CHAPTER THREE

INTRODUCTION TO SIMULTANEOUS
EQUATION MODELS

By: Habtamu Legese (Asst.Prof) 1

 3.1 Nature of Simultaneous Equation Models
So far we have been discussed by focusing exclusively on the problems
and estimations of a single equation regression models. In such models, a
dependent variable is expressed as a linear function of one or more
explanatory variables.
i.e, there was a single dependent variable Y and one or more
explanatory variables, X’s.
The cause-and-effect relationship in single equation models between the
dependent and independent variable is unidirectional.
An explanatory variable is the expected cause, and it explains the
results. A response variable is the expected effect, and it responds to other
variables.
But there are situations where such one-way or unidirectional causation
in the function is not meaningful. By: Habtamu Legese (Asst.Prof) 2
 Cont.
• This occurs if, for instance, Y (dependent variable) is not
only a function of X’s (explanatory variables) but also all or
some of the X’s are, in turn, determined by Y.

There is, therefore, a two-way flow of influence between Y

and (some of) the X’s which in turn makes the distinction
between dependent and independent variables a little
doubtful.

In a simultaneous model, there is more than one equation

–one for each of the mutually, or jointly, dependent or
endogenous variables.
The number of equations in such models is equal to the
number of jointly dependent or endogenous variables
involved in the phenomenon under analysis.
By: Habtamu Legese (Asst.Prof) 3
 Cont.
 Unlike the single equation models, in simultaneous
equation models, it is not usually possible to estimate a
single equation of the model without taking into
account the information provided by other
equations of the system.
 If one applies OLS to estimate the parameters of each
equation disregarding other equations of the model, the
estimates so obtained are not only biased but also
inconsistent, i.e. even if the sample size increases
indefinitely, the estimators do not converge to their
true values.

By: Habtamu Legese (Asst.Prof) 4

Cont.
Example: the classic example of simultaneous
causality in economics is supply and demand.
Both Prices and quantities adjust until supply
and demand are in equilibrium.
A shock of demand or supply causes both
prices and quantities to move.
As well known, the prices P of a commodity
and quantity Q sold are determined by the
intersection of the demand and supply curves
for that commodity.
By: Habtamu Legese (Asst.Prof) 5
By: Habtamu Legese (Asst.Prof) 6
Cont.

By: Habtamu Legese (Asst.Prof) 7

Cont.

By: Habtamu Legese (Asst.Prof) 8

 Cont.
• The reduced form of a structural model is the model
in which the endogenous variables are expressed as a
function of the predetermined variables and the
error term only.
• Illustration: Find the reduced form of the above
structural model. Since C and Y are endogenous
variables and only Z is the exogenous variable, we
have to express C and Y in terms of Z.

By: Habtamu Legese (Asst.Prof) 9

• To do this substitute Y= C+Z into equation (1).

By: Habtamu Legese (Asst.Prof) 10

Cont.

By: Habtamu Legese (Asst.Prof) 11

Cont.

By: Habtamu Legese (Asst.Prof) 12

 Simultaneity Bias
• Unlike the single equation models, in simultaneous equation
models, it is not usually possible to estimate a single
equation of the model without taking into account the
information provided by other equations of the system.
• If one applies OLS to estimate the parameters of each
equation disregarding other equations of the model, the
estimates so obtained are not only biased but also
inconsistent; i.e. even if the sample size increases
indefinitely, the estimators do not converge to their true
values.
• The bias arising from the application of such a procedure of
estimation which treats each equation of the simultaneous
equations model as though it were a single model is known
as simultaneity bias or simultaneous equation bias.
By: Habtamu Legese (Asst.Prof) 13
 Cont.
It is useful to see, in a simple model, that an
explanatory variable that is determined simultaneously
with the dependent variable is generally correlated with
the error term, which leads to bias and inconsistency
in OLS.
The two-way causation in a relationship leads to a a
violation of the important assumption of linear
regression model, i.e. one variable can be dependent
variable in one of the equation but becomes also an
explanatory variable in the other equations of the
simultaneous-equation model.
In this case E[XiUi] may be different from zero. To
show simultaneity bias, let’s consider the following
simple simultaneous equation model.

By: Habtamu Legese (Asst.Prof) 14

By: Habtamu Legese (Asst.Prof) 15
By: Habtamu Legese (Asst.Prof) 16
By: Habtamu Legese (Asst.Prof) 17
That is, covariance between X and U is not zero.
As a consequence, if OLS is applied to each
equation of the model separately the coefficients
will turn out to be biased.
Now, let’s examine how the non-zero co-variance
of the error term and the explanatory variable will
lead to biasness in OLS estimates of the parameters.

By: Habtamu Legese (Asst.Prof) 18

By: Habtamu Legese (Asst.Prof) 19
 Identification and Estimation of Structural Equations in SEM
Earlier we have said that SEM, unlike linear regression
model, cannot be estimated directly using OLS technique
for it will give us biased and inconsistent estimates.
Rather there are other estimation techniques-like
1.The reduced form method orindirect least squares (ISLS)
2.The method of instrumental variables
3.Two stage least squares (2SLS)
4.Limited information maximum likelihood (LIML)
5.The mixed estimation
6.Three stage least squares
7. Full information maximum likelihood (FIML)
However, a SEM has to first pass the criteria called
identification.
By: Habtamu Legese (Asst.Prof) 20
 Solution to the Simultaneous Equations
 N.B: 1-5---we can applied to one equation at
a time, and 6-7 are the systems methods b/c
they are applied to all equations of the system
simultaneously.
How to estimate the reduced form
parameters?
 The estimates of the reduced from coefficients
(π’s ) may be obtained in two ways.
1. Direct estimation of the reduced
coefficients by applying OLS.
2. Indirect estimation of the reduced form
coefficients. By: Habtamu Legese (Asst.Prof) 21
 Direct estimation of the reduced form coefficients

 Direct Method: Express the three endogenous

variables(Ct , It , and Yt ) as functions of the two
predetermined variables (Gt, andYt-1) directly
using π’s as the parameters of the reduced form
model as follows.
Ct = π11Yt-1 + π12Gt + V1
It , =π21Yt-1 + π22Gt +V2
Yt =π31Yt-1 + π32Gt + V3
Note: π11 , π12 , π21 , π22 , π31 , and π32 are reduced
from parameters.

By: Habtamu Legese (Asst.Prof) 22

 Direct estimation of the reduced form coefficients
 The reduced form π ’s may be estimated by the method of
least- squares – no restriction (LSNR).
 This means we can apply OLS to reduced form equation
because we express all the endogenous variables in terms of
exogenous variables.
 This method of obtaining the π 's is called least squares no
restriction (LSNR) because it doesn't take into consideration
any information on the structural parameters.
 In this method what required is knowledge of the
predetermined variables appearing in the system not about
the coefficients of structural questions.

By: Habtamu Legese (Asst.Prof) 23

 Indirect estimation of the reduced form coefficients
 It is known that there is a relationship between the reduced
form coefficients & the structural parameters (explained in
the table).

 Therefore, to obtain values of coefficients estimate the

structural parameters by any appropriate econometric
techniques and then substitutes these estimates in to the
system of parameters relationships to obtain indirectly.

 This indirect method involved three steps.

By: Habtamu Legese (Asst.Prof) 24

 Cont.
 1st step: Solve the system of endogenous
variables so that each equation contains only
predetermined explanatory variables.
 2nd step: Obtain the estimates of the
structural parameters by any appropriate
econometric method.
 3rd step: Substitute the estimates of β's and γ's
in to the system of parameters relations to find
the estimates of the reduced form coefficients.

By: Habtamu Legese (Asst.Prof) 25

 Recursive models
 A model is called recursive if its structural
equations can be ordered in such a way that:
 the first equation includes only the
predetermined variables in the right hand side.
 the second equation contains predetermined
variables and the first endogenous variable (of
the first equation) in the right hand side and so
on.
 The special feature of recursive model is that its
equations may be estimated, one at a time, by OLS
without simultaneous equations bias.

By: Habtamu Legese (Asst.Prof) 26

 Cont.

 OLS is not applicable if there is interdependence

between the explanatory variables and the error term.
 In the simultaneous equation models, the endogenous
variables may depend on the error terms of the model.
Hence, the OLS technique is not appropriate for
estimation of an equation in a simulations equations
model.
 However, in a special type of simultaneous equations
model called Recursive, Triangular or Causal model, the
use of OLS procedure of estimation is appropriate.
 Consider the following three equation system to
understand the nature of such models:

By: Habtamu Legese (Asst.Prof) 27

 Recursive models

• Consider the following three equation system to understand

the nature of such models:

• In the above illustration, as usual, the X’s and Y’s are

exogenous and endogenous variables respectively. The
disturbance terms follow the following assumptions.

By: Habtamu Legese (Asst.Prof) 28

Cont.
The above assumption is the most crucial
assumption that defines the recursive model.
If this does not hold, the above system is no longer
recursive and OLS is also no longer valid.
The first equation of the above system contains only
the exogenous variables on the right hand side.
Since by assumption, the exogenous variable is
independent of the error term (U) , the first equation
satisfies the critical assumption of the OLS
procedure.
Hence OLS can be applied straight forwardly to this
equation.
By: Habtamu Legese (Asst.Prof) 29
Cont.

By: Habtamu Legese (Asst.Prof) 30

Cont.

By: Habtamu Legese (Asst.Prof) 31

Cont.

By: Habtamu Legese (Asst.Prof) 32

 • The coefficient matrix of endogenous variables is thus a
triangular one; hence recursive models are also called as
triangular models

The coefficient matrix of endogenous variables is thus a triangular one; hence recursive models
are also called as triangular models
By: Habtamu Legese (Asst.Prof) 33
 The Order and Rank Condition of Identification
Problem
• In simultaneous equation models, the Problem of
identification is a problem of model formulation; it
does not concern with the estimation of the model.
• The estimation of the model depends up on the
empirical data and the form of the model. If the
model is not in the proper statistical form, it may turn
out that the parameters may not uniquely estimated even
though adequate and relevant data are available.
• In the language of econometrics, a model is said to be
identified only when it is in unique statistical form to
enable us to obtain unique estimates of its parameters
from the sample data.
By: Habtamu Legese (Asst.Prof) 34
Cont.
• To illustrate the problem identification, let’s consider a simplified
wage-price model. In simultaneous equation models, the
Problem of identification:
 is a problem of model formulation;
 It is not concerned with the estimation of the model because the
estimation of the model depends on the empirical data and the
form of the model.
 In the language of econometrics, a model is said to be identified
only when it is in unique statistical form to enable us to obtain
unique estimates of its parameters from the sample data.

By: Habtamu Legese (Asst.Prof) 35

Cont.
• There are three possible situations of identification:
 Exactly identified
 Over identified
 Under identified
• By observing the correspondence between reduced form and
structural form coefficients, it is possible to determine whether the
given equation is, exactly identified, over-identified or under-
identified as follows;
• An equation is exactly identified if there is a one-to-one
correspondence between reduced form coefficients and structural
form coefficients. We will get a unique solution in this case.
By: Habtamu Legese (Asst.Prof) 36
Cont.
If the number of reduced form coefficients exceeds
that of structural form coefficients, we have over
identification (that is no unique solution)-more
than sufficient information available.
If the number of reduced form coefficients is less
than that of structural form coefficients- under
identification (no solution can be found)-no
sufficient information available.

By: Habtamu Legese (Asst.Prof) 37

Cont.
If the number of reduced form coefficients exceeds
that of structural form coefficients, we have over
identification (that is no unique solution) - more
than sufficient information available.
If the number of reduced form coefficients is less
than that of structural form coefficients - under
identification (no solution can be found) - no
sufficient information is available.

By: Habtamu Legese (Asst.Prof) 38

Formal Rules (Conditions) for Identification
• In applying the identification rules, we should either
ignore the constant term or, if we want to retain it, we
must include in the set of variables a dummy variable (say
X0) which would always take on the value 1.

• Let’s ignore the constant intercept. There are two formal

rules for identification

i) Order condition and

ii) Rank condition for identification.
• Here we shall discuss the order condition.
By: Habtamu Legese (Asst.Prof) 39
 The order condition for identification
• This condition is based on a counting rule of the variables
included and excluded from the particular equation. It is a
necessary but not sufficient condition for the identification of
an equation. The order condition may be stated as follows.
• For an equation to be identified the total number of variables
(endogenous and exogenous) excluded from it must be equal
to or greater than the number of endogenous variables in the
model less one.
• Given that in a complete model the number of endogenous
variables is equal to the number of equations of the model, the
order condition for identification is sometimes stated in the
following equivalent form.
By: Habtamu Legese (Asst.Prof) 40
The order condition of identification
• Let G be the number of endogenous variables in the system and let
k be the total number of variables (both endogenous and exogenous)
missing from the equation under consideration, then if;
• a) k = G-1, the equation is exactly identified
• b) k >G-1, the equation is over identified
• c) k <G-1, the equation is under-identified
• Where, k = number of total variables in the model (endogenous
and predetermined) minus the number of variables, endogenous and
exogenous, included in a particular equation.
• The order condition is a necessary but not sufficient condition for
identification.
By: Habtamu Legese (Asst.Prof) 41
 Cont.
• Then the order condition for identification may be symbolically
expressed as:
k  (G  1)
excluded 
 var iable   total number of equatioins  1
 
Examples: State identifiability status of each the following equation using order condition stated
above.
) If a system contains 10 equations with 15 variables, ten endogenous and five exogenous, an equation
containing 11 variables. For the equation we have,
G  10 K  15 M  11
Order condition:
( K  M )  (G  1)
(15  11)  (10  1) ;that is, the order condition is not satisfied and thus, not identified.

By: Habtamu Legese (Asst.Prof) 42

Thank You!

By: Habtamu Legese (Asst.Prof) 43