Scribd
Upload
80 views2 pages

Answer To The Question Case 2

This document discusses spurious regression, which occurs when trending variables that are not truly related are regressed against each other. Spurious regression will often produce statistically significant results but no true relationship exists between the variables. Two examples of spurious regression are provided. The document also discusses how cointegration tests can determine if a relationship is spurious or if a long-term relationship exists between trending variables.

Uploaded by

Santo Saha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
80 views2 pages

Answer To The Question Case 2

This document discusses spurious regression, which occurs when trending variables that are not truly related are regressed against each other. Spurious regression will often produce statistically significant results but no true relationship exists between the variables. Two examples of spurious regression are provided. The document also discusses how cointegration tests can determine if a relationship is spurious or if a long-term relationship exists between trending variables.

Uploaded by

Santo Saha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Answer to the question Case 2

The regression is spurious when we regress one random walk onto another independent random
walk. It is spurious because the regression will most likely indicate a non-existing relationship
where the coefficient estimate will not converge toward zero (the true value). Instead, in the limit
the coefficient estimate will follow a non-degenerate distribution. The t value most often is
significant. R2 is typically very high. So, If a trending variable is regressand on one or more
trending variables we often find significant t and F statistics and a high R2, But there is no true
relationship between them because each variable is growing over time. This is known as the
problem of spurious or False regression. Here are some examples of spurious regression :

1.Us export index(Y) ,1960-1990, annual data,on Australian males life expectancy(x)

Y= -2943 + 45.7974x, R2=0.916, D/W = 0.3599, F = 315.2


(-16: 70)(17.76). Corr = 0.9570

2. Suppose we regress Y t on Xt. Since Y t and Xt are uncorrelated l(1) processes, the R2 from the
regression of Y on X should tend to zero; that is, there should not be any relationship between
the two variables. But wait till you see the regression results:

Variable Coefficients Std. Error t-statistic

C -13.2556 0.6203 -21.36856

X 0.3376 0.0443 7.61223

R2=0.1044. d=0.0121

As you can see, the coefficient of X is highly statistically significant, and, although the R2 value
is low, it is statistically significantly different from zero. From these results, you may be tempted
to conclude that there is a significant statistical relationship between Y and X, whereas a priori
there should be none. This is in a nutshell the phenomenon of spurious or nonsense regression.

(i) If per capita disposable income increases by 1%, holding all other things constant, on an
average per capita Consumption will increase by 0.77%. The regression coefficients are
individually statistically highly significant, for their p values ​are quite low. Economically
speaking, two variables will be cointegrated if they have a long-run, or equilibrium, relationship
between them. In the present context economie theory tells us that there is a strong relationship
between consumption,expenditures and personal disposable income. Here, PCE is about 77% of
PD1 .
(ii) No, this is not a Spurious regression model.
Here, the population regression model is,
LPCEt = B1+B2LPDI+B3t+Mt and Mt = LPCEt-B1-B₂LPDI-B3t
suppose we subject the estimated Mt to unit root analysis and find that it is stationary , that is, it
is l(0). This is an intriguing situation, for although the log of PCE and log of PDI are
individually l(1), that is, that they have stochastic trends, their (linear) combination is l(0). This
linear combination cancels out the stochastic trends in the two series.In that case the regression
of LPCE and LPDI is not spurious. If this happens, we say that the variables LPCE and LPDI are
cointegrated.

(iii) The output of lower part test of whether LPCE and LPDI are cointegrated which means they
have a long term relationship between them.
Here, K= contegrating parameters
H0;k=0 [S3 has a unit root]
H1;k>0 [S3 does not have a unit root]
From the lower part test, the output clearly shows that the residuals from regression are
stationary. The computed tau value of the lagged residual term [ss(-1)] which is -
3.392603(absolute form) far exceed, ADE test 1%, 5%, 10% level, the critical value of the table
S. The tau test is greater than the ADF or AEG test critical value. So the null hypothesis is
rejected. Secondly there is a relationship between LPDI and LPCE. So they are cointegrated.

(iv) Difference between the chit root and cointegration tests: Tests for unit roots are performed
on single time series, whereas cointegration deals with the relationship among a group of
variables, each having a unit root.

You might also like