COUNTERFACTUAL MAPPING AND INDIVIDUAL ... MAPPING AND INDIVIDUAL TREATMENT EFFECTS IN NONSEPARABLE MODELS WITH BINARY ENDOGENEITY* QUANG VUONG† AND HAIQING XU‡ ABSTRACT. This paper

COUNTERFACTUAL MAPPING AND INDIVIDUAL TREATMENT EFFECTSIN NONSEPARABLE MODELS WITH BINARY ENDOGENEITY*

QUANG VUONG† AND HAIQING XU‡

ABSTRACT. This paper establishes nonparametric identification of individual treatment

effects in a nonseparable model with a binary endogenous regressor. The outcome

variable may be continuous, discrete or a mixture of both, and the instrumental variable

can take binary values. We distinguish the cases where the model includes or does not

include a selection equation for the binary endogenous regressor. First, we establish

point identification of the structural function when it is continuous and strictly monotone

in the latent variable. The key to our results is the identification of a so-called “counter-

factual mapping” that links each outcome with its counterfactual. This then identifies

every individual treatment effect. Second, we characterize all the testable restrictions

imposed by the model with or without the selection equation. Lastly, we generalize our

identification results to the case where the outcome variable has a probability mass in its

distribution such as when the outcome variable is censored or binary.

Keywords: Nonparametric identification, nonseparable models, discrete endogenous

variable, counterfactual mapping, individual treatment effects

Date: Saturday 16th May, 2015.∗A previous version of this paper was circulated under the title “Identification of nonseparable modelswith a binary endogenous regressor”. We thank Jason Abrevaya, Federico Bugni, Karim Chalak, XiaohongChen, Victor Chernozhukov, Andrew Chesher, Denis Chetverikov, Xavier D’Haultfoeuille, StephenDonald, Jinyong Hahn, Shakeeb Khan, Brendan Kline, Qi Li, Robert Lieli, Matthew Masten, IsabellePerrigne, Geert Ridder, Xiaoxia Shi, Robin Sickles, Elie Tamer, Edward Vytlacil and Nese Yildiz foruseful comments. We also thanks seminar participants at Duke, Rice, NYU, UCLA, Princeton, Rochester,2013 Bilkent University Annual Summer Workshop, 23rd Annual Meeting of the Midwest EconometricsGroup, 2014 Cowles Summer Conference, 2014 Cemmap Conference, and the 6th French EconometricsConference.†(corresponding author) Department of Economics, New York University, 19 W. 4th Street, 6FL, NewYork, NY, 10012, [email protected].‡Department of Economics, University of Texas at Austin, Austin, TX, 78712, [email protected].

1

MAILTO:[email protected]

MAILTO:[email protected]

mailto:[email protected]

mailto:[email protected]

1. INTRODUCTION AND RELATED LITERATURE

The primary aim of this paper is to establish nonparametric identification of individ-

ual treatment effects in a nonseparable model with a binary endogenous regressor. We

focus on the case where the instrumental variable has limited variations, namely when

it takes only binary values. We introduce a counterfactual mapping, which links each

realized outcome with its counterfactual to identify individual treatment effects. As a

by–product, we also identify the structural function. The key idea is to exploit infor-

mation from the “complier group” in the presence of endogeneity following Imbens

and Angrist (1994). The identification results in the paper are related to the methods

in Chernozhukov and Hansen (2005), Athey and Imbens (2006), and Guerre, Perrigne,

and Vuong (2009). When the outcome variable has mass points in its distribution, our

approach also generalizes Vytlacil and Yildiz (2007) to the fully nonseparable case.

The secondary objective of this paper is to investigate the identification power as

well as the restrictions on observations provided by the selection equation, such as its

monotonicity. In particular, we derive an easily verifiable high level condition that is

sufficient for identification of the structural function and show that the monotonicity

of the selection equation is sufficient for such a condition. Moreover, we characterize

all the testable restrictions on observables imposed by the model with or without the

selection equation.

Nonparametric identification of nonseparable models has become central for under-

standing the source of identification power in structural models, especially in models

with discrete endogenous variables, see, e.g., Heckman, Smith, and Clements (1997),

Chesher (2005), Heckman and Vytlacil (2005) and the references therein. Theoretic mod-

els that admit structural relationships usually just provide qualitative properties, e.g.,

monotonicity between economic variables of interest (see e.g. Milgrom and Shannon,

1994; Athey, 2001, 2002; Reny, 2011). For the related empirical analysis, introducing

additional parametric restrictions on the functional form, especially on the form of

2

heterogeneity, without careful justifications may lead to spurious identification; see

Heckman and Robb (1986) and Imbens and Wooldridge (2009).

The literature on nonseparable models and treatment effects is vast, see e.g. Imbens

(2007), Imbens and Wooldridge (2009) for surveys. Our paper also considers the iden-

tification of the structural functions in nonseparable models with binary endogenous

regressors. Identification of such functions was studied in a setting with continuous

endogenous regressors; see Chesher (2003), Matzkin (2008), Imbens and Newey (2009),

D’Haultfœuille and Février (forthcoming), Torgovitsky (forthcoming), among others.

For the binary endogenous variable case, Chernozhukov and Hansen (2005), Chen,

Chernozhukov, Lee, and Newey (2014) and Chernozhukov and Hansen (2013) estab-

lish identification of the structural function without requiring a selection equation.

Further, Chesher (2005) establishes partial identification of the structural function at

some conditional quantile of the error term under local conditions on the instrumental

variable. Subsequently, Jun, Pinkse, and Xu (2011) tighten Chesher (2005)’s bounds by

strengthening Chesher’s local conditions to the full independence of the instrumental

variable.

The idea behind our identification strategy differs from the above literature. It is

based on identifying the counterfactual mapping that relates each individual outcome to

its counterfactual under the monotonicity of the outcome equation. This then identifies

the structural function. Similar to Imbens and Angrist (1994), we consider an exogenous

change in the instrumental variable, which affects the distribution of outcomes through

a subpopulation called the “complier” group. We can then identify the conditional prob-

ability distribution of the (potential) outcome for this subpopulation at each value of the

binary endogenous variable. From these two conditional distributions, we can identify

constructively the counterfactual mapping relating the quantiles of one distribution

to the other for the whole population. The idea of matching two quantile functions to

exploit limited variations of instrumental variables was introduced by Athey and Im-

bens (2006) in the context of policy intervention analysis with repeated cross–sectional

3

data in nonlinear difference–in–difference models. It was also used by Guerre, Perrigne,

and Vuong (2009) in the empirical auction literature with an endogenous number of

bidders, and exploited by D’Haultfœuille and Février (forthcoming) and Torgovitsky

(forthcoming) in a triangular model with continuous endogenous regressors.

Key among our identifying conditions is the (strict or weak) monotonicity of the

structural function, which comes from the nonseparable model literature. See e.g.

Matzkin (1999, 2003, 2008, 2015), Chesher (2003, 2005), Chernozhukov and Hansen (2005,

2013) and Chen, Chernozhukov, Lee, and Newey (2014). Without any monotonicity

restriction, Manski (1990) derives sharp bounds for the average treatment effect (ATE)

with and without instrumental variables. Using an instrumental variable and the weak

monotonicity assumption on the selection equation, Imbens and Angrist (1994) establish

point identification of the local average treatment effect (LATE). Alternatively, in a

similar setting, Heckman and Vytlacil (1999, 2005) develop the marginal treatment effect

(MTE) and establish its identification by using local variations in instrumental variables.

In this paper, we impose a strict/weak monotonicity assumption on the outcome

equation, which allows us to constructively identify the counterfactual mapping, as

well as the individual treatment effects.

In our setting, we allow the instrumental variable to take only binary values, a case

where identification at infinity obviously fails; see, e.g., Heckman (1990). When the

outcome variable is continuously distributed, we assume that the outcome equation is

strictly monotone in the error term. Under this assumption, our identification strategy

only requires a binary–valued instrumental variable. On the other hand, when the

outcome variable has a mass probability, the strict monotonicity condition is no longer

proper given that the error term is usually assumed to be continuously distributed. We

then replace the strict monotonicity by the weak monotonicity of the outcome equation.

As a consequence, our rank condition requires more variations in the instrumental

variable, though a finite support is still allowed, thereby generalizing Vytlacil and Yildiz

(2007)’s results from weakly to fully nonseparable models.

4

Our method is related to the instrumental variable approach developed in Cher-

nozhukov and Hansen (2005) and generalized by Chen, Chernozhukov, Lee, and Newey

(2014) and Chernozhukov and Hansen (2013). The instrumental variable approach does

not require a selection equation. Identification then relies on a full rank condition

of an equation system. In our setting, we exploit the identification power from the

monotonicity of some identified functions to deliver a weaker sufficient condition for

identification in a constructive way. Moreover, we characterize all the testable restric-

tions on observables imposed by the model with and without the selection equation,

thereby allowing researchers to assess the model from data.

The structure of the paper is organized as follows. We introduce our benchmark

model in Section 2 and we establish its identification in Section 3. We also discuss

partial identification when point identification fails. Section 4 extends our identification

argument to the case where there is no selection equation. Section 5 characterizes

the restrictions imposed on data by the model with or without the selection equation.

Section 6 generalizes our method to the case where the distribution of the outcome

variable has some mass points. Section 7 concludes.

2. THE BENCHMARK MODEL

We consider the nonseparable triangular system with a binary endogenous variable:

Y = h(D, X, ε), (1)

D = 1[m(X, Z)− η ≥ 0], (2)

where Y is the outcome variable, D ∈ {0, 1} is a binary endogenous variable, X ∈ RdX

is a vector of observed exogenous covariates and Z ∈ {z1, z2} is a binary instrumental

variable for the binary endogenous variable D.1 The error terms ε and η are assumed

1An early use of this triangular model is Heckman (1979) for sample selection in a parametric setting.Moreover, considering a binary valued instrument highlights the identification power of the instrumentalvariable. For the importance of having binary instruments in the treatment effects literature, see e.g.Imbens and Wooldridge (2009) for a detailed discussion.

5

to be scalar valued disturbances.2 The functions h and m are unknown structural

relationships, where h is the function of interest. For every x ∈ SX, we also define the

individual treatment effect (ITE) as the function

ITEx(ε) ≡ h(1, x, ε)− h(0, x, ε) (3)

where ε ∈ Sε.3 See e.g. Rubin (1974), and Heckman, Smith, and Clements (1997).

Following standard convention, we refer to (1) and (2) as the outcome equation and

the selection equation, respectively. Note that (2) covers the general setting where

D = g(X, Z, η) under additional standard assumptions. Specifically, suppose that

g is non–increasing and left–continuous in η. For each (x, z), let m(x, z) = inf{η ∈R : g(x, z, η) = 0}. It follows that g(x, z, η) = 1 {m(x, z)− η ≥ 0} for all (x, z). For a

detailed discussion, see e.g. Vytlacil (2002, 2006).

A running example of this model is the return to education (see e.g. Heckman, 1979;

Chesher, 2005): let Y, D and (X, Z) be ‘earnings’, ‘schooling’ and ‘demographics’, respec-

tively. Moreover, let ε be job related ability and η be education related talent. Intuitively,

these two latent variables should be correlated to each other, which accounts for the

endogeneity problem in the triangular system. The difference between demographics X

and Z is that Z affects the education level of an individual, but not the wage outcome.

For instance, Z could be some institutional features of the education system. Another

example arises when h(D, X, ·) is the equilibrium bidding strategy with risk averse

bidders, D indicates the level of competition (the number of bidders), X are characteris-

tics of the auctioned object and ε is bidder’s private value, see e.g. Guerre, Perrigne,

and Vuong (2000, 2009). This example is especially relevant as strict monotonicity and

nonseparability in the scalar private value ε arises from auction theory.

2Note that η being scalar is not essential and can be relaxed by the monotonicity assumption in Imbensand Angrist (1994). When ε ∈ Rk with k ≥ 2, there always exists a (known) bijection from Rk to R thatdepends on neither d nor x. In the nonseparable model context, multidimensional errors have also beenconsidered by Hoderlein and Mammen (2007) and Kasy (2014).3For a generic random variable W, we use SW to denote the support of W.

6

In the benchmark model, we make the following assumptions.

Assumption A. Equation (1) holds where (i) h is continuous and strictly increasing in ε, with

ε distributed as U[0, 1], and (ii) (X, Z) is independent of ε.

Assumption B. Equation (2) holds where (i) Z is conditionally independent of η given (X, ε),

and (ii) conditional on X, the joint distribution of (ε, η) is absolutely continuous with respect to

Lebesgue measure.

In assumption A–(i), the continuity and strict monotonicity of h follow e.g. Matzkin

(1999, 2003), Chesher (2003) and Chernozhukov and Hansen (2005). This assumption

rules out mass points in the distribution of Y. In Section 6, we generalize our results

by allowing h to be flat inside the support of ε. The uniform distribution of ε on

[0, 1] is a normalization which is standard in the literature; see e.g. Chesher (2003)

and Chernozhukov and Hansen (2005).4 The essential restriction in assumption A-(i)

is the so–called rank preservation/invariance condition, see e.g. Heckman, Smith,

and Clements (1997), Chernozhukov and Hansen (2005) and Firpo (2007), among

others. For any given τ ∈ (0, 1), it requires that the relative rank/quantile of h(1, x, τ)

in the distribution of h(1, x, ε) be the same as that of h(0, x, τ) in the distribution of

h(0, x, ε). In Section 5, we characterize the model restrictions on observables imposed

by assumption A. These restrictions are weak but testable. If the error term is additive,

as is widely assumed, i.e., Y = h∗(D, X) + ε for some real valued function h∗, then

assumption A–(i) holds. Assumption A–(ii) is standard in the literature, see, e.g., Imbens

and Newey (2009).

To illustrate, here we provide two examples of the nonseparable structural function h

satisfying assumption of strict monotonicity. The first example seems to be new. The

second example was considered by Guerre, Perrigne, and Vuong (2009).

4Matzkin (2003) proposes an alternative normalization on the structural function h, instead of normalizingthe distribution of ε.

7

Example 1 (Additive Error with Generalized Heterogeneity). Let

Y = h∗(D, X) + σ(D, X) · ε

for some real valued function h∗, positive function σ > 0 and where ε has unit variance. In par-

ticular, the heterogeneity σ depends on the endogenous binary variable D. Thus, h(D, X, ε) =

h∗(D, X) + σ(D, X) · ε.

Example 2 (First–price Auction with Risk Aversion). Consider a first price auction with I

risk averse bidders within the private value paradigm. In a symmetric equilibrium, each bidder’s

equilibrium bid has the following form

Bi = h(I, X, εi), ∀ i = 1, · · · , I,

where Bi is bidder i’s equilibrium bid, I ∈ {I`, Ih} is the number of bidders which reflects the

level of competition, X is characteristics of the auctioned object, εi is the private value. In

particular, the bidding strategy h is strictly increasing in private information εi.

Moreover, assumption B specifies the selection equation. Assumption B–(i) together

with assumption A–(ii) is equivalent to ε⊥X and (ε, η)⊥Z|X.5 It is worth emphasizing

that we require the instrumental variable Z to be independent of (ε, η) (conditionally

on X), which is stronger than the local independence restriction imposed by Chesher

(2005). Moreover, it is worth noting that if the objects of interest are the individual

treatment effects (ITE) but not the structural function h, then the independence condition

in assumption A–(ii) can be relaxed to Z⊥ε|X. The latter combined with the conditional

independence in assumption B–(i) becomes equivalent to Z⊥(ε, η)|X. Under such a

weaker condition, Section 3 shows that we can still identify the counterfactual mapping

φx and hence the ITEs as our identification argument is conditional on X = x. In other

words, identification of the ITEs does not require exogeneity of X. Assumption B–(ii)

5This is because assumption A-(ii) is equivalent to ε⊥X and ε⊥Z|X. The latter condition and η⊥Z|(X, ε)in assumption B–(i) are equivalent to (ε, η)⊥Z|X.

8

on the joint distribution of (ε, η) is standard and weak. It rules out mass points in the

joint distribution of (ε, η).

Under assumption B, the function m is identified up to the distribution function

Fη|X(·|·), i.e., m(x, z) = F−1η|X(E(D|X = x, Z = z)|x) for all (x, z) ∈ SXZ, where F−1

η|X(·|x)is the quantile. Moreover, for any x ∈ SX and t ∈ R, we have by (ε, η)⊥Z|X,

P(h(1, x, ε) ≤ t; η ≤ m(x, z)|X = x) = P(Y ≤ t; D = 1|X = x, Z = z);

P(h(0, x, ε) ≤ t; η > m(x, z)|X = x) = P(Y ≤ t; D = 0|X = x, Z = z).

In contrast, neither P(h(1, x, ε) ≤ t; η > m(x, z)|X = x) nor P(h(0, x, ε) ≤ t; η ≤m(x, z)|X = x) is identified yet. Next, suppose there are z1, z2 ∈ SZ|X=x with p(x, z1) <

p(x, z2), where p(x, z) = E(D = 1|X = x, Z = z) denotes the propensity score. Then,

the conditional distribution Ph(d,x,ε)|X=x,m(x,z1)<η≤m(x,z2) can be identified as follows:

For d = 0, 1 and all t ∈ R,

P(h(d, x, ε) ≤ t|X = x; m(x, z1) < η ≤ m(x, z2)

)=

P[h(d, x, ε) ≤ t; m(x, z1) < η ≤ m(x, z2)|X = x

]P[m(x, z1) < η ≤ m(x, z2)|X = x

]=

P(Y ≤ t; D = d|X = x, Z = z2)−P(Y ≤ t; D = d|X = x, Z = z1)

P(D = d|X = x, Z = z2)−P(D = d|X = x, Z = z1). (4)

As a matter of fact, the above calculation follows Imbens and Angrist (1994) who derives

the conditional expectations given the complier group, i.e., {X = x, m(x, z1) < η ≤m(x, z2)}, while we consider the full conditional distributions. An expression similar to

(4) can also be found in Imbens and Rubin (1997) and Froelich and Melly (2013). We use

(4) for the identification analysis in the next section.

9

3. IDENTIFICATION

In this section, we develop a simple approach for the identification of individual

treatment effects as well as the structural function h under assumptions A and B. In par-

ticular, our method involves a weak rank condition that is straightforward to verify: For

any given x, the propensity score has a non–degenerate support, i.e., p(x, z1) 6= p(x, z2).

Under our rank condition, the identification at infinity arguments are obviously not

satisfied (see e.g. Chamberlain, 1986; Heckman, 1990). The proposed identification strat-

egy is constructive and derived under a binary variation of the instrumental variable,

which differs from e.g. Heckman (1990) and Chernozhukov and Hansen (2005).

The key to our identification strategy is to match h(1, x, ·) with h(0, x, ·) under weak

conditions, i.e. h(1, x, ·) = φx(h(0, x, ·)) on [0, 1], where the function φx can be identi-

fied in a constructive manner for every x ∈ SX. We call φx the counterfactual map-

ping because we can find the counterfactual outcome h(1, x, e) from h(0, x, e) using

φx for any e ∈ [0, 1]. Specifically, fix x ∈ SX. For each y ∈ Sh(0,x,ε), then we have

φx(y) ≡ h(1, x, h−1(0, x, y)

), where h−1(0, x, ·) is the inverse function of h(0, x, ·). Under

assumption A, the counterfactual mapping φx is well–defined, continuous and strictly

increasing from Sh(0,x,ε) onto Sh(1,x,ε). Thus, the ITE satisfies

ITEx(ε) = D(Y− φ−1x (Y)) + (1− D)(φx(Y)−Y), (5)

conditional on X = x, where φ−1x (·) denotes the inverse of φx(·). In particular, ITEx(·)

is identified as soon as φx(·) is. Moreover, given φx and any (d, x), we can also identify

h(d, x, ·) as the quantile function of Fh(d,x,ε) following e.g. Chesher (2003).

We first provide a lemma that shows that identification of φx(·) is sufficient for

identifying h(d, x, ·) under assumption A.

Lemma 1. Suppose assumption A holds. Then, for any x ∈ SX, h(0, x, ·) and h(1, x, ·) are

identified on [0, 1] if and only if φx(·) is identified on Sh(0,x,ε).

Proof. See Appendix A.1 �

10

Lemma 1 reduces the identification of h(1, x, ·) and h(0, x, ·) into the identification of

one function, namely, the counterfactual mapping φx(·). To see the if part, note that

conditional on X = x,

h(1, x, ε) = YD + φx(Y)(1− D), h(0, x, ε) = φ−1x (Y)D + Y(1− D). (6)

Thus, the identification of φx(·) provides the distributions of h(0, x, ε) and h(1, x, ε),

which further identify h(0, x, ·) and h(1, x, ·). Specifically, for d = 0, 1 we have h(d, x, e) =

F−1h(d,x,ε)(e) for every e ∈ (0, 1) by assumption A, respectively.

To identify the counterfactual mapping φx(·), we introduce a minimal rank condition,

namely, that the propensity score p(x, z) varies with z.

Assumption C (Rank Condition). For every x ∈ SX, Sp(X,Z)|X=x is not a singleton.

Given that Z is binary, assumption C is equivalent to SZ|X=x = {z1, z2} and p(x, z1) 6=p(x, z2) for all x ∈ SX. Under assumption C, we can identify the conditional distribution

of h(d, x, ε) given m(x, z1) < η ≤ m(x, z2) (and X = x) for d = 0, 1 by (4). Throughout,

we use Fh(d,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(·) to denote the conditional CDF of h(d, x, ε) given

X = x and m(x, z1) < η ≤ m(x, z2). Let Cdx be its support.

We have Cdx ⊆ SY|D=d,X=x.6 In the next assumption, we require that the complier

group be sufficiently large so that these two supports are equal.

Assumption D (Support Condition). We have Cdx = SY|D=d,X=x for d = 0, 1 and x ∈ SX.

By (4), assumption D is testable. Assumption D requires that, for any individual in the

population, there is an individual from the complier group who has the same outcome

and treatment status. Without assumption D, the structural function h(d, x, ·) is point

identified only on the support of ε given the complier group as we discussed later.

6Because Y = h(D, X, ε), this is equivalent to Sε|m(x,z1)<η≤m(x,z2),X=x ⊆ Sε|D=d,X=x. Consider d = 1.We have Sε|m(x,z1)<η≤m(x,z2),X=x = Sε|m(x,z1)<η≤m(x,z2),Z=z2,X=x by (ε, η)⊥Z|X. But {m(x, z1) < η ≤m(x, z2), Z = z2, X = x} ⊆ {η ≤ m(x, z2), Z = z2, X = x} = {D = 1, Z = z2, X = x} ⊆ {D = 1, X = x}.The proof is similar for d = 0.

11

Assumption D is equivalent to the support of ε for the complier group being equal to

that in the population, i.e. Sε|m(x,z1)<η≤m(x,z2),X=x = [0, 1].7 It is typically satisfied. For

instance, a sufficient condition for assumption D is that conditional on X, (ε, η) has a

rectangular support such as [0, 1]×R as often assumed for the triangular model (1)-(2).

For a generic random variable W, let QW be the quantile function of its distribution,

i.e. QW(τ) = inf {w ∈ R : P(W ≤ w) ≥ τ} for any τ ∈ [0, 1]. Further, for any

x, d and a generic subset A ⊆ Sη, let Qh(d,x,ε)|X=x,η∈A be the conditional quantile

function of h(d, x, ε) given X = x and η ∈ A, i.e. Qh(d,x,ε)|X=x,η∈A(τ) = inf {h ∈ R :

P [h(d, x, ε) ≤ h|X = x, η ∈ A] ≥ τ}.

Lemma 2. Suppose assumptions A to D hold. For every x ∈ SX, let z1, z2 ∈ SZ|X=x such

that p(x, z1) < p(x, z2). Then, Sh(0,x,ε) = SY|D=0,X=x and the counterfactual mapping φx(·)is identified: For any y0 ∈ Sh(0,x,ε),

φx(y0) = Qh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)

(Fh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(y0)

), (7)

where Qh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(·) and Fh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(·) are given by (4).


As a second object of interest, we also identify the individual treatment effects by (5).

It is worth emphasizing that Lemma 2 holds without the independence between X and

ε, as it holds pointwise in x. On the other hand, the requirement that the rank condition

and support condition hold for any x ∈ SX in assumptions C and D, respectively,

is useful to identify every individual treatment effect in the whole population by (5).

Moreover, using the counterfactual mapping φx(·) and (6), we can identify other policy

7From the previous footnote, assumption D is equivalent to Sε|m(x,z1)<η≤m(x,z2),X=x = Sε|D=d,X=x ford = 0, 1. Thus Sε|m(x,z1)<η≤m(x,z2),X=x = Sε|X=x, which is equal to [0, 1] by assumption A. Conversely, ifSε|m(x,z1)<η≤m(x,z2),X=x = [0, 1], then Sε|m(x,z1)<η≤m(x,z2),X=x = Sε|X=x. Therefore, the first inclusion inthe previous footnote implies Sε|m(x,z1)<η≤m(x,z2),X=x = Sε|D=d,X=x for d = 0, 1.

12

effects of interest, e.g.,

ATE ≡ E[h(1, X, ε)− h(0, X, ε)

]= E

{D[Y− φ−1

X (Y)]+ (1− D)

[φX(Y)−Y

]}ATT ≡ E

[h(1, X, ε)− h(0, X, ε)

∣∣D = 1]= E

[Y− φ−1

X (Y)∣∣D = 1

]QTEx(·) ≡ Qh(1,x,ε)(·)−Qh(0,x,ε)(·)

= QD·Y+(1−D)·φX(Y)|X(·|x)−Q(1−D)·Y+D·φ−1X (Y)|X(·|x).

where ATT and QTE respectively refer to the average treatment effect on the treated

and the quantile treatment effect, which have also been extensively discussed in the

literature; See e.g. Heckman and Vytlacil (2007) and Imbens and Wooldridge (2009).

In particular, if one imposes additivity on h, i.e. h(D, X, ε) = h∗(D, X) + ε, then

φx(y) = h∗(1, x)− h∗(0, x) + y. By Lemma 2, we can show that for any τ ∈ [0, 1],

h∗(1, x)− h∗(0, x)

= Qh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(τ)−Qh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(τ). (8)

Equation (8) is worth discussing. First, by integrating out τ, we obtain

h∗(1, x)− h∗(0, x) = E[h(1, x, ε)− h(0, x, ε)|X = x, m(x, z1) < η ≤ m(x, z2)]

=E(Y|X = x, Z = z2)−E(Y|X = x, Z = z1)

p(x, z2)− p(x, z1).

Note that the RHS has the same expression as the (conditional) LATE in Imbens and

Angrist (1994). This is not surprising, since there is no unobserved heterogeneity

in individual treatment effects as h(1, x, ε) − h(0, x, ε) = h∗(1, x) − h∗(0, x). Thus,

individual treatment effects are the same as (conditional) LATE or conditional ATE,

which is defined as E[h(1, X, ε) − h(0, X, ε)|X = x].8 Second, (8) is a useful model

restriction from the linear additivity, which suggests several ways of testing the additive

separability (in ε) of the structural function h. A natural testing idea is to test that the

8From such an intuition, equation (2) is not even needed for this simple expression of h∗(1, x)− h∗(0, x).

13

slope of φx(·) equals 1. Alternatively, one can also test that the RHS of (8) is constant

across quantiles.

By Lemma 1 and Lemma 2, the identification of h follows.

Theorem 1. Suppose that assumptions A to D hold. For every x ∈ SX, d = 0, 1 and τ ∈ [0, 1],

h(d, x, τ) is identified as the τ–th quantile of the distribution of Fh(d,x,ε)(·), where

Fh(1,x,ε)(t) = P[YD + φX(Y)(1− D) ≤ t|X = x

],

Fh(0,x,ε)(t) = P[Y(1− D) + φ−1

X (Y)D ≤ t|X = x].

The proof of theorem 1 is straightforward given the above discussion, and hence omitted.

Our identification results in Theorem 1 are different from those in a seminal paper by

Chernozhukov and Hansen (2005) who establish the identification of h(d, x, τ) under a

full–rank condition for any given τ ∈ (0, 1). Subsequently, Chen, Chernozhukov, Lee,

and Newey (2014) and Chernozhukov and Hansen (2013) weaken this rank condition

with respect to the regions where it should hold. Our rank condition requires a binary

instrument for the identification of h(d, x, ·), which is weaker than the rank conditions

in Chernozhukov and Hansen (2005), Chen, Chernozhukov, Lee, and Newey (2014) and

Chernozhukov and Hansen (2013). A closer comparison of identification conditions

between our approach and Chernozhukov and Hansen (2005) is provided in Section 4,

where we show that our approach exploits the shape restrictions (i.e. assumption A) to

the fullest.9 Moreover, our identification is constructive and highlights the identification

power of complier groups (as well as defier groups when (2) is not assumed) that are

induced by variations in the instrumental variables.

3.1. Discussion. First, we note that the rank condition (assumption C) is minimal for

an instrumental variable Z. In contrast, the identification at infinity approach developed

in Chamberlain (1986) and Heckman (1990) involves a strong support condition on

Z. In a semiparametric setting with discrete endogenous regressors, Lewbel (1998)

9We thank Victor Chernozhukov for helpful comments.

14

proposes a “special regressor” approach for the identification of linear index coefficients

under a large support assumption on the special regressor. Our condition on the

instrumental variable is related to that in recent papers by D’Haultfœuille and Février

(forthcoming) and Torgovitsky (forthcoming), who study a triangular system with

continuous endogenous regressors. By extending the quantile matching approach using

a chaining idea, their approaches for the identification of the structural relationship also

allow for a binary valued instrumental variable. See also Guerre, Perrigne, and Vuong

(2009) for an early use of the chaining argument.

In Lemma 2, assumption D is a support condition that relates to the effectiveness of

the instrumental variable. Intuitively, the compliers group contains all the information

on (individual) treatment effects as well as the structural function (conditional on

X = x). Lemma 2 highlights that, in addition to generating variations in the propensity

score, the instrumental variable also needs to be fully effective to point identify the

counterfactual mapping over its whole support. Otherwise, there exists a non–trivial

subgroup in the population for which we can not use exogenous variations in the

instrumental variable to point identify their treatment effects. When assumption D fails,

we call the instrumental variable Z partially effective. In this case, the counterfactual

mapping on the support of the complier group provides bounds for potential outcomes

of the population.10

For any two generic random variables W and S, let Q∗W|S(τ|s) = sup{w : P(W ≤w|S = s) ≤ τ} for any τ ∈ [0, 1]. Because {w : P(W ≤ w|S = s) ≤ τ}⋃{w : P(W ≤w|S = s) ≥ τ} = R, we have QW|S(τ|s) ≤ Q∗W|S(τ|s) with equality if QW|S(τ|s) is an

inner point in the support of W given S = s. Moreover, we have Q∗W|S(1|s) = +∞ and

QW|S(0|s) = −∞, which represent trivial bounds.

10Note that parametric assumptions on h (or on the counterfactual mapping) can also help achieve pointidentification of potential outcomes outside of the support Cdx.

15

Corollary 1. Suppose assumptions A to C hold. For every x ∈ SX, let z1, z2 ∈ SZ|X=x such

that p(x, z1) < p(x, z2). Then, the counterfactual mapping φx(·) is partially identified by

φx,`(y0) ≡ Qh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)

(Fh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(y0)

)≤ φx(y0)

≤ Q∗h(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)

(Fh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(y0)

)≡ φx,u(y0) (9)

for all y0 ∈ SY|D=0,X=x.11 Moreover, the structural function h(d, x, τ) is partially identified

by

h`(d, x, τ) ≤ h(d, x, τ) ≤ hu(d, x, τ)

where for s = `, u, hs(1, x, τ) is the τ–th quantile of the distribution P[YD + φx,s(Y)(1−

D) ≤ t|X = x]; hs(0, x, τ) is the τ–th quantile of the distribution P

[ϕx,s(Y)D +Y(1−D) ≤

t|X = x], in which ϕx,s(·) is defined in footnote 11.

Proof. See Appendix A.3. �

Note that the upper and lower bounds of φx(y0) collapse to each other when y0 ∈ C ◦0x,

the interior of C0x. That is, φx(·) is point identified on C ◦0x. A similar property applies to

the structural function h(d, x, τ) when τ ∈ S ◦ε|X=x,m(x,z1)<η≤m(x,z2)

.

4. EXTENDING THE IDENTIFICATION ARGUMENT

In this section, we investigate the identification power arising from the selection

equation, as well as from variations in the instrumental variable Z. In particular, we

drop assumption B and provide a general sufficient condition for the identification of

the counterfactual mapping φx as well as the structural function h. Such a condition is

related to, but weaker than, the rank condition for global identification developed in

Chernozhukov and Hansen (2005, Theorem 2). Throughout, we maintain assumption A.

11Note that (9) implies that for all y1 ∈ SY|D=1,X=x,

ϕx,`(y1) ≡ Qh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)

(Fh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)

(y1))≤ φ−1

x (y1)

≤ Q∗h(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)

(Fh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)

(y1))≡ ϕx,u(y1).

By definition, we can show ϕx,`(y1) = inf{y0 : φx,u(y0) ≥ y1} and ϕx,u(y1) = sup{y0 : φx,`(y0) ≤ y1}.

16

Under assumption A, we have P[Y ≤ h(D, X, τ)|X = x, Z = z

]= τ for all z ∈

SZ|X=x and τ ∈ (0, 1), which is called the main testable implication by Chernozhukov

and Hansen (2005, Theorem 1). Because D is binary, we have for all z ∈ SZ|X=x,

P[Y ≤ h(1, x, τ); D = 1|X = x, Z = z

]+ P

[Y ≤ h(0, x, τ); D = 0|X = x, Z = z

]= τ. (10)

Suppose z1, z2 ∈ SZ|X=x with p(x, z1) < p(x, z2). Thus, we obtain

P[Y ≤ h(1, x, τ); D = 1|X = x, Z = z1

]+ P

[Y ≤ h(0, x, τ); D = 0|X = x, Z = z1

]= P

[Y ≤ h(1, x, τ); D = 1|X = x, Z = z2

]+P

[Y ≤ h(0, x, τ); D = 0|X = x, Z = z2

],

i.e.,

∆0(h(0, x, τ), x, z1, z2) = ∆1(h(1, x, τ), x, z1, z2), (11)

where ∆d(·, x, z1, z2) is defined for y ∈ R as

∆0(y, x, z1, z2) ≡ P [Y ≤ y; D = 0|X = x, Z = z1]−P [Y ≤ y; D = 0|X = x, Z = z2] ,

∆1(y, x, z1, z2) ≡ P [Y ≤ y; D = 1|X = x, Z = z2]−P [Y ≤ y; D = 1|X = x, Z = z1] .

Note that ∆d is (up to sign) the numerator of the RHS in (4). By definition, ∆d(·, x, z1, z2)

is identified on R for d = 0, 1. Let y = h(0, x, τ) in (11) so that h(1, x, τ) = φx(y). Since

τ is arbitrary, then

∆0(y, x, z1, z2) = ∆1(φx(y), x, z1, z2), ∀y ∈ Sh(0,x,ε). (12)

Our general identification result is based on (12) and exploits the strict monotonicity

of φx(·).12 Recall that under assumption B, ∆d(y, x, z1, z2) = P[h(d, x, ε) ≤ y; m(x, z1) <

η ≤ m(x, z2)|X = x], which is continuous and strictly increasing in y ∈ Sh(d,x,ε) under

12Chernozhukov and Hansen (2005) first write (10) for Z = z1 and Z = z2 and then find sufficientcondition for the resulting system of two (nonlinear) equations to have a unique local/global solution inthe two unknowns h(1, x, τ) and h(0, x, τ).

17

assumption D, thereby identifying φx(·) = ∆−11 (∆0(·, x, z1, z2), x, z1, z2) on Sh(0,x,ε). This

suggests that identification of the counterfactual mapping φx can be achieved under

weaker conditions than assumption B.

Definition 1 (Piecewise Monotone). Let g : R→ R and S ⊆ R. We say that g is piecewise

weakly (strictly) monotone on the support S if S can be partitioned into a countable number of

non–overlapping intervals such that g is weakly (strictly) monotone in every interval.

Lemma 3. Suppose assumption A holds. Given x ∈ SX, suppose z1, z2 ∈ SZ|X=x with

p(x, z1) < p(x, z2). Then, ∆1(·, x, z1, z2) is piecewise weakly (strictly) monotone on Sh(1,x,ε)

if and only if ∆0(·, x, z1, z2) is piecewise weakly (strictly) monotone on Sh(0,x,ε).


Assumption E. Suppose ∆d(·, x, z1, z2) is piecewise weakly monotone on Sh(d,x,ε), d = 0, 1.

Assumption E is weak. In particular, if ∆d(·, x, z1, z2) is continuously differentiable as in

Chernozhukov and Hansen (2005, Theorem 2-i), then assumption E holds.

Lemma 4. Let x ∈ SX such that z1, z2 ∈ SZ|X=x with p(x, z1) < p(x, z2). Suppose (i)

φx(·) : Sh(0,x,ε) → Sh(1,x,ε) is continuous and strictly increasing, and (ii) equation (12) and

assumption E hold where ∆d(·, x, z1, z2) and Sh(d,x,ε) are known for d = 0, 1. Then, φx(·) is

identified if and only if ∆d(·, x, z1, z2) is piecewise strictly monotone on Sh(d,x,ε) for some d.


Lemma 4 is useful when identification is based on (12) only. In this case, under the

maintained assumption E, Lemma 4 provides a necessary and sufficient condition for

the identification of φx(·).By replacing assumptions B and D with the weaker assumption that ∆d(·, x, z1, z2)

be piecewise strictly monotone on SY|X=x,D=d for d = 0, 1, we now extend Lemma 2

and Theorem 1. Note that the non–flatness of ∆d(·, x, z1, z2) on SY|X=x,D=d for d = 0, 1

plays a similar role as assumption D.

18

Theorem 2. Suppose that assumptions A and C hold. Let x ∈ SX such that z1, z2 ∈SZ|X=x with p(x, z1) < p(x, z2). Suppose ∆d(·, x, z1, z2) is piecewise strictly monotone

on SY|X=x,D=d for d = 0, 1. Then the support of h(d, x, ε) is identified by Sh(d,x,ε) =

SY|D=d,X=x. Moreover, φx(·) and h(d, x, ·) are identified on the supports Sh(0,x,ε) and [0, 1],

respectively.


5. CHARACTERIZATION OF MODEL RESTRICTIONS

In empirical applications, an important question is whether to adopt the nonseparable

model (1) with or without the selection equation (2). As shown in Section 3, the selection

equation provides a simple and constructive identification result, but can introduce

additional restrictions on the data. In this section, we characterize all the restrictions

on observables imposed by the model with or without the selection equation. These

restrictions are useful for developing model selection and model specification tests.

Formally, we denote these two models by

M0 ≡{[h, FεD|XZ] : assumption A holds

};

M1 ≡{[h, m, Fεη|XZ] : assumptions A and B hold

}.

To simplify, hereafter we assume SXZ = SX × {z1, z2}. Moreover, p(x, z1) < p(x, z2)

for all x ∈ SX. We say that a conditional distribution FYD|XZ of observables is rational-

ized by modelM if and only if there exists a structure inM that generates FYD|XZ.

Theorem 3. A conditional distribution FYD|XZ can be rationalized byM0 if and only if

(i) FY|DXZ is a continuous conditional CDF;

(ii) for each x ∈ SX, there exists a continuous and strictly increasing mapping gx : R→ R

such that gx maps S(1−D)Y+Dg−1x (Y)|X=x onto SDY+(1−D)gx(Y)|X=x and

∆0(·, x, z1, z2) = ∆1(gx(·), x, z1, z2). (13)

19


In Theorem 3, the key restriction is the existence of a solution to (13), which may not be

unique.

We now turn toM1.

Theorem 4. A conditional distribution FYD|XZ rationalized byM0 can also be rationalized by

M1 if and only if for any x ∈ SX and d ∈ {0, 1}, ∆d(·, x, z1, z2) is weakly increasing on R.


The condition in Theorem 4 strengthens Theorem 3–(ii): By Lemma 4, the fact that

∆d(·, x, z1, z2) is continuous and strictly increasing on SY|D=d,X=x implies that (13) has a

unique solution gx(·) = φx(·). See also Vuong and Xu (2014) for a characterization of all

the restrictions associated with two other models which do not impose monotonicity in

the outcome equation, namely, {[h, FεD|XZ]: ε is continuously distributed on an interval

and assumption A–(ii) holds} and {[h, m, Fεη|XZ]: assumption B holds}.

6. GENERALIZATION

This section provides another extension of Lemma 2 and Theorem 1. Specifically, we

relax the continuity and strict monotonicity assumption of h in assumption A so that

our method applies to the case where the outcome variable has a probability mass in

its distribution such as when the outcome variable is censored or binary (a challenging

situation according to Wooldridge, 2013).

Assumption A’. Equation (1) holds where (i) h is left–continuous and weakly increasing in ε,

with ε distributed as U[0, 1], and (ii) (X, Z) is independent of ε.

The left–continuity of h is a normalization for the identification of the structural function

at its discontinuous points.

Because assumption A’ relaxes assumption A, we need to strengthen assumption B

to achieve point identification of h. Specifically, we require the covariates X to be

20

exogenous in (2). This approach was first introduced by Vytlacil and Yildiz (2007) in a

weakly nonseparable model. See also Shaikh and Vytlacil (2011).

Assumption B’. Equation (2) holds where (i) (ε, η) is independent of (X, Z), (ii) the distri-

bution of (ε, η) is absolutely continuous with respect to Lebesgue measure, and (iii) S(ε,η) is a

rectangle.

Under assumption B’-(i), we can drop X = x in Fh(d,x,ε)|X=x,m(x,z1)<η≤m(x,z2). To simplify

our exposition, we assume assumption B’-(iii) which is slightly stronger than the support

condition in assumption D.

A key point from Vytlacil and Yildiz (2007) is that assumption B’ allows us to use

variations in X for the identification of h(d, x, ·) when Z has sufficient variations (more

than binary). The following rank condition is introduced for the identification of

h(1, x, ·). The identification of h(0, x, ·) can be obtained similarly.

Assumption C’ (Generalized Rank Condition). For any x ∈ SX, there exists x ∈ SX such

that (i) the set Sp(X,Z)|X=x⋂

Sp(X,Z)|X=x contains at least two different values, and (ii) for

any pair τ1, τ2 ∈ (0, 1),

h(0, x, τ1) = h(0, x, τ2) =⇒ h(1, x, τ1) = h(1, x, τ2).

Condition (i) of assumption C’ requires that there exist z1, z2 ∈ SZ|X=x and z1, z2 ∈SZ|X=x such that p(x, z1) = p(x, z1) < p(x, z2) = p(x, z2). Condition (ii) is testable

since it is equivalent to the following condition: For any τ1, τ2 ∈ (0, 1),

Qh(0,x,ε)|m(x,z1)<η≤m(x,z2)(τ1) = Qh(0,x,ε)|m(x,z1)<η≤m(x,z2)(τ2)

=⇒ Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)(τ1) = Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)(τ2).

Thus, we can verify whether there is x ∈ SX satisfying assumption C’. When h(d, x, ·)is strictly monotone in ε, by setting x = x, assumption C’ reduces to assumption C.

21

Fix x and let x satisfy assumption C’. We define a generalized counterfactual map-

ping φx,x(·) as φx,x(y)= h(1, x, h−1(0, x, y)) for all y ∈ Sh(0,x,ε).

13 If x = x, then

φx,x(·) reduces to the counterfactual mapping φx(·) in Section 3. Let (z1, z2) ∈ SZ|X=x

and (z1, z2)SZ|X=x with p(x, z1) = p(x, z1) < p(x, z2) = p(x, z2). The next theorem

generalizes Lemma 2 and Theorem 1.

Theorem 5. Suppose assumptions A’ and B’ hold. For any x ∈ SX, suppose in addition

assumption C’ hold with x, then φx,x(·) is identified by

φx,x(·) = Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Fh(0,x,ε)|m(x,z1)<η≤m(x,z2)(·)

). (14)

and for any τ ∈ [0, 1], h(1, x, τ) is identified as the τ–th quantile of the distribution

Fh(1,x,ε)(·) = P(Y ≤ ·; D = 1|X = x) + P[φx,x(Y) ≤ ·; D = 0|X = x

].


To illustrate Theorem 5, we discuss the generalized rank condition (assumption C’)

with two examples: the first example is a fully nonseparable censored regression model

while the second example is a weakly separable binary response model. The first

example seems to be new, though special cases have been studied previously under

some parametric and/or separability assumptions. The second example was studied by

Vytlacil and Yildiz (2007).

Example 3. Consider the model

Y = h∗(D, X, ε)1(h∗(D, X, ε) ≥ 0

),

D = 1(m(X, Z) ≥ η

),

where h∗ is strictly increasing in ε. The structural unknowns are (h∗, m, Fεη).

13Due to the weak monotonicity of h in ε, we define h−1(0, x, y) = infτ{τ : h(0, x, τ) ≥ y}.

22

Fix x ∈ SX. For d = 0, 1, let τdx solve h∗(d, x, τdx) = 0. W.l.o.g., let τdx ∈ (0, 1). Thus,

assumption C’ is satisfied if there exists an x ∈ SX such that τ0x ≤ τ1x and p(x, z1) =

p(x, z1) < p(x, z2) = p(x, z2) for some z1, z2 ∈ SZ|X=x, z1, z2 ∈ SZ|X=x.

Example 4. Let Y and D denote a binary outcome variable and a binary endogenous regressor,

respectively. Consider

Y = 1(h∗(D, X) ≥ ε

),

D = 1(m(X, Z) ≥ η

).

To identify h∗(1, x) for some x, assumption C’ requires that there exists x ∈ SX such that

h∗(1, x) = h∗(0, x) and p(x, z1) = p(x, z1) < p(x, z2) = p(x, z2) for some z1, z2 ∈ SZ|X=x,

z1, z2 ∈ SZ|X=x. Thus, assumption C’ reduces exactly to the support condition in Vytlacil and

Yildiz (2007).

Motivated by Shaikh and Vytlacil (2011), assumption C’-(ii) can be relaxed leading to

partial identification. For generic random variables W and S, let KW|S be the Kolmogorov

(conditional) CDF defined by KW|S(w|s) = P(W < w|S = s). By definition, we have

KW|S(w|s) ≤ FW|S(w|s) with equality if w is not a mass point of W given S = s.

Corollary 2. Suppose assumptions A’ and B’ hold. For any x ∈ SX, suppose in addition

assumption C’-(i) hold with x, then φx,x(·) is partially identified by

φx,x

(·) ≡ Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Kh(0,x,ε)|m(x,z1)<η≤m(x,z2)(·)

)≤ φx,x(·)

≤ Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Fh(0,x,ε)|m(x,z1)<η≤m(x,z2)(·)

)≡ φx,x(·),

and for any τ ∈ [0, 1], the lower and upper bounds of h(1, x, τ) are identified as the τ–th

quantiles of the distributions P(Y ≤ ·; D = 1|X = x) + P[φ

x,x(Y) ≤ ·; D = 0|X = x

]and

P(Y ≤ ·; D = 1|X = x) + P[φx,x(Y) ≤ ·; D = 0|X = x

], respectively. 14


14This corollary was first presented at Bilkent Workshop in Econometric Theory and Applications, 2013.

23

In Corollary 2, the lower and upper bounds collapse to each other if in addition C’-(ii)

holds for x.

Similarly to Corollary 1, we can also drop the support condition B’-(iii) to construct

bounds under assumption C’-(i).

Corollary 3. Suppose assumptions A’ and B’-(i,ii) hold. For any x ∈ SX, suppose assumption

C’-(i) hold with x, then φx,x(·) is partially identified by

φLx,x(·) ≡ Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Kh(0,x,ε)|m(x,z1)<η≤m(x,z2)(·)

)≤ φx,x(·)

≤ Q∗h(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Fh(0,x,ε)|m(x,z1)<η≤m(x,z2)(·)

)≡ φH

x,x(·),

and for any τ ∈ [0, 1], the lower and upper bounds of h(1, x, τ) are identified as the τ–th

quantiles of the distributions P(Y ≤ ·; D = 1|X = x) + P[φL

x,x(Y) ≤ ·; D = 0|X = x]

and

P(Y ≤ ·; D = 1|X = x) + P[φH

x,x(Y) ≤ ·; D = 0|X = x], respectively.


When there are multiple x satisfying assumption C’-(i), we can use them jointly to

tighten our bounds in Corollaries 2 and 3 by taking the sup and the inf over x. See

Shaikh and Vytlacil (2011).

7. CONCLUSION

This paper establishes nonparametric identification of the counterfactual mapping,

individual treatment effects and structural function in a nonseparable model with a

binary endogenous regressor. Our benchmark model assumes strict monotonicity in the

outcome equation and weak monotonicity in the selection equation. Our counterfactual

mapping then links each outcome with its counterfactual. Moreover, we consider two

extensions: One without a selection equation and the other with weak monotonicity in

the outcome equation.

As indicated in Section 3, the counterfactual mapping and individual treatment effects

can be identified under the weaker independence assumption Z⊥(ε, η)|X, the rank

24

condition (assumption C) and the support condition (assumption D). In particular,

assumption D is satisfied as soon as ε and η have a rectangle support given X. Some

policy effects such as ATE can also be identified. When assumption D fails, we obtain

partial identification of the counterfactual mapping and individual treatment effects. It

is important to note that such results do not require exogeneity of X. On the other hand,

identification of the structural function h, which is necessary for some counterfactuals

in empirical IO, requires the independence of X and ε in assumption A.

To conclude, one needs to develop a nonparametric estimation method for the struc-

tural function h. To simplify ideas, we consider the benchmark model in Section 3

where X is discrete and Z is binary. We further assume p(x, z1) 6= p(x, z2) for all

(x, z1), (x, z2) ∈ SXZ. A method will be first to estimate the counterfactual mapping

φx(·) and its inverse by

φx(·) = Qh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(Fh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(·)),

φ−1x (·) = Qh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(Fh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(·)),

where Qh(d,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(·) is the quantile function of

Fh(d,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(·)

=∑n

i=1 1(Yi ≤ ·; Di = d; Xi = x)[1(Zi = z2)− 1(Zi = z1)]

∑ni=1 1(Di = d; Xi = x)[1(Zi = z2)− 1(Zi = z1)]

.

In the second step, one estimates the structural function for any τ ∈ (0, 1) by

h(1, x, τ) = QYD+φx(Y)(1−D)|X=x(τ), h(0, x, τ) = QY(1−D)+φ−1x (Y)D|X=x(τ),

which are respectively the τ–th quantiles of

FYD+φx(Y)(1−D)|X=x(·) =∑n

i=1 1(YD + φx(Y)(1− D) ≤ ·; Xi = x)∑n

i=1 1(Xi = x),

FY(1−D)+φ−1x (Y)D|X=x(·) =

∑ni=1 1(Y(1− D) + φ−1

x (Y)D ≤ ·; Xi = x)∑n

i=1 1(Xi = x).

25

The above estimation procedure can be easily implemented.

Excluding possibly boundaries, the above suggests that the estimators of the counter-

factual mapping φx(·) and the structural function h are√

n–consistent. Their precise

asymptotic distributions can be derived using the functional delta method and the com-

position lemma 3.9.27 in Van Der Vaart and Wellner (1996). If Z is continuous, we conjec-

ture that φx(·) and h are still estimated at√

n–rate. This is because we can average out

Z and obtain EFh(0,x,ε)|X=x,m(x,Z1)<η≤m(x,Z2)(·) = EFh(1,x,ε)|X=x,m(x,Z1)<η≤m(x,Z2)(φx(·))where Z1 and Z2 are two different observations. On the other hand, if X is continuous,

the estimation of φx and h will no longer be√

n–consistent. An important question is

then the optimal rate for estimating these functions. Moreover, we should note that even

in the benchmark model, there might exist several values x 6= x satisfying assumption

C’–(i). In this case, one has other counterfactual mapping φx,x that can be used to

identify h. A second question is to use this property to improve efficiency.

REFERENCES

ATHEY, S. (2001): “Single crossing properties and the existence of pure strategy equilib-

ria in games of incomplete information,” Econometrica, 69(4), 861–889.

(2002): “Monotone comparative statics under uncertainty,” The Quarterly Journal

of Economics, 117(1), 187–223.

ATHEY, S., AND G. W. IMBENS (2006): “Identification and inference in nonlinear

difference-in-differences models,” Econometrica, 74(2), 431–497.

CHAMBERLAIN, G. (1986): “Asymptotic efficiency in semi-parametric models with

censoring,” Journal of Econometrics, 32(2), 189–218.

CHEN, X., V. CHERNOZHUKOV, S. LEE, AND W. K. NEWEY (2014): “Local identification

of nonparametric and semiparametric models,” Econometrica, 82(2), 785–809.

CHERNOZHUKOV, V., AND C. HANSEN (2005): “An IV model of quantile treatment

effects,” Econometrica, 73(1), 245–261.

26

(2013): “Quantile models with endogeneity,” Annual Review of Economics, 5,

57–81.

CHESHER, A. (2003): “Identification in nonseparable models,” Econometrica, 71(5),

1405–1441.

(2005): “Nonparametric identification under discrete variation,” Econometrica,

73(5), 1525–1550.

D’HAULTFŒUILLE, X., AND P. FÉVRIER (forthcoming): “Identification of nonseparable

models with endogeneity and discrete instruments,” Econometrica.

FIRPO, S. (2007): “Efficient semiparametric estimation of quantile treatment effects,”

Econometrica, 75(1), 259–276.

FROELICH, M., AND B. MELLY (2013): “Unconditional quantile treatment effects under

endogeneity,” Journal of Business & Economic Statistics, 31(3), 346–357.

GUERRE, E., I. PERRIGNE, AND Q. VUONG (2000): “Optimal nonparametric estimation

of first–price auctions,” Econometrica, 68(3), 525–574.

(2009): “Nonparametric identification of risk aversion in first-price auctions

under exclusion restrictions,” Econometrica, 77(4), 1193–1227.

HECKMAN, J. (1990): “Varieties of selection bias,” The American Economic Review, 80(2),

313–318.

HECKMAN, J. J. (1979): “Sample selection bias as a specification error,” Econometrica:

Journal of the econometric society, pp. 153–161.

HECKMAN, J. J., AND R. ROBB (1986): Alternative methods for solving the problem of

selection bias in evaluating the impact of treatments on outcomes. Springer.

HECKMAN, J. J., J. SMITH, AND N. CLEMENTS (1997): “Making the most out of pro-

gramme evaluations and social experiments: Accounting for heterogeneity in pro-

gramme impacts,” The Review of Economic Studies, 64(4), 487–535.

HECKMAN, J. J., AND E. VYTLACIL (2005): “Structural equations, treatment effects, and

econometric policy evaluation,” Econometrica, 73(3), 669–738.

27

HECKMAN, J. J., AND E. J. VYTLACIL (1999): “Local instrumental variables and latent

variable models for identifying and bounding treatment effects,” Proceedings of the

National Academy of Sciences, 96(8), 4730–4734.

(2007): “Econometric evaluation of social programs, part I: Causal models,

structural models and econometric policy evaluation,” Handbook of econometrics, 6,

4779–4874.

HODERLEIN, S., AND E. MAMMEN (2007): “Identification of marginal effects in nonsep-

arable models without monotonicity,” Econometrica, 75(5), 1513–1518.

IMBENS, G. W. (2007): “Nonadditive models with endogenous regressors,” Econometric

Society Monographs, 43, 17.

IMBENS, G. W., AND J. D. ANGRIST (1994): “Identification and estimation of local

average treatment effects,” Econometrica, 62(2), 467–475.

IMBENS, G. W., AND W. K. NEWEY (2009): “Identification and estimation of triangular

simultaneous equations models without additivity,” Econometrica, 77(5), 1481–1512.

IMBENS, G. W., AND D. B. RUBIN (1997): “Estimating outcome distributions for compli-

ers in instrumental variables models,” The Review of Economic Studies, 64(4), 555–574.

IMBENS, G. W., AND J. M. WOOLDRIDGE (2009): “Recent developments in the econo-

metrics of program evaluation,” Journal of Economic Literature, 47(1), 5–86.

JUN, S. J., J. PINKSE, AND H. XU (2011): “Tighter bounds in triangular systems,” Journal

of Econometrics, 161(2), 122–128.

KASY, M. (2014): “Instrumental variables with unrestricted heterogeneity and continu-

ous treatment,” The Review of Economic Studies, 81(4), 1614–1636.

LEWBEL, A. (1998): “Semiparametric latent variable model estimation with endogenous

or mismeasured regressors,” Econometrica, pp. 105–121.

MANSKI, C. F. (1990): “Nonparametric bounds on treatment effects,” The American

Economic Review, 80(2), 319–323.

MATZKIN, R. L. (1999): “Nonparametric estimation of nonadditive random functions,”

Discussion paper, Northwestern University.

28

(2003): “Nonparametric estimation of nonadditive random functions,” Econo-

metrica, 71(5), 1339–1375.

(2008): “Identification in nonparametric simultaneous equations models,” Econo-

metrica, 76(5), 945–978.

(2015): “Estimation of nonparametric models with simultaneity,” Econometrica,

83(1), 1–66.

MILGROM, P., AND C. SHANNON (1994): “Monotone comparative statics,” Econometrica:

Journal of the Econometric Society, pp. 157–180.

RENY, P. J. (2011): “On the existence of monotone pure–strategy equilibria in Bayesian

games,” Econometrica, 79(2), 499–553.

RUBIN, D. B. (1974): “Estimating causal effects of treatments in randomized and

nonrandomized studies.,” Journal of Educational Psychology, 66(5), 688.

SHAIKH, A. M., AND E. J. VYTLACIL (2011): “Partial identification in triangular systems

of equations with binary dependent variables,” Econometrica, 79(3), 949–955.

TORGOVITSKY, A. (forthcoming): “Identification of nonseparable models with general

instruments,” Econometrica.

VAN DER VAART, A. W., AND J. A. WELLNER (1996): Weak Convergence. Springer.

VUONG, Q., AND H. XU (2014): “Characterization of model restrictions in a triangular

system,” Discussion paper, New York University and University of Texas at Austin.

VYTLACIL, E. (2002): “Independence, monotonicity, and latent index models: An

equivalence result,” Econometrica, 70(1), 331–341.

(2006): “A note on additive separability and latent index models of binary choice:

representation results,” Oxford Bulletin of Economics and Statistics, 68(4), 515–518.

VYTLACIL, E., AND N. YILDIZ (2007): “Dummy endogenous variables in weakly sepa-

rable models,” Econometrica, 75(3), 757–779.

WOOLDRIDGE, J. (2013): “Control function methods in applied econometrics,” Discus-

sion paper, Michigan State University.

29

APPENDIX A. PROOFS

A.1. Proof of Lemma 1.

Proof. The only if part is straightforward by the definition of φx(·) and it suffices to show

the if part. Suppose φx(·) is identified. Fix x. By definition, h(1, x, ·) = φx(h(0, x, ·)) on

[0, 1]. Then, conditional on X = x, we have h(1, x, ε) = YD + φx(Y)(1− D) and h(0, x, ε) =

Y(1− D) + φ−1x (Y)D. Therefore we can identify Fh(d,x,ε) as follows: for all t ∈ R,

Fh(1,x,ε)(t) = P(YD + φx(Y)(1− D) ≤ t|X = x),

Fh(0,x,ε)(t) = P(Y(1− D) + φ−1x (Y)D ≤ t|X = x).

Further, by assumption A, we have h(d, x, τ) = Qh(d,x,ε)(τ) for all τ ∈ [0, 1]. �


Proof. Fix x ∈ SX and z1, z2 ∈ SZ|X=x with p(x, z1) < p(x, z2). First, we use proof by contradic-

tion to show C0x = Sh(0,x,ε): Suppose C0x ( Sh(0,x,ε). Then it implies E ≡ {e ∈ [0, 1] : h(0, x, e) 6∈

C0x} does not belong to the complier group. Hence, for any e ∈ E, either h(1, x, e) 6∈ C0x, or

h(0, x, e) 6∈ C0x, which contradicts assumption D. Similarly, we also have C1x = Sh(1,x,ε).

Because h is strictly monotone in ε, we have for any τ ∈ (0, 1)

Fh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(h(0, x, τ)) = Fε|X=x,m(x,z1)<η≤m(x,z2)(τ)

= Fh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(h(1, x, τ)).

Note that Fh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2) is continuous and strictly increasing at h(1, x, τ). Then

h(1, x, τ) = Qh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)

(Fh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(h(0, x, τ))

).

Let y = h(0, x, τ) ∈ C0x. Then, τ = h−1(0, x, y) and the above equation becomes

φx(y) = Qh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)

(Fh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(y)

). �

30

A.3. Proof of Corollary 1.

Proof. By the proof of lemma 2, we have

Fh(0,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(h(0, x, τ)) = Fh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)(h(1, x, τ)).

Fh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2) is continuous and weakly increasing at h(1, x, τ), we have

h(1, x, τ) ≥ Qh(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)


)and

h(1, x, τ) ≤ Q∗h(1,x,ε)|X=x,m(x,z1)<η≤m(x,z2)


).

Let y0 = h(0, x, τ) ∈ C0x. Then, h(1, x, τ) = φx(y0) and the above equation becomes

φx,`(y0) ≤ φx(y0) ≤ φx,u(y0).

By a similar argument, we can show the result in footnote 11.

Moreover, P[YD + φx,`(Y)(1− D) ≤ ·|X = x

]and P

[YD + φx,u(Y)(1− D) ≤ ·|X = x

]are

the upper and lower bounds of P(h(1, x, ε) ≤ ·|X = x), respectively. Therefore, their τ–th

quantile serves as the lower and upper bounds of h(1, x, τ), respectively. A similar argument

holds for h(0, x, τ).

�


Proof. For the if part, suppose ∆0(·, x, z1, z2) is piecewise weakly monotone on Sh(0,x,ε). Then,

by definition, Sh(0,x,ε) can be partitioned into a sequence of non–overlapping intervals {Ij : j =

1, · · · , J}, where J ∈N∪ {+∞}, such that ∆0(·, x, z1, z2) is weakly monotone on every interval.

By assumption A, φx(·) is continuous and strictly increasing. Then, Sh(1,x,ε) can be partitioned

into a sequence of non–overlapped intervals {φx(Ij) : j = 1, · · · , J}. Moreover, by (12), we have

∆1(y, x, z1, z2) = ∆0(φ−1

x (y), x, z1, z2), ∀y ∈ Sh(1,x,ε).

Clearly, ∆1(·, x, z1, z2) is weakly monotone in every interval φx(Ij). The only if part can be shown

similarly. �

31


Proof. We first show the if part. W.l.o.g., let ∆0(·, x, z1, z2) be piecewise strictly monotone on

Sh(0,x,ε), which can be partitioned into a sequence of non–overlapping intervals {Ij : j =

1, · · · , J}. On each interval Ij, due to the monotonicity, ∆0(·, x, z1, z2) has at most a countable

number of discontinuity points. Hence, Sh(0,x,ε) can be further partitioned into a countable

number of non–overlapped intervals such that ∆0(·, x, z1, z2) is continuous and strictly monotone

on every interval. For such a sequence of intervals, we further merge adjacent intervals if

∆0(·, x, z1, z2) is continuous and strictly monotone on the union of them.

Thus, we partition Sh(0,x,ε) into a countable number of non–overlapped intervals {I′j : j =

1, · · · , J′}, where J′ ∈ N ∪ {+∞}, such that ∆0(·, x, z1, z2) is continuous, strictly monotone

on every interval, and discontinuous or achieve a local extreme value at each endpoints of

these intervals. By the proof of Lemma 3, (12) and the fact that φx(·) : Sh(0,x,ε) → Sh(1,x,ε) is

continuous and strictly increasing implies that Sh(1,x,ε) can be partitioned into the same number

of non–overlapped intervals {φx(I′j) : j = 1, · · · , J′}, such that ∆1(·, x, z1, z2) is continuous,

strictly monotone on every interval, and discontinuous or achieve a local extreme value at each

endpoints of these intervals.

Moreover, for each y ∈ I′j , we solve φx(y) by (12) as

φx(y) = ∆−11,j (∆0,j(y, x, z1, z2), x, z1, z2),

where ∆0,j(·, x, z1, z2) and ∆1,j(·, x, z1, z2) are the projections of ∆0(·, x, z1, z2) and ∆1(·, x, z1, z2)

on the support I′j and φx(Ij), respectively.

For the only if part, w.l.o.g., suppose ∆0(·, x, z1, z2) is constant on a non–degenerate interval

I ⊆ Sh(0,x,ε). By the proof of Lemma 3, ∆1(·, x, z1, z2) is also constant on φx(I). It suffices to

construct a continuous and strictly increasing function φx 6= φx such that (12) holds for φx.

Let φx(y) = φx(y) for all y 6∈ I and φx(y) = φx(g(y)) for all y ∈ I, where g is an arbitrary

continuous, strictly increasing mapping from I onto I. Clearly, there are plenty of choices

for the function g. Moreover, φx 6= φx if g(t) is not an identity mapping. By construction,

∆1(φx(y), x, z1, z2) = ∆1(φx(y), x, z1, z2) holds for all y ∈ I because ∆1(·, x, z1, z2) is constant on

φx(I). This equation also holds for all y 6∈ I by the definition of φx. Then (12) holds for φx. �

32

A.6. Proof of Theorem 2.

Proof. We first show the identification of Sh(d,x,ε). Clearly, SY|X=x,D=d ⊆ Sh(d,x,ε). Suppose

w.l.o.g. SY|X=x,D=0 ( Sh(0,x,ε). Therefore, there exists an interval Iε in Sε such that P(ε ∈

Iε; D = 0|X = x, Z = z) = 0 and P(ε ∈ Iε; D = 1|X = x, Z = z) = P(Iε) for all z ∈ SZ|X=x. In

other words, conditional on X = x and Z = z for any z ∈ SZ|X=x, all individual with ε ∈ Iε

choose D = 1 almost surely. Thus, Sh(1,x,ε)|ε∈Iε⊆ SY|X=x,D=1 and the latter support is identified.

For e1 < e2 ∈ Iε, note that

P(Y ≤ h(1, x, e2); D = 1|X = x, Z = z)−P(Y ≤ h(1, x, e1); D = 1|X = x, Z = z)

= P(ε ∈ (e1, e2]), ∀z ∈ SZ|X=x.

Hence, for z1, z2 ∈ SZ|X=x with p(x, z1) < p(x, z2), we have

∆1(h(1, x, e2), x, z1, z2)− ∆1(h(1, x, e1), x, z1, z2)

= P(Y ≤ h(1, x, e2); D = 1|X = x, Z = z2)−P(Y ≤ h(1, x, e1); D = 1|X = x, Z = z2)

−P(Y ≤ h(1, x, e2); D = 1|X = x, Z = z1) + P(Y ≤ h(1, x, e1); D = 1|X = x, Z = z1) = 0.

which contradicts with the piecewise strict monotonicity of ∆1(·, x, z1, z2) on SY|X=x,D=1. There-

fore, we have SY|X=x,D=d = Sh(d,x,ε).

Thus, the identification of φx(·) and h(d, x, ·) follows directly from Lemmas 1 and 4. �


Proof. For the only if part, let gx(·) = φx(·) on the support Sh(0,x,ε). The result is straightforward

by Section 4,

For the if part, we prove by constructing a structure S = [h, FεD|XZ] to rationalize the given

distribution FYD|XZ. Fix an arbitrary x. Let Hx(y) ≡ P(Y · (1− D) + g−1

x (Y) · D ≤ y|X = x)

and h(0, x, τ) be its τ–th quantile. Moreover, let h(1, x, τ) = gx(h(0, x, τ)). Clearly, condition

(i) and the fact that gx is continuous and strictly increasing on the support ensure h(d, x, ·) are

continuous and strictly increasing on [0, 1]. Further let PS(ε ≤ τ; D = d|X = x, Z = z) = P(Y ≤

h(d, x, τ); D = d|X = x, Z = z) for all z ∈ SZ|X=x and (τ, d) ∈ [0, 1]× {0, 1}, where PS denote

33

the probability measure under the constructed structure S. We now show that (X, Z)⊥ε and

ε ∼ U[0, 1].

By (13), we have

P[Y ≤ gx(y); D = 1|X = x, Z = z1

]+ P

[Y ≤ y; D = 0|X = x, Z = z1

]= P

[Y ≤ gx(y); D = 1|X = x, Z = z2

]+ P

[Y ≤ y; D = 0|X = x, Z = z2

]= P

[Y ≤ gx(y); D = 1|X = x

]+ P

[Y ≤ y; D = 0|X = x

]= Hx(y).

where the second equality is because SZ|X=x = {z1, z2}.

Hence, for any τ ∈ [0, 1] and i = 1, 2,

PS(ε ≤ τ|X = x, Z = zi) = P(Y ≤ h(0, x, τ); D = 0|X = x, Z = zi

)+ P

(Y ≤ h(1, x, τ); D = 1|X = x, Z = zi

)= Hx(h(0, x, τ)) = τ,

where the last step is by the construction of h(0, x, ·) and the strict monotonicity of Hx(·) on the

support S(1−D)Y+Dg−1x (Y)|X=x. Therefore, (X, Z)⊥ε and ε ∼ U[0, 1].

Now it suffices to show that the constructed structure S = [h, FεD|XZ] generates the given

distribution FYD|XZ. This is true because for any (y, d, x, z) ∈ SYDXZ, we have

PS(Y ≤ y; D = d|X = x, Z = z) = PS(ε ≤ h−1(d, x, y); D = d|X = x, Z = z)

= P(Y ≤ y; D = d|X = x, Z = z).

The last step comes from the construction of FεD|XZ.


Proof. By Section 4, the only if part is trivial.

We now show the if part. Fix X = x. Suppose the condition holds for a structure S0 =

[h, FεD|XZ] satisfying assumption A. For notation simplicity, we will suppress x in the following

analysis.

It suffices to construct an observational equivalent structural S1 ∈ M1. Let η ∼ U(0, 1) and

m(z) = p(z). Hence, it suffices to construct the copula function of the joint distribution Fεη .

34

By Theorem 3, there exists a continuous and strictly increasing function g, which maps the

support S(1−D)Y+Dg−1(Y) onto SDY+(1−D)g(Y) and solves (13). Moreover, for each τ ∈ (0, 1), we

define h(1, τ) and h(0, τ) as τ–th quantile of the distribution of P(DY + (1− D)g(Y) ≤ ·) and

P(Dg−1(Y) + (1− D)Y ≤ ·), respectively. Because g is a one–to–one and onto mapping from

S(1−D)Y+Dg−1(Y) to SDY+(1−D)g(Y), h(d, ·) is strictly increasing on the support (0, 1). Moreover,

let C = Sh−1(1,Y)|D=1 ∩Sh−1(0,Y)|D=0. By definition, (i) ∆d(y, z1, z2) is strictly increasing on h(d, C)

and flat elsewhere; (ii) ∆0(h(0, τ), z1, z2) = ∆1(h(1, τ), z1, z2).

Moreover, for any τ ∈ (0, 1), let

P(ε ≤ τ, m(z1) < η ≤ m(z2)) = ∆1(h(1, τ), z1, z2),

which is weakly increasing in h(1, τ) ∈ SDY+(1−D)g(Y). Note that P(m(z1) < η ≤ m(z2)) =

∆1(∞, z1, z2) = p(z2)− p(z1). Moreover, for any τ ∈ (0, 1), let

P(ε ≤ τ, η ≤ m(z1)) = P(Y ≤ h(1, τ)|D = 1, Z = z1)− ∆1(h(1, τ), z1, z2).

P(ε ≤ τ, η > m(z2)) = P(Y ≤ h(0, τ)|D = 0, Z = z2)− ∆0(h(0, τ), z1, z2).

By the weak monotonicity of ∆d(·, z1, z2), the constructed Fεη is also monotone on its support.

Using the constructed m, h, Fε,η , one can verify that this structure S1 ∈ S1 is observationally

equivalent. �


Proof. Our proofs take two steps: First, we will show that

h(1, x, τ) = Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Fh(0,x,ε)|m(x,z1)<η≤m(x,z2)(h(0, x, τ))

)∀τ ∈ [0, 1].

Second, we will show that the distribution of h(d, x, ε) can be identified, from which we identify

function h(d, x, ·).

Fix x ∈ SX and x ∈ SX satisfying assumption C’. Let further z1, z2 ∈ SZ|X=x and z1, z2 ∈

SZ|X=x such that p(x, z1) = p(x, z1) < p(x, z2) = p(x, z2). By definition, the RHS of (14) is

weakly increasing and left–continuous. For any τ ∈ [0, 1], let ψ(0, x, τ) = sup{e : h(0, x, e) =

35

h(0, x, τ)}. By A’, we have

Fh(0,x,ε)|m(x,z1)<η≤m(x,z2)(h(0, x, τ)) = Fε|m(x,z1)<η≤m(x,z2)(ψ(0, x, τ)).

Therefore,

Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Fh(0,x,ε)|m(x,z1)<η≤m(x,z2)(h(0, x, τ))

)= Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Fε|m(x,z1)<η≤m(x,z2)(ψ(0, x, τ))

)= Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Fε|m(x,z1)<η≤m(x,z2)(ψ(0, x, τ))

).

The last step comes from the fact that m(x, zj) = m(x, zj) for j = 1, 2. Note that

P[h(1, x, ε) ≤ h(1, x, ψ(0, x, τ))

∣∣m(x, z1) < η ≤ m(x, z2)]

≥ P[ε ≤ ψ(0, x, τ)

∣∣m(x, z1) < η ≤ m(x, z2)]= Fε|m(x,z1)<η≤m(x,z2)(ψ(0, x, τ)),

which implies


(Fε|m(x,z1)<η≤m(x,z2)(ψ(0, x, τ))

)≤ h(1, x, ψ(0, x, τ)).

Moreover, for any y < h(1, x, ψ(0, x, τ)),

P[h(1, x, ε) ≤ y

∣∣m(x, z1) < η ≤ m(x, z2)]

= P[h(1, x, ε) ≤ h

(1, x, ψ(0, x, τ)

)∣∣m(x, z1) < η ≤ m(x, z2)]

− P[y < h(1, x, ε) ≤ h(1, x, ψ(0, x, τ))

∣∣m(x, z1) < η ≤ m(x, z2)]

< Fε|m(x,z1)<η≤m(x,z2)(ψ(0, x, τ)),

where the last inequality comes from the fact that by A’, for any y < h(1, x, ψ(0, x, τ),

P[y < h(1, x, ε) ≤ h(1, x, ψ(0, x, τ))

∣∣m(x, z1) < η ≤ m(x, z2)]> 0.

Thus, we have that


(Fε|m(x,z1)<η≤m(x,z2)(ψ(0, x, τ))

)= h (1, x, ψ(0, x, τ)) ,

36

which gives us that


(Fh(0,x,ε)|m(x,z1)<η≤m(x,z2)(h(0, x, τ))

)= h (1, x, ψ(0, x, τ)) .

By the definition of ψ(0, x, τ) and condition (ii), there is h (1, x, ψ(0, x, τ)) = h (1, x, τ) for all

τ ∈ [0, 1]. Hence,


(Fh(0,x,ε)|m(x,z1)<η≤m(x,z2)(y)

)= h

(1, x, h−1(0, x, y)

)for all y ∈ Sh(0,x,ε).

For the second step, it is straightforward that the distribution of h(1, x, ε) is identified as

Fh(1,x,ε)(y) = P(Y ≤ y; D = 1|X = x) + P[φx,x(Y) ≤ y; D = 0|X = x

], ∀y ∈ R.

Now we show the identification of h(1, x, ·) from Fh(1,x,ε).

By definition, Qh(1,x,ε)(τ) = inf {y ∈ R : P [h(1, x, ε) ≤ y] ≥ τ}. Because of the weakly mono-

tonicity of h in ε, we have h(1, x, u) ≤ h (1, x, τ) for all u ≤ τ. Therefore, we have that

P [h(1, x, ε) ≤ h (1, x, τ)] ≥ τ.

It follows that Qh(1,x,ε)(τ) ≤ h (1, x, τ).

Moreover, fix arbitrary y < h (1, x, τ). Then

P [h(1, x, ε) ≤ y] = P [h(1, x, ε) ≤ y; ε ≤ τ] = P [ε ≤ τ]−P [ε ≤ τ; h(1, x, ε) > y] < τ.

where the first equality is because h(1, x, ε) ≤ y implies ε ≤ τ, and the inequality comes from

the fact that P [ε ≤ τ; h(1, x, ε) > y] > 0 under A’. Thus, Qh(1,x,ε)(τ) > y for all y < h(1, x, τ).

Hence, Qh(1,x,ε)(τ) = h (1, x, τ). �


Proof. Fix x ∈ SX and x ∈ SX satisfying assumption C’-(i). Let further z1, z2 ∈ SZ|X=x and

z1, z2 ∈ SZ|X=x such that p(x, z1) = p(x, z1) < p(x, z2) = p(x, z2). By the proof of Corollary 1,

we have


(Fh(0,x,ε)|m(x,z1)<η≤m(x,z2)(h(0, x, τ))

)= h (1, x, ψ(0, x, τ)) ≥ h (1, x, τ)

37

where the last inequality comes from the fact that ψ(0, x, τ) ≥ τ. Therefore,


(Fh(0,x,ε)|m(x,z1)<η≤m(x,z2)(y)

)≥ h

(1, x, h−1(0, x, y)

)= φx,x(y)

for all y ∈ Sh(0,x,ε).

For the lower bound, let ϕ(0, x, τ) = inf{e : h(0, x, e) = h(0, x, τ)}. By A’, we have

Kh(0,x,ε)|m(x,z1)<η≤m(x,z2)(h(0, x, τ)) = Fε|m(x,z1)<η≤m(x,z2)(ϕ(0, x, τ)).

Therefore,


(Kh(0,x,ε)|m(x,z1)<η≤m(x,z2)(h(0, x, τ))

)= Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Fε|m(x,z1)<η≤m(x,z2)(ϕ(0, x, τ))

)= Qh(1,x,ε)|m(x,z1)<η≤m(x,z2)

(Fε|m(x,z1)<η≤m(x,z2)(ϕ(0, x, τ))

)= h(1, x, ϕ(0, x, τ)) ≤ h(1, x, τ),

which thereafter provides a lower bound for h(1, x, h−1(0, x, ·)).

Given the interval identification of φx,x(·), the bounds of h(1, x, y) follow a similar argument

of the proof in Corollary 1. �


Proof. The proof simply follows the arguments in Corollaries 1 and 2. �

38

Documents

COUNTERFACTUAL MAPPING AND INDIVIDUAL ... MAPPING AND INDIVIDUAL TREATMENT EFFECTS IN NONSEPARABLE MODELS WITH BINARY ENDOGENEITY* QUANG VUONG† AND HAIQING XU‡ ABSTRACT. This paper