THE ECONOMIC GROWTH OF GDP INFLUENCED BY DEATH RATE, CAPITAL AND LABOR IN MALAYSIA FOR THE PERIOD 1979 TO 2008.
Introduction
Malaysia has experiences an economic growth since 1970. After the May 1969 incident, the Malaysian government has introduced the New Economic Policy (Dasar Ekonomi Baru), which is implemented in year of 1970. It is a 20 years plan which is creating an integration of different races in different jobs, to terminate the poverty, and increase the involvement of locals into private sectors. The strategy for the policy is developing the suburban area, increase the standard of living, and increase the productivity and employment.
In this term paper, we are focusing on the productivity of Malaysia for the past of 30 years, which is from 1979 until 2008. We will examine the relationship of productivity with the factors that will influence the productivity. As an economist, it is important to identify the relationship between productivity and factors that influence the productivity because it can help an economist to make an effective policy, so that the economist can make a good decision at the right time.
The Production Function
In the classical Macroeconomics model, there is central relationship in the aggregate production function. The production function, which is based on the technology of individual firms, is a relationship between the level of output and the level of factor inputs. For each level of inputs, the production function shows the resulting level of output and is written as;
Y = AF(K,L)
Where,
Y, is the real GDP,
A, is the knowledge,
F, is technology ,
K, is the capital
L, is the labor
Mathematical function,
Y = A+K+L
Where,
Y, is the real GDP
A, is the technology that measured with the number of death rate
K, is the capital
L, is the labor
Assumption
E(ei) = 0. Each random error has a a probability distribution zero mean. Some errors will be positive, some will be negative; over a large number of observations, they will average out no zero.
var(ei) = σ². Each random error has a probability distribution variance σ². the variance σ² is an unknown parameter and it measures the uncertainty in the statistical model. It is the same for each observation, so that for no observations will the model uncertainty be more, or less, nor is to directly related to any economic variable. Errors with the property are said to be hemoskedastic.
Con(ei,ej) = 0. the covariance between the two random errors corresponding to any two different observation is zero. Thus, any pair of errors is uncorrelated.
We will sometimes further assume that the random errors ei have normal probability distributions. That is, ei ~ N(0, σ²).
EMPIRICAL RESULT
Dependent Variable: GDP
Method: Least Squares
Date: 02/15/11 Time: 11:15
Sample: 1979 2008
Included observations: 30
Variable
Coefficient
Std. Error
t-Statistic
C
-3.52E+11
5.55E+10
-6.348749
DEATH
3.57E+10
7.06E+09
5.054019
CAPITAL
1.525753
0.299600
5.092628
LABOR
26378.46
2663.297
9.904436
R-squared
0.945864
Mean dependent var
Adjusted R-squared
0.939618
S.D. dependent var
S.E. of regression
1.25E+10
Akaike info criterion
Sum squared resid
4.09E+21
Schwarz criterion
Log likelihood
-737.9902
Hannan-Quinn criter.
F-statistic
151.4246
Durbin-Watson stat
Prob(F-statistic)
0.000000
Estimation Command:
=========================
LS GDP C DEATH CAPITAL LABOR
Estimation Equation:
=========================
GDP = C(1) + C(2)*DEATH + C(3) *CAPITAL + C(4)*LABOR
Substituted Coefficients:
=========================
GDP = -352073804222 + 35661849928.9*DEATH+ 1.52575329767*CAPITAL + 26378.4579145*LABOR
GDP = β1 + β2DEATH + β3CAPITAL + β4LABOR
GDP=352073804222+35661849928.9DEATH+1.52575329767CAPITAL+26378.4579145LABOR+e
(se) (5.55E+10) (7.06E+09) (0.299600) (2663.297)
(t) (-6.348749) (5.054019) (5.092628) (9.904436)
R2=0.945864 SSE=1.25E+21 F-STAT=151.4246 N= 30 ADJ-R2=0.939618
Intrepet each of the estmates β2 , β3, and β4.
Β2 = 35661849928.9, an increase in 1% in total death rate will increase the total GDP by
35661849928.9.
Β3 = 1.525753, an increase in 1% of total capital will increase the total GDP by 1.525753.
Β4 = 26378.46, an increase in 1 person in labor will increase the total GDP by 26378.46.
From this econometric model, we can explain about the estimate of β2 which is explain about sums of death rate. The technology is measured base on the death rate. Specifically, a one percentge point increase in death rate openess would generate about a 35661849928.9 percentage point increase in GDP inflows which is based on the empirical result. Hence, the result imply that greater economy growth of the death rate may be conducive in inward GDP.
The fit of model to the data would be explained by R-squared. Based on the R-squared, the model is fit to the data because only 94.58 percent the variation in GDP is explained by DEATH,CAPITAL, and LABOR. However 5.42 percent of the variation is explained by the other factor.
Dependent Variable: LOG(GDP)
Method: Least Squares
Date: 02/15/11 Time: 21:27
Sample: 1979 2008
Included observations: 30
Variable
Coefficient
Std. Error
t-Statistic
C
-27.63376
3.460163
-7.986260
LOG(DEATH)
2.462308
0.182231
13.51200
LOG(CAPITAL)
2.040847
0.363051
5.621373
LOG(LABOR)
0.428808
0.041930
10.20775
R-squared
0.989932
Mean dependent var
Adjusted R-squared
0.988770
S.D. dependent var
S.E. of regression
0.070679
Akaike info criterion
Sum squared resid
0.129884
Schwarz criterion
Log likelihood
39.06648
Hannan-Quinn criter.
F-statistic
852.1232
Durbin-Watson stat
Prob(F-statistic)
0.000000
Estimation Command:
=========================
LS LOG(GDP) C LOG(DEATH) LOG(CAPITAL) LOG(LABOR)
Estimation Equation:
=========================
LOG(GDP) = C(1) + C(2)*LOG(DEATH) + C(3)*LOG(CAPITAL) + C(4) *LOG(LABOR)
Substituted Coefficients:
=========================
LOG(GDP) = )=-27.6337589199+2.46230780946*LOG(DEATH)+2.04084652462*LOG(CAPITAL)+0.428007718557*LOG(LABOR)
Se = (3.460163) (0.182231) (0.363051) (0.041930)
t = (-7.986260) (13.51200) (5.621373) (10.20775)
The coefficient of , , and is 2.462308, 2.040847 and 0.428808. The changes in GDP, it will caused by 1 percent changes in , , and , are 2.462308, 2.040847 and 0.428808 respectively.
The value of
The fit of model to the data would be explained by R-squared. Based on the R-squared, the model is fit to the data because only 98.99 percent the variation in GDP is explained by DEATH,CAPITAL, and LABOR. However 1.01 percent of the variation is explained by the other factor.
Factor most important
From the data interpretation above, we find out that death rate (technology) plays the most important role in the economic growth of Malaysia. We can see that 1% change in the death rate (technology) increases the GDP by 2.462308% when other capital and labor force are constant. This is because when new technology is functional into the production process, it generates more production that will enhance the economic more.
The t-statistics and hypothesis of death rate (technology), β2
Null hypothesis : H0 : β2 = 0
Alternative hypothesis : H1 : β2 ≠ 0
t = b2 / se (b2)
t = / 0.182231
t = 13.51200
t critical = t (0.975,26)
= 2.056
t > t critical, thus we reject H0 : β2 = 0
The Durbin Watson Test
The Durbin Watson test is designed to test the model whether it is effected by the collinearity problem. As we examine the e-views result, it is clear that collinearity problem does exist in our model. When the value of Durbin Watson test is less than 2 (in our model it is 0.770527), it encounters the collinearity problem. When data are the result of an uncontrolled experiment many of economic variables may move together in systematic ways. Such variables are said to be collinear and the problem is labeled collinearity. By the Gauss-Markov theorem,the least square estimator is still the best linear unbiased estimator. There may be a problem, however, if the best we can do is not very good because of the poor characteristic of our data. When collinearity problem exists, the variance of the variables would be high which means the estimate may not be significantly different from zero and an interval estimate will be wide. However, there are solutions that can be applied to handle this kind of problem. First, is to obtain more information and include it in the analysis. One form of new information can take is more, and better, sample data. Second is by adding new information is to introduce, nonsample information in the form of restriction on the parameters. Besides that, we can also throw away one of the variables that almos similar to another.
Conclusion
By following the econometric model, we can conclude that the responsiveness of percentage to variations in death rate (technology), capital, and labor, the death rate (technology) are the most effect of important crises experienced during the 30 years period on the GDP in Malaysia. Although the labor shows an increasing from the coefficient but it can't give a big changing in the GDP compare to technology. The elasticity of the GDP model is measured by death rate (technology), total coefficient is greater than 1, so it is elastic. We can say that the technology are running forward day by day due to the changing of quality production. The government should increase the productivity by using more technology to ensure the quality of standard living rise consistently.
YEAR
GDP (USD)
CAPITAL (USD)
LABOR (UNIT)
DEATH RATE (%)
2008
2.21828+11
43, 303, 592, 814
11, 732, 499
4.478
2007
1.86642E+11
40, 230, 523, 356
11, 474, 573
4.465
2006
1.56523E+11
32, 483, 106, 267
11, 217, 771
4.46
2005
1.37848E+11
28, 281, 002, 639
10, 982, 445
4.464
2004
1.24749E+11
26, 141, 052, 960
10, 735, 294
4.473
2003
1.10202E+11
24, 701, 052, 942
10, 493, 105
4.488
2002
1.00846E+11
23, 682, 895, 034
10, 250, 829
4.506
2001
92,783, 948, 533
23, 310, 526, 608
10, 001, 253
4.529
2000
93, 789, 738, 019
23, 721, 316, 087
9, 724, 275
4.556
1999
79, 148, 423, 191
17, 326, 597, 283
9, 283, 538
4.589
1998
72, 175, 310, 308
19, 361, 553, 094
9, 002, 150
4.629
1997
1.00169E+11
43, 187, 119, 239
8, 703, 883
4.678
1996
1.00852E+11
42, 857, 427, 077
8, 428, 794
4.736
1995
88, 832, 452, 512
38, 718, 654, 962
8, 157, 353
4.805
1994
74, 408, 816, 088
29, 975, 231, 260
7, 907, 288
4.884
1993
66, 894, 450, 252
26, 004, 040, 045
7, 675, 969
4.974
1992
59, 151, 288, 903
21, 665, 619, 490
7, 457, 551
5.073
1991
49, 133, 852, 000
17, 863, 350, 578
7, 231, 448
5.179
1990
44, 024, 178, 270
14, 546, 932, 728
7, 003, 834
5.289
1989
38, 848, 565, 930
11, 296, 145, 596
6, 695, 517
5.398
1988
35, 271, 881, 996
8, 678, 020, 961
6, 380, 551
5.502
1987
32, 181, 695, 659
7, 105, 890, 471
6, 157, 329
5.605
1986
28, 243, 103, 020
7, 157, 731, 667
5, 945, 259
5.711
1985
31, 772, 244, 237
9, 121, 371, 200
5, 729, 949
5.83
1984
34, 565, 849, 169
10, 611, 339, 225
5, 533, 535
5.976
1983
30, 682, 563, 370
10, 638, 174, 542
5, 380, 412
6.157
1982
27, 287, 163, 523
9, 538, 904, 648
5, 245, 655
6.376
1981
25, 463, 038, 429
8, 824, 273, 751
5, 112, 875
6.63
1980
24, 937, 045, 114
7, 467, 324, 037
4, 976, 959
6.91
1979
21, 602, 645, 098
5, 482, 558, 345
4, 593, 173
7.2
Data sources: World Data Bank, Trading Economics, Statistics Malaysia.
