Professional Documents
Culture Documents
Existence and
Forecasting the
Fisher Effect in
Malaysia and
Canada
BSc Banking and
Finance
073604149
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
1.0 Introduction
2
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
Canada is.
it=rt+ π et
3
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
The nominal interest rate can be divided into two parts, the ex
ante real interest rate ret, and the expected inflation π et. This was
proposed by Fisher (1930). Using this, the fisher effect can be
written as it= ret + πte . It is possible that the expected inflation may
be different from actual inflation. The errors are said to be
stationary, both types of interest rates have similar properties when
they differ by a stationary factor, therefore:
4
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
In the paper ‘Is there really the Fisher effect’ written by Paul
A. Johnson, Johnson writes about how the cointegration of the
inflation and nominal interest rates is constant with any theory
implying a stationary interest rate and therefore is not a sufficient
condition for the fisher effect to hold.
Mishkin also wrote a paper ‘Is the Fisher effect for real’ where
he found support for the long-run fisher relationship where inflation
and interest rates are cointegrated. In his later paper he found that
both interest rate and inflation contained unit roots and the rest
indicated that there was evidence of long run fisher effect but none
for short run fisher effect. His paper solves the problem of why
strong fisher effect occurs only in some periods and not others by
re-examining the relationship between inflation and interest rates
with modern techniques. Mishkin was one of the first to use the
Engle-Granger concept of Cointegration successfully.
5
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
6
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
5.0 Analysis
7
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
There are many tests that you could do to check if the data is
normally distributed, one test is to plot your data into a histogram
and to see if is normally distributed with this graphical method. The
results are summerised in the table below and the histograms are in
the appendix.
Skewnes Kurtosi Probabilit
s s Jarque-Bera y
-
2.36640 9.1556
Log Cpi Canada 4 52 150.7288 0.000000
-
2.80282 12.976
Dlog Cpi Canada 8 33 321.9201 0.000000
-
Log Cpi 0.02855 2.2371
Malaysia 7 3 1.438698 0.487069
Dlog Cpi 1.35061 9.7526
Malaysia 8 28 127.8287 0.000000
Log nominal 0.04142 1.6208
Canada 2 1 4.772571 0.091971
-
Dlog nominal 0.47913 3.3482
Canada 3 32 2.555537 0.278658
Log nominal 2.1788
Malaysia 0.66748 07 6.038844 0.048829
-
Dlog nominal 1.25569 10.050
Malaysia 7 03 135.3577 0.000000
8
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
9
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
8 2
- -
Trend and 3.49066 3.49214
logcpi_mly intercept -2.61554 2 -5.85026 9
- -
Trend and 3.48922 3.48922
logcpi_can intercept -1.75387 8 -4.34684 8
And as you can see in 1st difference the t-statistic is smaller than the
critical value of 5% which shows that the data is stationary.
Stationary is when the statistical properties of a time series’ data,
such as mean and variance, are all constant over time. We are
given an idea for finding appropriate forecasting models whilst
making data stationary. Having stationary data makes extrapolation
more valid when using statistical findings. I could have also used the
Phillips Perron test, which would have done the same thing.
10
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
5.5 Cointegration
11
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
Obs*R-
squared Prob Chi2 value
Canad 0.000 11.07049
a 21.2838 0 769
Malays 0.000 11.07049
ia 8.064592 0 769
So if the R2 value is less than or equal to the Chi squared then you
can not reject the null hypothesis, therefore it is heteroskedasticity.
12
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
F- F-
statisti statistics(Ch Prob.
c ow) F
Canad 39.217 12.85481 0.00
a from 99 00
13
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
2005
Q1
Malays 87.970
ia from 09
2005Q 0.00
1 9.423081 00
So if you look at the ‘prob f’ number, for both the output for the
chow test says its 0.0000 for both regression then this means that
there is a high margin of error, so in other words the regression will
be very inaccurate in forecasting future figures. The figure closest to
one means it will be a better forecaster. I have tried various
different years, and I get the same results, the errors could have
occurred from a number of things, this could be because in
inaccurate data, or because I tried to forecast before the financial
crisis and the data I have for that period may have been impaired.
6 Conclusion
14
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
univariate. However I have seen papers and journals that used the
Johansen test for the fisher effect and with univariable data. And an
alternative unit root test I could have done is the Phillips Perron.
And I would have done another forecasting test to just verify the
forecasting accuracy of my regression, and to compare the two
forecasters. I would do this because for the chow forecasting I saw
that both of the regressions are very poor forecasters to predict
future values.
If I were to make changes to this project, I would pick more
variables to make my model multivariate and try the Johnsen test,
because I have heard that it is more sophisticated to use than the
Engle Granger, and gives more of an accurate result. And I would
have chosen two very different countries, for example a developing
country, for example India and a well developed country like the
United Kingdom to see and compare them. Also what would be
interesting to see in these very different countries, that in quarterly
data, how the holidays for the countries may affect the results. For
example in the UK it is a highly Christian populated country so in the
final quarter when Christmas and in the second quarter when Easter
takes place, to see if this has any significance on the results, and
India is a high number of Hindus, and to see whether the results
change in corresponding to their holidays and festivals.
I would have also changed the CPI data, and find another
source to show inflation, because I read that even though I can find
out inflation from calculating the log of CPI, I could get slightly
different results from another source for example if I found the
inflation from the countries GDP data then I might have got different
results, for example my data may not have been stationary at any
point, or may result into the regression being a better forecaster
with a low probability of errors.
Also I think if I had more practice and experience in using
eviews or any other econometrics software, I could execute and
15
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
interpret more tests and to get better results and more accurate
results.
16
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
02 33 7 667 7
1999q 90.34 93.16666
03 2.837 3 667 4.719
1999q 2.734 90.77 93.76666
04 67 39 667 4.865
2000q 2.747 91.51 94.36666 5.1346
01 33 18 667 7
2000q 2.757 91.54 5.5836
02 33 24 94.8 7
2000q 91.66 95.66666 5.6036
03 2.989 48 667 7
2000q 92.27 5.6373
04 2.951 65 96.7 3
2001q 92.91 96.93333
01 2.85 88 333 4.85
2001q 2.807 92.97
02 33 99 98.2 4.351
2001q 92.91 98.23333 3.6243
03 2.79 88 333 3
2001q 2.721 93.37 97.73333 2.2476
04 33 76 333 7
2002q 2.729 94.26 98.43333 2.1263
01 67 45 333 3
2002q 2.724 94.78
02 67 45 99.5 2.59
2002q 94.84 2.8903
03 2.725 57 100.6 3
2002q 95.02 101.4666
04 2.749 92 667 2.736
2003q 2.796 95.48 102.7666 2.9386
01 33 8 667 7
2003q 2.781 95.64 102.2333 3.1883
02 33 09 333 3
2003q 2.803 95.79 102.7666 2.7016
03 33 38 667 7
2003q 2.772 95.76 2.6516
04 33 32 103.2 7
2004q 96.37 2.1276
01 2.53 49 103.7 7
2004q 2.546 96.74 2.0013
02 67 2 104.5 3
2004q 97.20 104.7666
03 2.457 07 667 2.212
2004q 2.049 98.17 105.5666 2.5386
04 5 95 667 7
2005q 2.347 98.69 105.9666 2.4823
01 5 13 667 3
17
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
18
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
Appendix of outputs
Comparison of original data and transformed data.
120 12
CPI MLY CPI Can
LOGCPI_MLY LOGCPI_CAN
10
110
8
100 6
4
90
2
80
0
70 -2
1996 1998 2000 2002 2004 2006 2008 1996 1998 2000 2002 2004 2006 2008
140 12
Nominal Can Nominal MLY
LOGNOMINAL_CAN LOGNOMINAL_MLY
120 10
100
8
80
6
60
4
40
2
20
0 0
1996 1998 2000 2002 2004 2006 2008 1996 1998 2000 2002 2004 2006 2008
19
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
16
Series: LOGCPI_CAN
14 Sample 1995Q1 2009Q4
Observations 60
12
Mean 1.124237
10 Median 1.293021
Maximum 2.078191
8 Minimum -1.514128
Std. Dev. 0.723547
6
Skewness -2.366404
Kurtosis 9.155652
4
Jarque-Bera 150.7288
2
Probability 0.000000
0
-1 0 1 2
Dlogcpi Canada
20
Series: DLOGCPI_CAN
Sample 1995Q1 2009Q4
16 Observations 59
Mean -0.060887
12 Median -0.008358
Maximum 0.199625
Minimum -1.136532
8 Std. Dev. 0.221683
Skewness -2.802828
Kurtosis 12.97633
4
Jarque-Bera 321.9201
Probability 0.000000
0
-1.2 -1.0 -0.8 -0.6 -0.4 -0.2 -0.0 0.2
20
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
10
Series: LOGCPI_MLY
Sample 1995Q1 2009Q4
8 Observations 59
Mean 4.546965
6 Median 4.551606
Maximum 4.743148
Minimum 4.355104
4 Std. Dev. 0.103172
Skewness -0.028557
Kurtosis 2.237130
2
Jarque-Bera 1.438698
Probability 0.487069
0
4.4 4.5 4.6 4.7
Dlogcpi malaysia
14
Series: DLOGCPI_MLY
12 Sample 1995Q1 2009Q4
Observations 58
10
Mean 0.006290
Median 0.005852
8
Maximum 0.040298
Minimum -0.015804
6 Std. Dev. 0.007680
Skewness 1.350618
4 Kurtosis 9.752628
2 Jarque-Bera 127.8287
Probability 0.000000
0
-0.01 0.00 0.01 0.02 0.03 0.04
21
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
10
Series: LOGNOMINAL_CAN
Sample 1995Q1 2009Q4
8 Observations 60
Mean 4.606131
6 Median 4.605655
Maximum 4.747537
Minimum 4.465142
4 Std. Dev. 0.090665
Skewness 0.041422
Kurtosis 1.620810
2
Jarque-Bera 4.772571
Probability 0.091971
0
4.45 4.50 4.55 4.60 4.65 4.70 4.75
10
Series: DLOGNOMINAL_CAN
Sample 1995Q1 2009Q4
8 Observations 59
Mean 0.004786
6 Median 0.004821
Maximum 0.012983
Minimum -0.008128
4 Std. Dev. 0.004417
Skewness -0.479133
Kurtosis 3.348232
2
Jarque-Bera 2.555537
Probability 0.278658
0
-0.005 0.000 0.005 0.010
22
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
24
Series: LOGNOMINAL_MLY
Sample 1995Q1 2009Q4
20
Observations 59
16 Mean 1.261041
Median 1.094939
Maximum 2.183689
12 Minimum 0.640801
Std. Dev. 0.389120
8 Skewness 0.667480
Kurtosis 2.178807
4 Jarque-Bera 6.038844
Probability 0.048829
0
0.6 0.8 1.0 1.2 1.4 1.6 1.8 2.0 2.2
Dlognominal malaysia
24
Series: DLOGNOMINAL_MLY
Sample 1995Q1 2009Q4
20
Observations 58
16 Mean -0.016226
Median -0.001790
Maximum 0.400521
12 Minimum -0.558589
Std. Dev. 0.124558
8 Skewness -1.255697
Kurtosis 10.05003
4 Jarque-Bera 135.3577
Probability 0.000000
0
-0.6 -0.4 -0.2 -0.0 0.2 0.4
23
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
24
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
25
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
Cointegration
White Test
White test for Canada:
15.6675
F-statistic 5 Prob. F(2,57) 0.0000
21.2838 Prob. Chi-
Obs*R-squared 0 Square(2) 0.0000
Scaled 61.3658 Prob. Chi-
explained SS 7 Square(2) 0.0000
Test Equation:
Dependent Variable: RESID^2
Method: Least Squares
Date: 04/17/10 Time: 23:30
Sample: 1995Q1 2009Q4
Included observations: 60
Coefficie
Variable nt Std. Error t-Statistic Prob.
1091.27
C 4 298.0955 3.660821 0.0006
-
LOGNOMINAL_C 477.829 -
AN 0 129.4198 3.692087 0.0005
LOGNOMINAL_C 52.2983
AN^2 0 14.04255 3.724274 0.0005
26
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
Test Equation:
Dependent Variable: RESID^2
Method: Least Squares
Date: 04/17/10 Time: 23:32 Regression
Regression
Sample: for Canada:
1995Q1 2009Q3
Included observations: 59
Dependent Variable: LOGCPI_CAN
Coefficie
Method: Least Squares
Date:Variable
04/17/10 Time: 23:10nt Std. Error t-Statistic Prob.
Sample: 1995Q1 2009Q4
Included observations: 60-
0.03053 -
C
Variable 8 0.012416
Coefficie Std. Error 2.459677
t-Statistic 0.0170
Prob.
LOGNOMINAL_M 0.05665 nt
LY 0 0.019105 2.965162 0.0044
C 22.6717- 3.911218 5.796597 0.0000
LOGNOMINAL_M 0.02031 5 -
LOGNOMINAL_C
LY^2 6- 0.006825
0.848971 2.976605- 0.0000
0.0043
AN 4.67800 5.510207
0.13668 7 Mean dependent 0.0055
R-squared 8 var 68
R-squared
Adjusted R- 0.34361 S.D.
0.10585 Meandependent
dependent 1.1242
0.0070
squared 2 var
5 var 37
67
Adjusted R- 0.33229 S.D. dependent 0.7235-
squared
S.E. of 0.00668 5 varAkaike info 47
7.1292
S.E. of
regression 0.59123 Akaike info
2 criterion 1.8195
15
regression 4 criterion 55-
Sum squared
Sum squared 20.2743 Schwarz criterion
0.00250 1.8893
7.0235
resid
resid 3 Schwarz criterion
1 66
78
Log likelihood - Hannan-Quinn 1.8468-
213.311 criter.
52.5866 Hannan-Quinn 62
7.0879
Log likelihood 8 criter. 79
4.43323 Durbin-Watson
27 0.4974
F-statistic 4 stat 35
0.01631
Prob(F-statistic) 9
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
4
30.3623 Durbin-Watson 0.1549
F-statistic 9 stat 05
0.00000
Prob(F-statistic) 1
Coefficie
Variable nt Std. Error t-Statistic Prob.
4.77567
C 7 0.033783 141.3643 0.0000
-
LOGNOMINAL_M 0.18136 -
LY 8 0.025617 7.079841 0.0000
28
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
t-Statistic Prob.*
t-Statistic Prob.*
29
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
t-Statistic Prob.*
t-Statistic Prob.*
30
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
Chow Forecasting
Test Equation:
Dependent Variable: LOGCPI_CAN
Method: Least Squares
Date: 04/30/10 Time: 14:28
Sample: 1995Q1 2004Q4
Included observations: 40
Test Equation:
Dependent Variable: LOGCPI_MLY
Method: Least Squares
Date: 04/30/10 Time: 14:26
Sample: 1995Q1 2004Q4
Included observations: 40
31
073604149
Testing the Existence and Forecasting the Fisher Effect in Malaysia
and Canada
Bibliography
Johnson, P.A. (2006), ‘Is there really the Fisher effect?’, Applied
Economics Letters 13, pp. 201-203.
Fahmy, Y.A.F. and M. Kandil (2003), ‘The Fisher effect: new evidence
and implications’, International Review of Economics and Finance
12, pp. 451-465.
32