BUSINESS REPORT
Introduction
The main goal of this paper is to provide a forecast for Real GDP of Malaysia for 2005, the loan growth of the Malaysian banking industry and the selected Malaysian Bank. In this particular case, the Bank selected is Bank Negara. The data that will be used is shown in the following Table:
Table 1
Macro Economic Indicator for Malaysia
Table 1 shows the Real GDP of Malaysia, banking systems loan growth and the bank Negara loan growth from 1997-1998. As can be seen the data are subdivided in to June and December for each year.
Linear Regression Model
Real GDP of Malaysia and Loan Growth of Banking System
The following tables show the linear regression[1] result for the Real GDP of Malaysia and Loan Growth of Banking System.
Table 2
Simple Linear Regression – Analysis of Variance
Simple Linear Regression – Analysis of Variance
ANOVA
DF
Sum of Squares
Mean Square
Regression
1.000000
120.472921
120.472921
Residual
3.000000
130.035079
43.345026
Total
4.000000
250.508000
62.627000
F-TEST
2.779394
Table 3
Simple Linear Regression – Autocorrelation
Simple Linear Regression – Autocorrelation
Statistic
Value
Durbin-Watson
1.766644
Von Neumann Ratio
2.208305
rho – Least Squares
-0.434836
rho – Maximum Likelihood
-0.188256
rho – Serial Correlation
-0.229753
rho – Goldberger
-0.286113
Table 4
Simple Linear Regression – Descriptive Statistics
Simple Linear Regression – Descriptive Statistics
Statistic
Value
Mean X
13.500000
Biased Variance X
138.732000
Biased S.E. X
11.778455
Mean Y
0.520000
Biased Variance Y
50.101600
Biased S.E. Y
7.078248
Mean F
0.520000
Biased Variance F
24.094584
Biased S.E. F
4.908623
Mean e
0.000000
Biased Variance e
26.007016
Biased S.E. e
2.944317
Figure 1
Simple Linear Regression: Real GDP of Malaysia
And Loan Growth of Banking System
Real GDP of Malaysia and Loan Growth of Bank Negara
The following tables show the linear regression result for the Real GDP of Malaysia and Loan Growth of the selected bank which is Bank Negara.
Table 5
Simple Linear Regression – Analysis of Variance
Simple Linear Regression – Analysis of Variance
ANOVA
DF
Sum of Squares
Mean Square
Regression
1.000000
15.020614
15.020614
Residual
3.000000
235.487386
78.495795
Total
4.000000
250.508000
62.627000
F-TEST
0.191356
Table6
Simple Linear Regression – Autocorrelation
Simple Linear Regression – Autocorrelation
Statistic
Value
Durbin-Watson
1.817350
Von Neumann Ratio
2.271687
rho – Least Squares
-0.061275
rho – Maximum Likelihood
-0.057567
rho – Serial Correlation
-0.063649
rho – Goldberger
-0.059392
Table 5
Simple Linear Regression – Descriptive Statistics
Simple Linear Regression – Descriptive Statistics
Statistic
Value
Mean X
8.340000
Biased Variance X
0.298400
Biased S.E. X
0.546260
Mean Y
0.520000
Biased Variance Y
50.101600
Biased S.E. Y
7.078248
Mean F
0.520000
Biased Variance F
3.004123
Biased S.E. F
1.733241
Mean e
0.000000
Biased Variance e
47.097477
Biased S.E. e
3.962216
Figure 2
Simple Linear Regression: Real GDP of Malaysia
And Loan Growth of Bank Negara
Correlation Real GDP of Malaysia and Loan Growth of banking System
Correlation
0.693480
It shows that the two variables have positive correlation. Herein, it can be concluded that Real GDO and Loan Growth of banking system of Malaysia has a moderately high correlation. This implies that the variable can be used as an indicator for identifying the growth of the Malaysia.
Correlation Real GDP of Malaysia and Loan Growth of Bank Negara
Correlation
-0.354905
It shows that the two variables have negative correlation. This indicates that the two variables have a negligible correlation. This means that Real GDP of Malaysia and the Loan Growth of Bank Negara have a small relationship to be used as an indicator. It also implies that both variables are not a good factor for determining the growth of the bank. This means that when the growth of the Real GD increases, the growth of Bank Negara for loan growth decreases or vice versa.
Method of Least Squares
Since this paper aims to determine or forecasts the 2005 Real GDP growth of Malaysia, the loan growth of Malaysian Banking industry as well as the Loan growth of Bank Negara the use of Method of Least Squares was performed[2]. Basically, if a straight line assured, the line of trend will have a formula:
In this formula the value of and must be determined. The principle of least square, states that a trend best fit a given set of values when the constants of the equation are chosen so that the sum of the squares of the deviations between the original data and the corresponding trend values are a minimum. If the line fits the data perfectly, each point will lie on the line and the sum of the squares of the deviations will be zero. The farther the points are from the trend, the larger will the deviations, although the line may still be fitted so that these squared deviations will be a minimum.
In order to find these values for and by the method of least squares, it is necessary to solve the following normal equations in which time is designated by X and the values in the series by Y.
The procedure may be simplified by arbitrarily shifting the origin of the series ( in the middle year for an odd number of years between the two centre years for an even number of years) in this way so that , the preceding equation can be reduced to
After the values of a and b are determined, it then becomes possible with the use of the equation,, to compute the actual trend values.
Let’s try to consider the given data below for Real GDP
Time Series Data
Year
Qtr
Real GDP(Y)
Loan Growth of Banking Industry (X)
X2
XY
1999
June
4.1
1.3
1.69
5.33
1998
June
-5.2
10.2
104.04
-53.04
December
-10.3
1.3
1.69
-13.39
1997
June
8.4
28.2
795.24
236.88
December
5.6
26.5
702.25
148.4
Total
2.6
69.2
1604.91
324.18
Using the computed values above we have:
= = 0.52
== .201992635
Thus, the equation model will then be read:
Y= 0.52+.201992635X where y=Real GDP and X=Loan Growth of banking industry
Figure 3
Time Series Chart
Using the model equation Y= 0.52+.201992635X, we can now predict the Real GDP of Malaysia for 2005. Referring to the time series data, the loan growth of Malaysian banking industry (x value) for June 1997 is 28.2 then we may state that the equivalent x value for the first quarter of 2005 is 10.5 and for December 2005 is 11.5.
Using the model equation Y= 0.52+.201992635X we have:
For June 2005:
Y= 0.52+.201992635X
Y= 0.52+.201992635(10.5)
Y= 2.640961675 or 2.64
For December 2005:
Y= 0.52+.201992635X
Y= 0.52+.201992635(11.5)
Y= 2.842153025 or 2.84
Forecasting for Loan Growth of Banking Industry
Year
Qtr
Loan Growth of Banking Industry (Y)
Real GDP(X)
X2
XY
1999
June
1.3
4.1
16.81
5.33
1998
June
10.2
-5.2
104.04
-53.04
December
1.3
-10.3
106.09
-13.39
1997
June
28.2
8.4
70.56
236.88
December
26.5
5.6
31.6
148.4
Total
69.2
2.6
328.86
324.18
Using the computed values above we have:
= = 13.84
== .98576902
Thus, the equation model will then be read:
Y= 13.84+.98576902X where y= Loan Growth of banking industry and X= Real GDP of Malaysia
Figure 4
Time Series Chart
Using the model equation Y= 13.84+.98576902X, we can now predict the Loan Growth of Malaysian banking industry for 2005. Referring to the time series data, the real GDP of Malaysia have an equivalent x-value of 8.4 for June 1997 then we may state that the equivalent x value for the first quarter of 2005 is 5.2, for December 2005 is 6.5.
Using the model equation Y= 13.84+.98576902X we have:
For June 2005:
Y= 13.84+.98576902X
Y= 13.84+.98576902(5.2)
Y= 18.9659989 or 18.97
For December 2005:
Y= 13.84+.98576902X
Y= 13.84+.98576902(6.5)
Y= 20.24749863 or 20.25
Forecasting for Loan Growth of Banking Industry
Year
Qtr
Loan Growth of Bank Negara (Y)
Real GDP(X)
X2
XY
1999
June
9.2
4.1
16.81
37.72
1998
June
8.5
-5.2
104.04
-44.2
December
8.5
-10.3
106.09
-87.55
1997
June
7.5
8.4
70.56
63
December
8.2
5.6
31.6
45.92
Total
41.9
2.6
328.86
14.89
Using the computed values above we have:
= = 8.38
== .045277625
Thus, the equation model will then be read:
Y= 8.38+.045277625X where y= Loan Growth of bank Negara and X= Real GDP of Malaysia
Figure 4
Time Series Chart
Using the model equation Y= 8.38+.045277625X, we can now predict the Loan Growth of Bank Negara for 2005. Referring to the time series data, the real GDP of Malaysia have an equivalent x-value of 8.4 for June 1997 then we may state that the equivalent x value for the first quarter of 2005 is 10.2, for December 2005 is 11.5.
Using the model equation Y= 8.38+.045277625X we have:
For June 2005:
Y= 8.38+.045277625X
Y= 8.38+.045277625(10.2)
Y= 8.841831783 or 8.84
For December 2005:
Y= 8.38+.045277625X
Y= 8.38+.045277625(11.5)
Y= 8.900692688 or 8.90
Limitations of the Forecasting Model
Actually, forecasting, by professional, is too frequently a guessing game. Even when forecasters agree, they are apt to reach their common conclusion by different methods and for different reasons. And when they happen to be right, they are frequently right because of reasons or conditions they did not anticipate. In connection to this, the use of Least Square Method was employed in order to forecasts the Malaysian real GDP, loan growth of the banking sector and the selected banking sector for 2005. Furthermore, it is suggested that the use of other forecasting technique should also be considered since unorganised forecasting is usually the product of personal judgment or intuition or, sometimes, only a subconscious feeling for the course of future events. It is more art than science, and it will remain in this unsatisfactory state until its methods can be brought into the realm of the rational and can be based on logical relationships that govern banking behavior and can be stated in measurable terms.
The main weakness of the least squares methods can be attributed to the shape of the linear models. Herein, the shapes may have the possibility to have a poor extrapolation properties and sensitive to outliers. In addition, while the method often provides optimal estimates of the unknown parameters, it is very susceptible to the presence of unusual data given in a data utilised to fit a certain model.
With this weakness it can be said that the result of the analysis does not constitute a strong reliability. Hence, it is suggested that the forecaster should be able to use other methods suitable for this case in order to determine if there is a discrepancy or whether this method us reliable or not.
Conclusion and Recommendation
As can be seen at the computation, the Real GDP of Malaysia and the loan growth of the banking industry in the nation has a positive and moderately high correlation. This means that whenever the GDP increases there is a greater possibility of having an increasing loan growth. On the other hand, the Real GDP of Malaysia and loan growth of the selected bank has a negative correlation. As mentioned above, when the Real GDP decreases, loan growth of Bank Negara increases or vice versa. The use of least squares method for forecasting the growth of Real GDP, loan growth of Malaysian banking industry and loan growth of bank Negara for the year 2005.
Meanwhile, the bank of Negara should be able to management its business operations and financial performance well to achieve growth in terms of Loan. Business management is the functional application of marketing techniques. It refers to the analysis, planning, implementation, and control of programs designed to create, build, and maintain mutually beneficial exchanges with target markets. The bank selected must be able to use all its resources and maximise key indicators to be able to achieve a high loan growth for year 2005.
[1] Burrill G F, Burrill J C, Hopfensperger P W, Landwehr J M. Exploring Regression (Teacher’s Edition). Dale Seymour Publications, 1999
[2] Pavel B. Bochev and Max D. Gunzburger. Finite Element Methods of Least-Squares Type. SIAM Review, 40(4):789-837, 1998.
Credit:ivythesis.typepad.com
0 comments:
Post a Comment