Top Banner
1 A Report on Multiple Regression Analysis of Chinese Economic Factors Based on Stata Sheikh TanjillaDipti Assistant Professor Department of Finance University of Dhaka GROUP # 04 Section: A Batch: 19th Department of Finance University of Dhaka Date of Submission: 20 th February, 2015 PREPARED FOR PREPARED BY
30

Multiple Regression Analysis of Chinese Economic Factors Based on Stata

Jul 18, 2015

Download

Data & Analytics

Rifat Ahsan
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

1

A Report on

Multiple Regression Analysis of Chinese

Economic Factors Based on Stata

Sheikh TanjillaDipti

Assistant Professor

Department of Finance

University of Dhaka

GROUP # 04 Section: A

Batch: 19th

Department of Finance

University of Dhaka

Date of Submission: 20thFebruary, 2015

PREPARED FOR

PREPARED BY

Page 2: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

2

GROUP NO # 04

Sl.

No.

Name

Name

Roll

No.

Remarks

Remarks 1. Maruf Hossain 19-013

2. Md.Monjurul Ahsan 19-099

3. Md.Ripon Molla 19-123

4. Abdul Quyum 19-121

5. Raqib Hosssain 19-157

Group Profile

Page 3: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

3

Date: February 20 ,2015

Course teacher,

Department of Finance,

University of Dhaka.

Subject: Submission of report.

Dear Mam’am,

With due respect, we are submitting here with our report on Multiple Regression Analysis of

Chinese Economic Factors Based on Stata. It is a requirement of BBA program from

department of finance, University of Dhaka. In spite of a number of limitations we have exerted

our best effort to prepare this report and to make it a vivid and comprehensive one for

accomplishing our academic requirement

So, we request you to accept our report and give us a proper suggestion in this case. We shall

always be obliged to furnish our clarification regarding this report, if required. If we did any

mistake, we are looking forward to your important advice.

Sincerely yours,

On behalf of the group 04

..............................................

LETTER OF TRANSMITTAL

Page 4: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

4

First of all we would like to express our gratitude from heart to the Almighty Allah for giving

us the strength and patience to prepare this report within the scheduled time.

We would like to acknowledge the contributions of the various Authors, whose textbooks have

been instrumental in preparing this Report.

Finally, we are especially grateful to our honourable course teacher for giving his valuable

suggestions and precious contributions .what he taught us in our course has worked as a beacon

while preparing this report.

Acknowledgement

Page 5: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

5

Statistics is a general term used to summarize a process that an analyst, mathematician or

statistician can use to characterize a data set. If the data set is based on a sample of a larger

population, then the analyst can extend inferences onto the population based on the statistical

results from the sample. We have completed the course “Applied Statistics (F-207)” and the

report is a part of the course.As we are the business students of country’s top renowned

institution ,it is bound for us to know about the mechanism related to statistics tools specially

Stata. We have tried to show our best competence in our report.Our report is basically based on

the multiple regession software solution. It contains the most economically strong country

China’s GDP and Inflation rate as dependent variables and political stability, government

efficiency , regulatory quality, rule of law ,control of corruption as a independent variables .

After the solution both of the variables equation on software is significant. After the entire model

is valid because the F Value is less than 5%. We have collected the information about our report

by browsing information , studying related pdfs from internet.We have made our best effort to

make the report logical and interpretable to the users.

Executive summary

Page 6: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

6

Table of contents

S. N.

Topics Page

1. Chapter: 1 Introduction 1.1: Background of The study 1.2: Origen of the Report 1.3 Objective of the report 1.4: Methodology of the Study 1.5: Limitation of the Study

01 02 02 03 03 03

2. Chapter: 2 Country Profile

05

3. Chapter: 3 World Banks Governance Index 3.1: Introduction 3.2: WGI Data Sources

O7 08 09

4. Chapter: 4

Multiple regression analysis of GDP (Y1) Process of working with this data on Stata Multiple regression analysis of Inflation (Y3)

Process of working with this data on Stata

14 15

19

20

Page 7: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

7

Chapter: 1

Introduction

Page 8: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

8

1.1: Background of The study As a student of business we need to learn basic mechanism and skill to organize analyze and transfer of data and present of information .So bookish knowledge is not enough for us .In this semester we have studied Applied Statistic(course F-207) and learn many tactical tools and

methods .So here we are given a chance to applied a practical knowledge, where we have to make a report on Russia on their various economic variables.

1.2: Origen of the Report

The BBA Program under the department of finance offers a course named“Applied Statistics (F-207)” which requires submitting a report on a specific topic on “Influence of Governance

Index on Economy : A study on China. The report under the above headline has been prepared.

1.3 Objective of the report There are many objectives to make this report, from where we can come to know the various

point such as To take GDP and Inflation as dependent variables and other five independent variables as

political stability ,govt. efficiency ,role of law and regulator control .

To show the raw data in excel. From using the value of excel on stata software and run the software.

To draw equation multiple regression. To interpret the result of the equation. To solve the case of the study.

1.4: Methodology of the Study

Page 9: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

9

Preparing this report is very difficult for us.for this we have to need on help of seniors and some discussion of other group. To prepare this report we mainly depend on secondary data. But also

take some help from our course instructor & seniors.

1.5: Limitation of the Study We have faced some typical constraints during our preparation for the report. The major

limitations are as follows:

To make this report we had to need various data such as politicalstability, law of control, government efficiency and other data from 1996 to 2013 but in some year here have not any data available on the internet .On where we have to average the previous and next data to complete

the report.

Before this time and about how to prepare a report and so faced some problems regarding this Report. Our calculations are mainly based on secondary data.

When we stat to make this report there we have not find all the data such as Gini coefficient index and other ,then we come to know that we have to use only GDP and Inflation rate as

dependent variables .

All the variables are changing in nature and sometimes it has no relationship with share price.

Page 10: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

10

Chapter: 2

2.1 Country Profile

Page 11: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

11

Country Name: People's Republic of China

China officially the People's Republic of China (PRC), is a sovereign state located in East Asia.

It is the world's most populous country, with a population of over 1.35 billion.The PRC is

a singlepartystate governed by the Communist Party, with its seat of government in the capital

city of Beijing. It exercises jurisdiction over 22 provinces, five autonomous regions, four direct-

controlled municipalities (Beijing, Tianjin, Shanghai andChongqing), and two mostly self-

governing special administrative regions(Hong Kong and Macau). The PRC also claims the

territories governed by the Republic of China (ROC), a separate political entity commonly

known as Taiwan today, as a part of its territory, which includes the island of Taiwan asTaiwan

Province, Kinmen and Matsu as a part of Fujian Province and islands the ROC controls in

the South China Sea as a part of Hainan Province. These claims are controversial due to the

complex political status of Taiwan.

Covering approximately 9.6 million square kilometers, China is the world'ssecond- largest

country by land area, and either the third or fourth- largest by total area, depending on the method

of measurement

China had the largest and most complex economy in the world for most of the past two thousand

years, during which it has seen cycles of prosperityand decline. Since the introduction

of economic reforms in 1978, China has become one of the world's fastest-growing major

economies. As of 2013, it is the world's second-largest economy by both nominal total

GDP andpurchasing power parity (PPP), and is also the world's largest exporter and importer of

goods.China is a recognized nuclear weapons state and has the world's largest standing army,

with the second- largest defence budget.The PRC has been a United Nations member since 1971,

when it replaced the ROC as a permanent member of the U.N. Security Council. China is also a

member of numerous formal and informal multilateral organizations, including

the WTO, APEC, BRICS, the Shanghai Cooperation Organization, the BCIM and the G-20.

China is a great power and a major regional power within Asia, and has been characterized as

a potential superpower by a number of commentators.

2.1 China At a glance :

Capital : Beijing

Largest city: Shanghai

Page 12: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

12

Official language:Standard Chinese

Area total: 9,596,961 sqkm

Land: 3,705,407 sqkm

Population: 1,357,380,000 (July 2013 EST.)

Density: (145/km2)

Unemployment rate: 5.6% (2013est.) 5.5% (2012 EST.)

Page 13: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

13

Chapter 3

World Banks Governance Index 3.1 Introduction Governance consists of the traditions and institutions by which authority in a country is

exercised. This includes the process by which governments are selected, monitored and

Page 14: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

14

replaced; the capacity of the government to effectively formulate and implement sound

policies; and the respect of citizens and the state for the institutions that govern economic and social interactions among them.

The Worldwide Governance Indicators report on six broad dimensions of governance for 215 countries over the period 1996-2013:

Voice and Accountability Political Stability and Absence of Violence Government Effectiveness Regulatory Quality Rule of Law Control of Corruption

In the above, we have mentioned each of the six dimensions of governance, and a list of the individual indicators on which each aggregate indicator is based. The WGI are composite governance indicators based on 32 underlying data sources. These data sources are rescaled and combined to create the six aggregate indicators using a statistical methodology known as an unobserved components model. A key feature of the methodology is that it generates margins of error for each governance estimate. These margins of error need to be taken into account when making comparisons across countries and over time.

3.2 WGI Data Sources The WGI compile and summarize information from 32 existing data sources that report the

views and experiences of citizens, entrepreneurs, and experts in the public, private and NGO sectors from around the world, on the quality of various aspects of governance.

The WGI draw on four different types of source data:

Surveys of households and firms Commercial business information providers

Non-governmental organizations Public sector organizations

Page 15: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

15

Worldwide Governance Indicators (WGI) for

China

This Country Data Report summarizes the data from the Worldwide Governance Indicators (WGI) project for a single country. The WGI report six aggregate governance indicators for over

200 countries and territories over the period 1996-2013, covering i) Voice and Accountability, ii) Political Stability and Absence of Violence, iii) Government Effectiveness, iv) Regulatory Quality, v) Rule of Law, and vi) Control of Corruption. The line graphs on each page show the country's percentile rank on each of the six governance indicators. Percentile ranks indicate the percentage of countries worldwide that rank lower than the indicated country, so that higher values indicate better governance scores. The line

graphs include margins of error shown as dashed lines, corresponding to 90% confidence intervals. Changes over time in the aggregate scores that are small relative to these margins of

error should not be interpreted as signalling a statistically significant change in the indicators. The WGI are composite measures based on a large number of underlying data sources. The

source data for each aggregate indicator are reported in a table on each page. Individual data sources have been rescaled to run from 0 (low) to 1 (high). These scores are comparable over

time and across countries since most individual measures are based on similar methodologies over time. Scores from different individual indicators are not however directly comparable with

each other since the different data sources use different units and cover different sets of countries. We show the WGI of china below in graph.

China, 1996-2013 Aggregate Indicator: Voice &Accountability

Page 16: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

16

China, 1996-2013

Aggregate Indicator: Political Stability and Absence of Violence

China, 1996-2013

Aggregate Indicator: Government Effectiveness

Page 17: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

17

China, 1996-2013

Aggregate Indicator: Regulatory Quality

China, 1996-2013

Page 18: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

18

Aggregate Indicator: Rule of Law

China, 1996-2013

Aggregate Indicator: Control of Corruption

Page 19: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

19

Page 20: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

20

Chapter 4 Multiple regression analysis of GDP (Y1)

Page 21: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

21

Process of working with this data on Stata

. tsset year

time variable: year, 1996 to 2013

delta: 1 unit

. reg y1 x1 x2 x3 x4 x5

Source | SS df MS Number of obs = 18

-------------+------------------------------ F( 5, 12) = 2.69

Model | 28.0327069 5 5.60654137 Prob> F = 0.0744

Residual | 25.0167362 12 2.08472801 R-squared = 0.5284

-------------+------------------------------ Adj R-squared = 0.3319

Total | 53.049443 17 3.12055547 Root MSE = 1.4439

------------------------------------------------------------------------------

y1 | Coef. Std. Err. t P>|t| [95% Conf. Interval]

-------------+----------------------------------------------------------------

x1 | -.3970101 .2709605 -1.47 0.169 -.9873823 .193362

Page 22: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

22

x2 | .0176029 .1684906 0.10 0.919 -.3495066 .3847125

x3 | .0014679 .1965445 0.01 0.994 -.4267658 .4297015

x4 | .0692561 .022989 3.01 0.011 .0191673 .1193449

x5 | .0220397 .1719012 0.13 0.900 -.3525009 .3965803

_cons | 8.784755 13.57164 0.65 0.530 -20.7853 38.35481

------------------------------------------------------------------------------

. dwstat

Durbin-Watson d-statistic( 6, 18) = 1.733433

. pwcorr x1 x2 x3 x4 x5

| x1 x2 x3 x4 x5

-------------+---------------------------------------------

x1 | 1.0000

x2 | 0.8056 1.0000

x3 | -0.7767 -0.7574 1.0000

x4 | 0.3945 0.3858 -0.1641 1.0000

x5 | -0.6898 -0.6043 0.6862 -0.4044 1.0000

. save "C:\Users\Rifat\Desktop\riff stat.dta" ,replace

file C:\Users\Rifat\Desktop\riff stat.dta saved

. exit, clear

Page 23: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

23

Regression equation

Y= 8.784755-.3970101X1+.0176029X2+.0014679X3+.0692561X4+.0220397X5+E

Here,

X1= Voice and Accountanbility

X2= Political Stability No Voilance

X3= Government Effectiveness

X4= Regulatory Quality

X5= Rule of Law

Level 0f Significance is 5%

T-test Analysis

In our t-test analysis null hypothesis and alternative hypothesis is

H0: β=0

H1: β≠0

From the regression table we can compare the P value with the level of significance. We know if

the P-value is less than the level of significance H0 is rejected that means there is a relation

between dependent variable and independent variables.

In this case we can see that for all the variables p-value except X1 is greater than the level of

significance so null hypothesis that means there is no significant relation between dependent

variable and the independent variables at 5% level of significance.

F-test Analysis

In our F-test hypothesises are

H0: β1=β2=β3=β4=β5

H1: β1≠β2≠β3≠ β4≠ β5

In our F-test analysis we found the p value is.0.0744that is far greater than 5% level of

significance so H0 is not rejected that means as a whole dependent and independent variable

Page 24: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

24

doesn’t have significant relationship at 5% level of significance so we can say that model is

invalid.

R-squared

In our analysis we found R-square is 0.5284 that means 52.84% change in Y is influenced by the

independent variables.

Durbin-Watson Test

Using this we can find whether the model has a autocorrelation or not. Autocorrelation problem

due to time series. In this case the value of d-stat is1.733433.

PW Correlation

We use pw correlation to find out whether there is any relation among the Independent

variable.From the result we can see that there is a multicoilinerity problem. We try to solve it by

logarithm, factoring and dropping. But after a number of trial and error we are failed to solve the

problem.

Page 25: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

25

Multiple regression analysis of GDP (Y3)

Collection of Raw Data

Page 26: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

26

Process of working with this data on Stata

name: <unnamed>

log: C:\Users\Rifat\Desktop\riff stat\2\y2.smcl

log type: smcl

opened on: 19 Feb 2015, 01:19:51

. insheet using "C:\Users\Rifat\Desktop\riff stat\2\stat y2.csv"

(7 vars, 18 obs)

. tsset year

time variable: year, 1996 to 2013

delta: 1 unit

. reg y2 x1 x2 x3 x4 x5

Source | SS df MS Number of obs = 18

-------------+------------------------------ F( 5, 12) = 16.52

Model | 333.989032 5 66.7978064 Prob> F = 0.0001

Residual | 48.520393 12 4.04336609 R-squared = 0.8732

-------------+------------------------------ Adj R-squared = 0.8203

Total | 382.509425 17 22.5005544 Root MSE = 2.0108

------------------------------------------------------------------------------

y2 | Coef. Std. Err. t P>|t| [95% Conf. Interval]

Page 27: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

27

-------------+----------------------------------------------------------------

x1 | -1.37086 .3773573 -3.63 0.003 -2.193051 -.548669

x2 | -.0285262 .2346511 -0.12 0.905 -.5397871 .4827347

x3 | .404625 .2737207 1.48 0.165 -.1917613 1.001011

x4 | .029809 .032016 0.93 0.370 -.0399479 .099566

x5 | -.0948287 .2394009 -0.40 0.699 -.6164385 .4267811

_cons | 36.21159 18.90075 1.92 0.080 -4.969609 77.39278

------------------------------------------------------------------------------

. dwstat

Durbin-Watson d-statistic( 6, 18) = 1.47294

. pwcorr x1 x2 x3 x4 x5

| x1 x2 x3 x4 x5

-------------+---------------------------------------------

x1 | 1.0000

x2 | 0.8056 1.0000

x3 | -0.7767 -0.7574 1.0000

x4 | 0.3945 0.3858 -0.1641 1.0000

x5 | -0.6898 -0.6043 0.6862 -0.4044 1.0000

. save "C:\Users\Rifat\Desktop\riff stat.dta" ,replace

file C:\Users\Rifat\Desktop\riff stat.dta saved

Page 28: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

28

. exit, clear

Regression equation

Y= 36.21159-1.37086X1-.0285262X2+.404625X3+.029809X4-.0948287X5+E

Here,

X1= Voice and Accountanbility

X2= Political Stability No Voilance

X3= Government Effectiveness

X4= Regulatory Quality

X5= Rule of Law

Level 0f Significance is 5%

T-test Analysis

In our t-test analysis null hypothesis and alternative hypothesis is

H0: β=0

H1: β≠0

From the regression table we can compare the P value with the level of significance. We know if

the P-value is less than the level of significance H0 is rejected that means there is a relation

between dependent variable and independent variables.

In this case we can see that for except x5 all the variables p-value is greater than the level of

significance so null hypothesis that means except x5 there is no significant relation between

dependent variable and the independent variables at 5% level of significance.

In case of x1 as the p-value is less than the level of significance so the null hypothesis is rejected

that means β≠0. So, the is significant relation between x1 and Y at 5% level significance.

If x1 is increase by 1 unit then Y will decrease by 1.37086unit holding other variable constant.

Page 29: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

29

F-test Analysis

In our F-test hypothesises are

H0: β1=β2=β3=β4=β5

H1: β1≠β2≠β3≠ β4≠ β5

In our F-test analysis we found the p value is 0.0001that is less than 5% level of significance so

H0 is rejected that means as a whole dependent and independent variable have significant

relationship at 5% level of significance so we can say that model is valid.

R-squared

In our analysis we found R-square is 0.8732that means 87.32% change in Y is influenced by the

independent variables.

Durbin-Watson Test

Using this we can find whether the model has a autocorrelation or not. Autocorrelation problem

due to time series. In this case the value of d-stat is 1.47294that means there is negative

autocorrelation problem.

PW Correlation

We use pw correlation to find out whether there is any relation among the Independent

variable.From the result we can see that there is a multicoilinerity problem. We try to solve it by

logarithm, factoring and dropping. But after a number of trail and error we are failed to solve the

problem.

Page 30: Multiple Regression Analysis of Chinese Economic Factors Based on Stata

30

Conclusion

We have learned about the practice and mechanism about using stata. We also can come to the country of China “an important developed country and also the largest land area of the world . After completing this report now con know how to applythis kind of difficult

software.To make this report we use GDP and Inflation as a dependent variable and other such as Russian political stability Government effectiveness, rule of law, and control of corruption as

independent variables effect on the model. After the solution of the software one variable control of corruption, is significant. After all the entire model is valid because the F Value is less

than 5%. At first we solve by command but there is autocorrelation and multicollinearity problem in the project. Finally the whole model is valid because in both case Prob> F (,in

y1,Prob>0.2338and y2,prob>0.1093) is less than 5% level of significance. So the endeavors are fruitful and the project is true.