The
report focuses on the initial methodology, assumption that was made and outcome that was
observed due to the adoption of that methodology and necessary assumptions.
Through this research we are trying to find out whether food price can be used to measure
utility as there is no fundamental unit or methods of measuring utility and food is one of the
necessary items in our daily life. A cobb Douglas equation was used to make the necessary
theoretical base of the research
U=X1 X2
After completing the necessary theoretical basis, the raw data of HIES2010 was carefully
studied, the was carried out throughout the country and was divided into 6 division Dhaka ,
Chittagong , Khulna , Barisal , Rajshahi and Sylhet. Among the 6 Divisions the number of
observation was highest in Dhaka , Chittagong and Rajshahi. Each division had its own unique
division number and each division was further divided using PSU number. Barisal(10) PSU 1-49,
Chittagong(20) PSU 50-159, Dhaka(30) PSU 160-337, Khulna(40) PSU 337-426 , Rajshahi(50) PSU
427-569 and Sylhet(60) PSU 570-612. The strata no. number indicates whether the PSU number
is under Urban or rural area.
After recording the required data, a key assumption was made i.e Income is directly
proportional to utility. So a rise(fall) in income would lead to an increase(decrease) in utility.
The HIES survey 2010 had a given food basket and expenditure and a non-food basket and
expenditure and also the income source of the household surveyed.
A unit root test of each variable INCOME, FOOD and NON-FOOD was carried out to test for
multicollinearity and the test showed that the variables had no multicollinearity problem.
A correlation test was carried out to test whether there is any correlation between the
variables. The test results showed that all the variable are positively correlated.
Then a regression equation was calculated with INCOME as dependent variable and Food
expenditure and Non-food expenditure as Independent variable.
A conintegration test was lastly carried out which gave a 3 equations instead of 2 equations.
Again this same tests was carried out by taking the log of each variables.
The results of each test is given below:
UNITROOT TEST
Null Hypothesis: FOOD has a unit root
Exogenous: Constant
Lag Length: 3 (Automatic - based on SIC, maxlag=42)
t-Statistic
Prob.*
-61.04692
-3.430582
-2.861527
-2.566804
0.0001
Coefficient
Std. Error
t-Statistic
Prob.
FOOD(-1)
D(FOOD(-1))
D(FOOD(-2))
D(FOOD(-3))
C
-0.688909
0.163815
-0.014038
0.037499
10734.24
0.011285
0.010352
0.008825
0.007819
287.3622
-61.04692
15.82446
-1.590613
4.795922
37.35438
0.0000
0.0000
0.1117
0.0000
0.0000
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.316111
0.315942
28873.81
1.35E+13
-188878.5
1866.585
0.000000
0.451789
34910.63
23.37957
23.38195
23.38035
1.999592
t-Statistic
Prob.*
-19.44591
-3.430583
-2.861527
-2.566804
0.0000
Coefficient
Std. Error
t-Statistic
Prob.
INCOME(-1)
D(INCOME(-1))
D(INCOME(-2))
D(INCOME(-3))
D(INCOME(-4))
D(INCOME(-5))
D(INCOME(-6))
D(INCOME(-7))
D(INCOME(-8))
D(INCOME(-9))
D(INCOME(-10))
D(INCOME(-11))
D(INCOME(-12))
D(INCOME(-13))
D(INCOME(-14))
D(INCOME(-15))
D(INCOME(-16))
D(INCOME(-17))
C
-0.334209
-0.508548
-0.403562
-0.340326
-0.336733
-0.299825
-0.269954
-0.214326
-0.192210
-0.169593
-0.140768
-0.104302
-0.113110
-0.111381
-0.071745
-0.065730
-0.062177
-0.031367
1366.776
0.017187
0.017736
0.017912
0.017916
0.017832
0.017684
0.017491
0.017279
0.016955
0.016554
0.016083
0.015532
0.014809
0.013970
0.012957
0.011829
0.010306
0.007888
104.8387
-19.44591
-28.67386
-22.53069
-18.99552
-18.88327
-16.95455
-15.43368
-12.40365
-11.33660
-10.24468
-8.752552
-6.715164
-7.638137
-7.972986
-5.537079
-5.556867
-6.032815
-3.976421
13.03694
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0000
0.0001
0.0000
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.418383
0.417734
9903.141
1.58E+12
-171432.4
644.4129
0.000000
4.645689
12978.13
21.24027
21.24932
21.24326
1.997663
t-Statistic
Prob.*
-36.70546
-3.430582
0.0000
5% level
10% level
-2.861527
-2.566804
Coefficient
Std. Error
t-Statistic
Prob.
NON_FOOD(-1)
D(NON_FOOD(-1))
D(NON_FOOD(-2))
D(NON_FOOD(-3))
D(NON_FOOD(-4))
D(NON_FOOD(-5))
D(NON_FOOD(-6))
D(NON_FOOD(-7))
D(NON_FOOD(-8))
C
-0.603340
-0.153897
-0.162375
-0.222662
0.095206
-0.030074
-0.003833
0.032366
-0.057521
1633.743
0.016437
0.015902
0.015302
0.014593
0.013826
0.013256
0.011555
0.009859
0.007857
107.1739
-36.70546
-9.677728
-10.61144
-15.25851
6.885929
-2.268707
-0.331702
3.282978
-7.320526
15.24385
0.0000
0.0000
0.0000
0.0000
0.0000
0.0233
0.7401
0.0010
0.0000
0.0000
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.448519
0.448211
12389.96
2.48E+12
-175151.4
1458.786
0.000000
-0.043336
16679.52
21.68778
21.69254
21.68935
1.999220
Correlation test
FOOD
INCOME
NON_FOOD
FOOD
INCOME
NON_FOOD
1.000000
0.004217
0.017586
0.004217
1.000000
-0.001583
0.017586
-0.001583
1.000000
Regression
Dependent Variable: INCOME
Method: Least Squares
Date: 02/23/14 Time: 10:06
Sample: 1 16162
Included observations: 16162
Variable
Coefficient
Std. Error
t-Statistic
Prob.
FOOD
NON_FOOD
0.001379
-0.001307
0.002556
0.006201
0.539689
-0.210704
0.5894
0.8331
4066.375
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.000021
-0.000103
10471.62
1.77E+12
-172533.7
0.165881
0.847148
92.93604
43.75455
0.0000
4084.382
10471.08
21.35091
21.35234
21.35138
1.534798
Cointegration Test
Date: 02/23/14 Time: 11:00
Sample (adjusted): 6 16162
Included observations: 16157 after adjustments
Trend assumption: Linear deterministic trend
Series: INCOME FOOD NON_FOOD
Lags interval (in first differences): 1 to 4
Unrestricted Cointegration Rank Test (Trace)
Hypothesized
No. of CE(s)
Eigenvalue
Trace
Statistic
0.1
Critical Value
Prob.**
None *
At most 1 *
At most 2 *
0.157134
0.119305
0.097926
6479.781
3717.779
1665.121
27.06695
13.42878
2.705545
1.0000
1.0000
0.0000
Eigenvalue
Max-Eigen
Statistic
0.1
Critical Value
Prob.**
None *
At most 1 *
At most 2 *
0.157134
0.119305
0.097926
2762.003
2052.658
1665.121
18.89282
12.29652
2.705545
1.0000
1.0000
0.0000
FOOD
-5.49E-05
-5.32E-06
1.52E-06
NON_FOOD
1.69E-05
-0.000133
2.60E-05
8.177548
12368.97
-560.4604
1 Cointegrating Equation(s):
-902.5171
1250.090
4423.560
-3191.296
-327.3745
-972.5916
Log likelihood
-537712.7
2 Cointegrating Equation(s):
Log likelihood
-536686.4
IN
INFOOD
INNONOFOOD
IN
INFOOD
INNONOFOOD
1.000000
-0.008072
0.034440
-0.008072
1.000000
0.019010
0.034440
0.019010
1.000000
Coefficient
Std. Error
t-Statistic
Prob.
INFOOD
INNONOFOOD
C
-0.006061
0.024574
8.238533
0.007431
0.007600
0.083323
-0.815669
3.233568
98.87434
0.4147
0.0012
0.0000
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.001262
0.001033
0.954955
7954.841
-11977.96
5.512493
0.004050
8.355882
0.955449
2.746038
2.748470
2.746867
1.151294
Eigenvalue
Trace
Statistic
0.05
Critical Value
Prob.**
None *
At most 1 *
At most 2 *
0.152904
0.095018
0.055381
419.2587
203.7013
74.00896
29.79707
15.49471
3.841466
0.0001
0.0001
0.0000
Eigenvalue
Max-Eigen
Statistic
0.05
Critical Value
Prob.**
None *
At most 1 *
At most 2 *
0.152904
0.095018
0.055381
215.5574
129.6924
74.00896
21.13162
14.26460
3.841466
0.0001
0.0001
0.0000
IN
0.120326
-1.287658
0.264012
INFOOD
1.237298
0.108861
0.057504
INNONFOOD
-0.240386
0.266910
1.080025
-0.069647
-0.520300
0.006059
1 Cointegrating Equation(s):
0.283567
-0.072247
-0.046860
-0.029883
-0.008188
-0.283325
Log likelihood
-5990.809
2 Cointegrating Equation(s):
Log likelihood
-5925.963