations on same individual – most rudimentary form of panel data
A Brief Introduction to Panel Data Panel Data has both time-series and cross- section dimension – N individuals over T periods Will restrict attention to balanced panels – same number of observations on each individuals Whole books written about but basics can be understood very simply and not very different from what we have seen before Asymptotics typically done on large N, small T Use y it to denote variable for individual i at time t
The Pooled Model Can simply ignore panel nature of data and estimate: y it =βx it +ε it This will be consistent if E(ε it |x it )=0 or plim(X ε/N)=0 But computed standard errors will only be consistent if errors uncorrelated across observations This is unlikely: –Correlation between residuals of same individual in different time periods –Correlation between residuals of different individuals in same time period (aggregate shocks)
A More Plausible Model Should recognise this as model with group- level dummies or residuals Here, individual is a group
Three Models Fixed Effects Model –Treats θ i as parameter to be estimated (like β) –Consistency does not require anything about correlation with x it Random Effects Model –Treats θ i as part of residual (like θ) –Consistency does require no correlation between θ i and x it Between-Groups Model –Runs regression on averages for each individual
Proposition 5.2 The fixed effect estimator of β will be consistent if: a.E(ε it |x it )=0 b.Rank(X,D)=N+K Proof: Simple application of what you should know about linear regression model
Intuition First condition should be obvious – regressors uncorrelated with residuals Second condition requires regressors to be of full rank Main way in which this is likely to fail in fixed effects model is if some regressors vary only across individuals and not over time Such a variable perfectly multicollinear with individual fixed effect
Estimating the Fixed Effects Model Can estimate by brute force - include separate dummy variable for every individual – but may be a lot of them Can also estimate in mean-deviation form:
How does de-meaning work? Can do simple OLS on de-meaned variables STATA command is like:. xtreg y x, fe i(id)
Problems with fixed effect estimator Only uses variation within individuals – sometimes called within-group estimator This variation may be small part of total (so low precision) and more prone to measurement error (so more attenuation bias) Cannot use it to estimate effect of regressor that is constant for an individual
Random Effects Estimator Treats θ i as part of residual (like θ) Consistency does require no correlation between θ i and x it Should recognise as like model with clustered standard errors But random effects estimator is feasible GLS estimator
More on RE Estimator Will not describe how we compute Ω-hat – see Wooldridge STATA command.xtreg y x, re i(id)
Proposition 5.3 The random effects estimator of β will be consistent if: a.E(ε it |x i1,..x it,.. x iT )=0 b.E(θ i |x i1,..x it,.. x iT )=0 c.Rank(XΩ -1 X)=k Proof: RE estimator a special case of the feasible GLS estimator so conditions for consistency are the same. Error has two components so need a. and b.
Comments Assumption about exogeneity of errors is stronger than for FE model – need to assume ε it uncorrelated with whole history of x – this is called strong exogeneity Assumption about rank condition weaker than for FE model e.g. can estimate effect variables that are constant for a given individual
Another reason why may prefer RE to FE model If exogeneity assumptions are satisfied RE estimate will be more efficient than FE estimator Application of general principle that imposing true restriction on data leads to efficiency gain.
Another Useful Result Can show that RE estimator can be thought of as an OLS regression of: On: Where: This is sometimes called quasi-time demeaning See Wooldridge (ch10, pp286-7) if want to know more
Between-Groups Estimator This takes individual means and estimates the regression by OLS: Stata command is xtreg y x, be i(id) Condition for consistency the same as for RE estimator But BE estimator less efficient as does not exploit variation in regressors for a given individual And cannot estimate variables like time trends whose average values do not vary across individuals So why would anyone ever use it – lets think about measurement error
Measurement Error in Panel Data Models Assume true model is: Where x is one-dimensional Assume E(ε it |x i1,..x it,.. x iT )=0 and E(θ i |x i1,..x it,.. x iT )=0 so that RE and BE estimators are consistent
Measurement Error Model Assume: where u it is classical measurement error, x* i is average value of x* for individual i and η it is variation around the true value which is assumed to be uncorrelated with and u it and iid. We know this measurement error is likely to cause attenuation bias but this will vary between FE, RE and BE estimators.
Proposition 5.4 For FE model we have: For BE model we have: For RE model we have: Where:
What should we learn from this? All rather complicated – dont worry too much about details But intuition is simple Attenuation bias largest for FE estimator – Var(x*) does not appear in denominator – FE estimator does not use this variation in data
Attenuation bias larger for RE than BE estimator as T>1>κ The averaging in the BE estimator reduces the importance of measurement error. Important to note that these results are dependent on the particular assumption about the measurement error process and the nature of the variation in x it – things would be very different if measurement error for a given individual did not vary over time But general point is the measurement error considerations could affect choice of model to estimate with panel data
Time Effects Have treated time and individual dimensions asymmetrically – no good reason for this Errors likely to be correlated for different individuals in same time period – most common way to deal with this is to include set of time dummies:
Estimating Fixed Effects Model in Differences Can also get rid of fixed effect by differencing:
Comparison of two methods Estimate parameters by OLS on differenced data If only 2 observations then get same estimates as de-meaning method But standard errors different Why?: assumption about autocorrelation in residuals
What Are these assumptions? For de-meaned model: For differenced model: These are not consistent:
This leads to time series… Which is better depends on which assumption is right – how can we decide this? We are not going to cover this in this course.