User talk:Shimul Kubi

Research By Shimul Kubi Department of Economics Jatiya Kabi Kazi Nazrul University. Sub: Income Education Nexus of the salesman of Ready-made Garments Products.

Abstract:

Our research topic is “Income Education Nexus of the salesman of Ready-made Garments Products.” If we want to run our study we need data. In our assignment we will use primary data. We will collect data from MymensinghSadar and TrishalUpazila. Because, to prepare in our study it will be easy for us to collect data from this region. We assume that if the level of education is increased then income also increased. We can say that they are positively related with each other. We know that there exist many sector such as teaching, banking, business and so on sectors. But it is really impossible for us to study every sector. That’s why we have chosen this sector to collect data in our assignment.

Introduction:

Now we want to introduce our research topic and why we have chosen this topic. In this study we want to examine “The relationship between income and education of the salesman of readymade garments products.” We know that income and education are positively related. Education is the fundamental important factors of economic growth. No country can achieve sustainable economic growth without substantial investment in human capital i.e. education. It improves the quality of lives and leads to broad social benefits to individuals and society. That’s why we have chosen this topic.

Education is one of the key elements of human resource. It is also one of the principal sources for increasing economic growth and development. It enhances welfare of an individual and a household in the process of economic transformation. Increased labor productivity, effective use of land and other physical assets and improved socio economic empowerment are three important routes through which education can contribute to economic development. That’s why we thought that this topic is so much important.

Literature Review:

A researcher can answer the question of what information is already available and what is the knowledge- gap,only after reviewing the related literature. For this, it studies a number of research works on supporting the relationship between education and income. These are as follows: The interrelation between education and economic growth has been discussed since ancient Greece. Adam Smith (1776) and the classical economists emphasized the importance of investment in human skills.

They said that Education is one of the key elements of human asset. It is also one of the principal sources of increased income. When income level increases, the living index also becomes better. Which brings overall socio-economic development.

Aims and objectives of the study:

The main objective of this assignment will be - 	We want to know about the relationship between education and income level. This relationship can be positive or negative. Since we assume that there is exists positive relationship. When we collect data and run a regression. We hope that the result will be positive and goodness of fit test will be better.

Methodology of the Study:

This study aims at analyzing the impact of education in the level of income. The study has attempted to provide an overall scenario of it. For this purpose, the relationship between income and education are investigated by the following model –

Yi = β1+ β2Xi+ β3Xii+ β4Xiii+ β5Xiv+β6D1i+ β7D2i+ β8D3i+ β9D4i+β10D5 +ui Where, Yi =INCOME β1= Intercept Xi =Consumption Xii =Family size Xiii=Age Xiv=Working hours D1i= Education Level. Higher education=1, lower Education=o D2i = Gender. Male =1, female= 0 D3i = Region. Mymensingh =1, Trishal=0 D4i = Skill. Experienced=1 (Above 5 years), Less Experienced=0 D5i=Satisfaction. Satisfied=1, Not Satisfied=0 ui=Stochastic Disturbance Term

β1= lower Education, Female, Trishal, Less Experienced, Not Satisfied. This is also known as benchmark category. And all comparisons are made in relation to the benchmark category. We will use primary data to prepare this assignment.

Limitations:

There are some limitations in our assignment, which is entailed as following – 	People avoid us. 	Tendency of people to hide information. 	We are not expert about regression analysis. 	We cannot include other variables in the model which also affect the dependent variable. 	We are not expert about the operating system of stata. 	Lack of data related to this topic. 	Time is limited. 	Website restriction.

Data Analysis:

In our model, we have used ANCOVA model that is includes Quantitative and Qualitative variable. Here, Quantitative variable are consumptions, family size, age and working hours respectively and Education level, Gender, Region, skill and satisfaction are qualitative variable respectively. In our assignment we use the time series data.

Including data part: In this part we have included our collecting data

SL	Income	Consumption	Family size	Age	Working hours	Education	Gender	Region	skill	Satisfaction 1	8000	6000	3	48	10	0	1	1	1	1 2	6000	5000	8	24	11	0	1	1	1	1 3	12000	12000	2	28	12	0	1	1	1	1 4	6000	6000	4	21	12	0	1	1	1	1 5	3000	3000	5	18	12	0	1	1	1	0 6	6000	6000	5	23	12	0	1	1	1	0 7	2400	2400	4	19	12	0	1	1	0	0 8	5000	5000	3	36	12	1	0	1	0	0 9	15000	10000	4	45	6	1	1	1	0	1 10	3500	3500	5	22	11	0	0	1	0	0 11	15000	9000	4	22	12	1	1	1	1	1 12	15000	10000	7	20	11	1	0	1	0	1 13	4000	4000	3	19	11.30	0	0	1	0	0 14	5500	3000	2	29	10.30	0	0	1	1	1 15	8000	2000	4	25	10	0	0	1	1	1 16	5000	5000	3	25	10.30	1	0	1	0	1 17	4500	4500	3	42	10	0	0	1	1	0 18	3000	3000	4	21	10	1	0	1	0	0 19	6000	3000	3	18	8	0	1	1	0	1 20	5000	5000	6	18	10	1	1	1	0	0

SL	Income	Consumption	Family Size	Age	Working Hours	Education	Gender	Region	Skill	Satisfaction 21	16000	12000	5	26	11	1	1	1	1	1 22	5500	5500	6	20	12	1	1	1	1	1 23	10000	4000	11	24	11	1	1	1	1	1 24	20000	15000	2	25	11	1	1	1	1	1 25	10000	4000	11	21	8	1	1	1	1	1 26	7000	5000	6	25	12	0	1	1	1	0 27	20000	18000	4	18	10	0	1	1	1	1 28	10000	6000	4	23	5	1	1	1	1	1 29	8000	6000	4	24	10	0	1	1	1	1 30	5000	5000	6	18	8	0	1	1	0	0 31	8500	5500	4	23	10	0	1	0	1	1 32	8000	8000	6	25	10	0	1	0	1	0 33	5000	5000	4	23	8	0	0	0	0	0 34	11000	9000	6	25	10	1	1	0	1	1 35	8000	6000	4	26	10.30	0	1	0	0	1 36	10000	8000	5	23	10	1	1	0	1	1 37	8000	7000	4	24	10	0	1	0	1	1 38	10000	8000	5	22	10	0	1	0	1	1 39	8000	6000	5	23	10	0	1	0	0	1 40	7000	6000	4	24	10	0	1	0	1	1

SL	Income	Consumption	Family Size	Age	Working Hours	Education	Gender	Region	Skill	Satisfaction 41	8000	6000	5	22	10	0	1	0	1	1 42	10000	8000	5	26	10	0	1	0	1	1 43	8500	7000	6	23	10	0	1`	0	1	1 44	4000	4000	4	22	9	0	1	0	0	0 45	8000	7000	4	24	10	0	1	0	1	1 46	6000	6000	4	15	10	0	1	0	1	0 47	15000	12000	4	32	12	0	1	0	1	1 48	12000	10000	2	30	12	0	1	0	1	1 49	8500	8000	6	28	11	0	1	0	1	1 50	10000	10000	5	25	12	0	1	0	1	1 51	10000	7000	9	27	8	0	1	0	1	1 52	8000	2500	9	22	8	1	1	0	1	1 53	3000	3000	2	14	12	0	1	0	0	1 54	8000	6000	4	21	10	1	1	0	1	0 55	11000	11000	6	24	10	1	1	0	1	1 56	4000	4000	2	17	12	0	1	0	0	0 57	10000	8000	4	25	12	1	1	0	1	1 58	8000	6000	6	22	12	0	1	0	1	0 59	7000	7000	2	18	12	0	1	0	1	0 60	7000	5000	4	23	9	0	0	0	0	1

Regression Analysis:

Dependent variable: Income (Monthly income) Method: Least Square Sample: 60 Included observation: 60

The Regression results are as flloows--

Yi= 1430.539+0.9970324Xi+177.0605 Xii+7.218994 Xiii -249.1936 Xiv +886.1664D1i-221.6614 D2i+579.6898 D3i+576.1561 D4i+1642.327 D5i

(Se) = (1980.916) (.0744105) (113.5558) (34.01634) (137.8608) (459.4287) (600.1471) (414.0601) (517.3615) (470.9555)

t = (.72) (13.40)     (1.56)      (0.21)      (-1.81)(1.93)      (-0.37)      (1.40)      (1.11)(3.49) (0.474)* (0.000)* (0.125)* (0.833)**(0.077)*(0.059)*(0.713)**(.168)** (.271)*(.001)*

R²= 0.8815Adjusted R2=0.8601N= 60

Where * indicates the P values less than 5 percent and ** indicates the P values higher than 5 present.

Interpretation:

Sign of the coefficient of variables:

Non dummy: The sign of the coefficient of the various non- dummy regressors make economic sense. The coefficient of  Xi, Xii and Xiiiare expected to be positive and Xivis expected to be negative. Dummy: The differential intercepts coefficients of D1i, D3i, D4i, and D5i,are expected to be positive. The differential intercepts coefficients of D2i,expected to be negative. Interpretation non-dummy:

0.9970324is the partial regression coefficient of consumption tells us that with the influence of family size, age, and working hours are held constant, as consumption increases by 1 taka (BDT), on average, income goes up by 0.9970324taka (BDT). The estimated slope coefficient for consumption is statistically significant because as their p value is quite low.

177.0605 is the partial regression coefficient of family size tells us that with the influence of consumption, age, and working hours are held constant, as family size increases by 1 member, on average, income goes up by 177.0605 taka (BDT). The estimated slope coefficient for family size is statistically significant at 12 percent level of significance, as its p value is 12 Percent. But if we take the standard 1 and 5 percent level of significance then this slope coefficient is not statistically significant at this level.

7.218994 is the partial regression coefficient of age tells us that with the influence of consumption, family size, and working hours are held constant, as age increases by 1 year, on average, income goes up by 7.218994 taka (BDT). The estimated slope coefficient for age is statistically significant at 83 percent level of significance, as its p value is 83 Percent. But if we take the standard 1 and 5 percent level of significance then this slope coefficient is not statistically significant at this level.

-249.1936 is the partial regression coefficient of working hours tells us that with the influence of consumption, family size, and age are held constant, as working hours decreases by 1 hour, on average, income goes down by -249.1936 taka (BDT). The estimated slope coefficient for working hours is statistically significant at 7 percent level of significance, as its p value is 7 Percent. But if we take the standard 1 and 5 percent level of significance then this slope coefficient is not statistically significant at this level.

Interpretation of dummy variable:

The average income in these benchmarks is about 1430.539taka. Compared with this the average income for higher education level is higher by about 886.1664taka (BDT), for an actual average income of 2316.7054. The estimated slope coefficient for higher education level is statistically significant at 5 percent level of significance, as its p value is 5 Percent.

The average income in these benchmarks is about 1430.539taka. Compared with this the average income level for male is lower by about 221.6614 taka (BDT), for an actual average income of 1208.8776 taka. The estimated slope coefficient for higher education level is statistically significant at 71 percent level of significance, as its p value is 71 Percent.

The average income in these benchmarks is about 1430.539taka. Compared with this the average income for Mymensingh is lower by about 579.6898 taka, (BDT) for an actual average income of 2010.2288 taka. The estimated slope coefficient for higher education level is statistically significant at 16 percent level of significance, as its p value is 16 Percent.

The average income in these benchmarks is about 1430.539taka. Compared with this the average income for experienced person is higher by about 576.1561 taka, (BDT) for an actual average income of 2006.6951 taka. The estimated slope coefficient for higher education level is statistically significant at 27 percent level of significance, as its p value is 27 Percent.

The average income in these benchmarks is about 1430.539taka. Compared with this the average income for satisfied person is higher by about 1642.327 taka, (BDT) for an actual average income of 3072.866 taka. The estimated slope coefficient for higher education level is statistically significant at 0.07 percent level of significance, as its p value is 0.07 Percent.

Interpretation of R²:

The value of about 0.8815indicates that, about 89 percent of the variation in average income is explained by the consumption, family size, age and working hours and which is also explained by the entire dummy variable.

The Adjusted R2 tells that after considering the number regression the model explains 0.8601percent of the variation in income level.

Conclusion:

A conclusion is like the final chord in a song. It makes the listener feel that the piece is complete and well done. The same is true for our audience. We want them to feel that we supported what we stated in our thesis. We then become a reliable author for them and they are impressed by that and will be more likely to read our work in the future. They may also have learned something and maybe have had their opinion changed by what we have written or created!

References:

Book: 	Basic Gujarati, D. N., Basic Econometrics, 5th edition. -Damudar N Gujarati -Dawn C Porter -SangeethaGunasekar

Special Advisors: 	Important direction of our honorable course teacher. Bakhtiaruddin Associate Professor, Department of Economics, JatiyaKabiKaziNazrul Islam University