3/13/2025 Henok s

Introduction
In all the chapters discussed so far, we have been focusing exclusively with the
problems and estimations of a single equation regression models.
 In such models, a dependent variable is expressed as a function of one or more explanatory
variables.
The cause-and-effect relationship in such models between the dependent and independent
variable is unidirectional.
 That is, the explanatory variables are the cause and the dependent variable is the effect.
 But there are situations where such one-way or unidirectional causation in the
function is not meaningful.
 This occurs if, for instance, Y (dependent variable) is not only function of X’s (explanatory
variables) but also all or some of the X’s are, in turn, determined by Y.

3/13/2025 Henok s
 Con…
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.
Under such circumstances, we need to consider more than one regression
equations; one for each interdependent variables to understand the multi-flow of
influence among the variables.
This is precisely what is done in simultaneous equation models.

3/13/2025 Henok s
 Con…
The number of equations in such models is equal to the number of jointly
dependent or endogenous variables involved in the phenomenon under analysis.
Unlike the single equation models, in simultaneous equation models it is not
usually possible (possible only under specific assumptions) to estimate a single
equation of the model without taking into account the information provided
by other equation 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.
3/13/2025 Henok s
 Definitions of Some Concepts
Endogenous and Exogenous Variables
In simultaneous equation models variables are classified as
Endogenous and
Exogenous.
The traditional definition of these terms is that endogenous variables are
variables that are determined by the economic model (within the system) and
Exogenous variables are those determined from outside. Exogenous variables
are also called predetermined.

3/13/2025 Henok s
 Con…
Predetermined groups can be divided into two categories which are
considered in general as exogenous variables. These are:
Current and lagged exogenous and
Lagged endogenous.
For instance; Xt and Xt-1 depict the current and lagged exogenous variables
and Yt-1 depicts lagged endogenous variable.
 This is on the assumption that X’s symbolize the exogenous variables and Y’s symbolize
the endogenous variables.
Thus, Xt , Xt-1 and Yt-1 are regarded as predetermined (exogenous) variables.
Since the exogenous variables are predetermined, they are supposed to be
independent of the error terms in the model.
3/13/2025 Henok s
 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 cause both prices and quantities to move.
As well known, the prices of a commodity and quantity sold are
determined by the intersection of the demand and supply curves for the
commodity.
Look at the graph of demand and supply from micro economics book

3/13/2025 Henok s
 Con…
Thus , assuming for simplicity that the demand and supply curves are linear and
adding the stochastic term 𝑼𝟏 and 𝑼𝟐 , we may write the empirical DD and SS
function as:
𝑸𝒅 = 𝜷𝟏 𝑷 + 𝜷𝟐 𝒀 + 𝑼𝟏 ……………….(1)
𝑸𝒔 = 𝜶𝟎 + 𝜶𝟏 𝑷 + 𝜶𝟐 𝑹 + 𝑼𝟐 … … … … (2)
Where; Q=quantity, Y=income, P=price, R=Rainfalls, U1 &U2 are error terms.
Here P and Q are endogenous variables and Y and R are exogenous variables.
Equilibrium condition: 𝑸𝒅 =𝑸𝒔

3/13/2025 Henok s
 Con…
Because of simultaneous dependence between quantity and price, then 𝑼𝟏
and p, and 𝑼𝟐 and p can’t be independent.
If 𝑼𝟏 in above equation changes because changes in other variables affecting
quantity such as income, wealth and testes), the demand curve will shift
upward if 𝑼𝟏 is +ve and downward if 𝑼𝟏 is negative.
Thus, shifts in demand curve change both P and Q.
Similarly, a change in 𝑼𝟐 because of weather, import or export restriction,
etc; will shift the ss curves, again affect both P and Q.
Because of this simultaneous dependence hence Q and P, 𝑼𝟏 and, P and 𝑼𝟐
and, P can’t independent. Thus, a regression of Q and P as in above equation
would violate an important assumptions of classical linear regression model:
namely the assumption of no correlation between the explanatory
variable(s) and the disturbance term.
3/13/2025 Henok s
 Structural Models
A structural model describes the complete structure of the relationships
among the economic variables.
Structural equations of the model may be expressed in terms of endogenous
variables, exogenous variables and disturbances (random variables).
The parameters of structural model express the direct effect of each explanatory
variable on the dependent variable.
 Variables not appearing in any function explicitly may have an indirect effect and is
taken into account by the simultaneous solution of the system.

3/13/2025 Henok s
 Con…
For instance, a change in consumption affects the investment indirectly and is
not considered in the consumption function.The effect of consumption on
investment cannot be measured directly by any structural parameter, but is
measured indirectly by considering the system as a whole.
Example:The following simple Keynesian model of income determination can be
considered as a structural model.
C = 𝜶 + 𝜷Y + U……………………(3)
Y = C + Z…………………………(4)
For 𝜶 > 0 and 0 < 𝜷 < 1
Where: C=consumption expenditure, Z=non-consumption expenditure Y=national income, C and Y
are endogenous variables while Z is exogenous variable.
3/13/2025 Henok s
 Reduced form of the model
The reduced form of a structural model is the model in which the endogenous
variables are expressed a function of the predetermined variables and the
error term only.
Illustration: Find the reduced form of the previous slide Keynesian structural model
(equation 3 and 4)
Since C and Y are endogenous variables and only Z is the exogenous variables, we
have to express C and Y in terms of Z. To do this substitute Y=C+Z into
equation (3).

3/13/2025 Henok s
 Con…
C     (C  Z ) + U
C    C  Z  U

C  C    Z  U
C (1   )    Z  U

    U
C    Z  ----------------(5)
1  1   1 

Substituting again (5) into (4) we get;

  1  U
Y   Z  -------------------(6)
1  1   1 

Equation (5) and (6) are called the reduced form of the structural model of the above.
We can write this more formally as:
3/13/2025 Henok s
 Con…
Structural form equations Reduced form equations

C    Y  U     U
C  
1  
 Z 
1    1 

Y CZ   1  U
Y  
1  
 Z 
1    1 

 Parameters of the reduced form measure the total effect (direct and indirect) of
a change in exogenous variables on the endogenous variable.
  
 For instance, in the above reduced form equation(5), 
1  
 measures the
 
total effect of a unit change in the non-consumption expenditure on
 1 
consumption. This total effect is  , the direct effect, times 
1  
 ,the
 
indirect
3/13/2025 effect. Henok s
 Con…
After simple algebraic manipulation,
Yt = 𝝅𝟐 + 𝝅𝟑 Zt + Wt
𝛼 1 𝑈
Where, 𝝅𝟐 = , 𝝅𝟑 = , 𝑾𝒕 =
1−𝛽 1−𝛽 1−𝛽
This reduced form indicates the endogenous variable Y solely as a function of the
exogenous variable Z and the stochastic disturbance term u. 𝝅𝟐 and 𝝅𝟑 are the
associated reduced form coefficients. Notice that these reduced form coefficients are
nonlinear combinations of the structural coefficients.
If in the preceding Keynesian model the non-consumption expenditure is increased by,
say $1 and if the MPC is assumed to be 0.8, then we obtain 𝝅𝟑 =5. this result means
that increasing the non consumption by $1 will immediately lead to an increase in
income of $5.
3/13/2025 Henok s
 Con…
After simple algebraic manipulation,
Ct = 𝝅𝟎 + 𝝅𝟏 Zt + Wt
𝛼 𝛽 𝑈
Where, 𝝅𝟎 = , 𝝅𝟏 = , 𝑾𝒕 = ,
1−𝛽 1−𝛽 1−𝛽
The reduced form coefficients, such as 𝝅𝟎 and 𝝅𝟏 are also known as impact,
or short run, multipliers, because they measure the immediate impact on the
endogenous variable of a unit change in the value of the exogenous variable.
The preceding Keynesian consumption model shows that 𝝅𝟏 =4, meaning that
$1 increasing non consumption expenditure will lead immediately to $4
increase in consumption expenditure.

3/13/2025 Henok s
 How to estimate the reduced form parameters?
The estimates of the reduced from coefficients (p’s ) may be obtained in two ways.
I. Direct estimation of the reduced coefficients by applying OLS.
II. Indirect estimation of the reduced form coefficients:

3/13/2025 Henok s
 Direct estimation of the reduced coefficients
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 variable
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.
3/13/2025 Henok s
 Indirect estimation of the reduced form coefficients
It is known that there is a relationship between the reduced form
coefficients and 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.

3/13/2025 Henok s
 Indirect estimation of the reduced form coefficients
This indirect method involved three steps
1st step: solve the system of endogenous variable so that each equation
contains only predetermined explanatory variable.
2st step: obtain the estimates of the structural parameters by any
appropriate econometric model.
3st step: substitute the estimates of 𝛼’s and 𝛽 ’s in to the system of
parameters relations to find the estimates of the reduced form
coefficients.

3/13/2025 Henok s
 The 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 a 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.
3/13/2025 Henok s
 Con…
Identification problems do not just arise only on two equation-models.
Using the above procedure, we can check identification problems easily if we have
two or three equations in a given simultaneous equation model.
However, for ‘n’ equations simultaneous equation model, such a procedure
is very cumbersome.
In general for any number of equations in a given simultaneous equation, we have
two conditions that need to be satisfied to say that the model is in general
identified or not.
In the next slide section we will see the formal conditions for identification.

3/13/2025 Henok s
 Formal Rules (Conditions) for Identification
Identification may be established either by the examination of the
specification of the structural model, or by the examination of the reduced form of
the model.
Traditionally identification has been approached via the reduced form.
Actually the term ‘identification’ was originally used to denote the possibility
(or impossibility) of deducing the values of the parameters of the structural
relations from a knowledge of the reduced form parameters. In this section we
will examine structural approaches.
However, we think that the reduced form approach is conceptually
confusing and computationally more difficult than the structural model
approach,
Because it requires the derivation of the reduced from first and then examination of the values
of the determinant formed form some of the reduced form coefficients.
The structural form approach is simpler and more useful.
3/13/2025 Henok s
 Con…

• 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:

 Either convention leads to the same results as far as identification is concerned.

 In this chapter, we will ignore the constant intercept.

3/13/2025 Henok s
Establishing Identification from the Structural Form of the Model

There are two conditions which must be fulfilled for an equation to be

identified.
1. The order condition for identification
2. The rank condition for identification

3/13/2025 Henok s
 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.

3/13/2025 Henok s
 Con…
For an equation to be identified the total number of variables excluded from it but included
in other equations must be at least as great as the number of equations of the system less one.
Let: G = total number of equations, K= number of total variables in the model (endogenous and
predetermined) M= number of variables, endogenous and exogenous, included in a particular
equation.
Then the order condition for identification may be symbolically expressed as:

3/13/2025 Henok s
 Con…
Example 1, if a system contains 10 equations with 15 variables, ten endogenous and five exogenous,
an equation containing 11 variables is not identified, while another containing 5 variables is
identified.
For the first equation we have
G = 10 K = 15 M = 11
Order condition
(K -M) ≥ (G - 1) ; that is, the order condition is not satisfied.
(15 - 11) < (10 - 1)

3/13/2025 Henok s
Example 2. Assume the following simple version of the Keynesian

model of income determination.

Consumption function: Ct  a0  a1Yt  a2Tt  u

Investment function: I t  b0  b1Yt 1  u

Taxation function: Tt  c0  c1Yt  w

Definition: Yt  Ct  I t  Gt

3/13/2025 Henok s
 There are six variables in the model (K=6) and four equations (G=4). The
consumption function contains three variables (M=3).
(K-M)=3 and (G-1)=3
 Thus (K-M)=(G-1), which shows that the order condition for identification is
satisfied.
 The investment function includes two variables. Hence
K-M = 6-2
 Clearly (K-M) > (G-1), given that G-1=3. The order condition is fulfilled.
3/13/2025 Henok s
 The rank condition for identification
The rank condition states that in a system of G equations any particular
equation is identified
If and only if it is possible to construct at least one non-zero determinant of order (G-1)
from the coefficients of the variables excluded from that particular equation but
contained in the other equations of the model.
The practical steps for tracing the identifiablity of an equation of a structural
model may be outlined as follows.
Firstly. Write the parameters of all the equations of the model in a separate table, noting
that the parameter of a variable excluded from an equation is equal to zero.

3/13/2025 Henok s
 Con…
For example let a structural model be:
y1 = 3y2 - 2x1 + x2 + u1
y2 = y3 + x3 + u2
y3 = y1 - y2 - 2x3 + u3
Where the y’s are the endogenous variables and the x’s are the predetermined variables.
This model may be rewritten in the form
- y1 + 3y2 + 0 y3 - 2x1 + x2 + 0x3 + u1 = 0
0 y1 - y2 + y3 + 0x1 + 0x2 + x3 + u2 = 0
y1 - y2 - y3 + 0x1 + 0x2 - 2x3 + u3 = 0

3/13/2025 Henok s
 Con…
Ignoring the random disturbance the table of the parameters of the model is as follows:

Variables

Equations Y1 Y2 Y3 X1 X2 X3

1st equation -1 3 0 -2 1 0

2nd equation 0 -1 1 0 0 1

3rd equation 1 -1 -1 0 0 -2
3/13/2025 Henok s
 Con…
Secondly. Strike out the row of coefficients of the equation which is being
examined for identification.
For example, if we want to examine the identifiability of the second equation of the model
we strike out the second row of the table of coefficients.
Thirdly. Strike out the columns in which a non-zero coefficient of the
equation being examined appears. By deleting the relevant row and columns we
are left with the coefficients of variables not included in the particular equation,
but contained in the other equations of the model.
For example, if we are examining for identification the second equation of the
system, we will strike out the second, third and the sixth columns of the previous slide
table, thus obtaining the next slide tables.

3/13/2025 Henok s
 Con…
Table of structural parameters Table of parameters of excluded variables
Y 1 Y 2 Y 3 X1 X 2 X3 Y1 X1 X2

1st -1 3 0 -2 1 0 -1 -2 1
2nd 0 -1 1 0 0 1

3rd 1 -1 -1 0 0 -2 1 0 0
3/13/2025 Henok s
 Con…
Fourthly. Form the determinant(s) of order (G-1) and examine their value. If
at least one of these determinants is non-zero, the equation is identified.
If all the determinants of order (G-1) are zero, the equation is
underidentified.
In the previous slide example of exploration of the identifiability of the
second structural equation we have three determinants of order (G-1)=3-1=2.
They are:
−𝟏 −𝟐 −𝟐 𝟏 −𝟏 𝟏
𝑫𝟏 = ≠𝟎 𝑫𝟐 = = 𝟎 𝑫𝟏 = ≠𝟎
𝟏 𝟎 𝟎 𝟎 𝟏 𝟎
(The symbol D stands for ‘determinant’) We see that we can form two non-zero
determinants of order G-1=3-1=2; hence the second equation of our system is
identified.
3/13/2025 Henok s
 Con…
Fifthly. To see whether the equation is exactly identified or over identified
we use the order condition (K - M ) ≥ (G - 1). with this criterion, if the
equality sign is satisfied, that is if (K - M ) = (G - 1) , the equation is exactly
identified. If the inequality sign holds, that is, if (K - M ) > (G - 1) , the
equation is over identified.
In the case of the second equation we have:
G=3 K=6 M =3
And the counting rule (K - M ) ≥ (G - 1) gives
(6-3) > (3-1)
Therefore the second equation of the model is over identified
3/13/2025 Henok s
 Con…

The identification of a function is achieved by assuming that some variables

of the model have zero coefficient in this equation, that is, we assume that some
variables do not directly affect the dependent variable in this equation.

3/13/2025 Henok s
 Implications Of Identification
If an equation (model) is under-identified it is impossible to estimate all its
parameters with any econometric technique.
If an equation (model) is identified in general its coefficients can be estimated.
The appropriate estimation technique will depend upon whether it is exactly
identified or over-identified.

3/13/2025 Henok s
Indirect least squares and 2SLS estimation of structural equations

If there is no simultaneous equation, or simultaneity problem, the OLS

estimators produce consistent and efficient estimators.
On the other hand, if there is simultaneity, OLS estimators are not even
consistent. In the presence of simultaneity, the methods of two-stage least
squares (2SLS) and Indirect Least squares will give estimators that are
consistent and efficient.

3/13/2025 Henok s
 Indirect Least Squares (ILS)

 Estimating structural parameters by transforming the reduced form parameters.

 For just or exactly identified structural equation, the method of obtaining the estimates of
the structural coefficients from the OLS estimators of the reduced form coefficients is
known as the method of indirect least squares (ILS).
 Indirect Least Squares: the procedure of backing out the structural parameters from
reduced form equations.
 To conduct ILS, the structural parameters must be identified.

3/13/2025 Henok s
 Con…
Steps to Indirect Least Squares:
1. Algebraically rewrite the structural equations in reduced form.
2. Estimate the reduced form equations.
3. Algebraically calculate formulas for each structural parameter in terms of the reduced form
parameters.
4. Compute the formulas using the reduced form estimates.

3/13/2025 Henok s
 Two SLS estimation of structural equations

 This method is applied in estimating an over identified equation.

 2-SLS is equivalent to ILS in the just-identified case, it is usually applied uniformly to all
identified equations in the system.

 The 2-SLS procedure is generally applicable for estimation of over-identified

equations as it provides unique estimators.

3/13/2025 Henok s
3/13/2025 Henok s
 Assumption of two stage least squares

1. The disturbance term of the original structural equation must satisfy the
stochastic assumption of zero mean, constant variance and zero covariance.
2. The error term of the reduced form equation must satisfy the stochastic
assumption of zero mean, constant variance and zero covariance.
 These assumptions are fulfilled as soon as the random term of all structural equations
satisfy these conditions.
 This is because the error term of the reduced form equation are linear function of the
disturbance term of the original structural equation.

3/13/2025 Henok s
 Con…
3. The explanatory variables are not perfectly multicollinearity.
4. It is assumed that the samples is large so that the number of observation is
greater than the number of predetermined variables in the structural system.
 If the sample size is small in relation to the total number of exogenous variables, it may not be
possible to obtain significant estimates of the reduced form coefficients when applying ordinary
least square at the first stage.

3/13/2025 Henok s
 Properties of 2SLS

1. For small samples the estimates are biased.

 However, for large sample size the bias trends zero.
oThat means, the 2SLS estimates are asymptotically unbiased.
2. The 2SLS estimates are consistent.
 As the sample size increase, the average value of the estimates approaches to the true parameter.
oThat means, as the sample size increase, the estimator become unbiased estimator.

3/13/2025 Henok s
 Con…
The bias arising from application of such 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.
To avoid this bias we will use other methods of estimation, such as,
Indirect Least Square (ILS) and
Two Stage Least Square (2SLS.

3/13/2025 Henok s