Vous êtes sur la page 1sur 34

House Renting of FMT – 07 Students

ACKNOWLEGMENT

We would like to express our gratitude to all those who gave us the possibility to

complete this research paper. We want to thank the Faculty of Management and

Tourism, Hanoi University for giving us the permission to conduct the research as

well as supporting us with useful materials. Furthermore, we are deeply indebted to

our supervisor, Ms. Dao Binh, Lecturer in Econometrics and Mr. Nguyen Xuan

Truong, whose help, stimulating suggestions and encouragement helped us in all the

time of research for and writing of this paper.

Also, to the FMT – 07 students of Hanoi University, we whole heartedly thank and

highly appreciate you for the kindness and patience that given us. We spent two

days in delivering questionaire but it seems like we have spent more than two

weeks. That’s why we would like to thank for the love and efforts that support us to

finish this report.

Econometrics Project Page 1


House Renting of FMT – 07 Students

ABSTRACT

Today, house renting becomes a problem familiar to the Non-Hanoians, especially


with students. In fact, thousands of students pass the entrance exams to universities
each year that makes the need to rent an apartment more essential. There are many
factors affecting the renting house selection such as: distance in comparison with
universities, prices, securities, etc... This research is conducted in order to
investigate about house renting of Non-Hanoi students of FMT-07 in Hanoi
University, particularly how house renting price that one student have to pay
monthly is affected by some main factors such as the income flow of students
including family’s support and part time’s wages, the location in Hanoi, the area of
room on average and living condition. Moreover, we go into details the current
situation of house renting of Hanoi university students, in which we assess both
pros and cons of this Renting. Specific examples of FMT-07 students are given so
that readers can have a closer look and more realistic understanding. Last but not
least, the results of this research are discussed, consisting of predictions about
trends of the house renting of FMT-07 students in near future.

Econometrics Project Page 2


House Renting of FMT – 07 Students

LIST OF ABBREVIATION

FMT : Faculty of Management and Tourism


RNT : House rent
INF : Income flow
S : Area
L : Location
DUM : Dummy

Econometrics Project Page 3


House Renting of FMT – 07 Students

TABLE OF CONTENT
ACKNOWLEDGEMENTS ......................................................................................................................1
ABSTRACT ................................................................................................................................................1
LIST OF ABBREVIATION......................................................................................................................2
TABLE OF APPENDIXES .......................................................................................................................5
LIST OF TABLES .....................................................................................................................................5
LIST OF FIGURES ...................................................................................................................................5
INTRODUCTION......................................................................................................................................6
MODEL SPECIFICATION ......................................................................................................................7
DATA ..........................................................................................................................................................9
1. DEPENDENT VARIABLES........................................................................................................10
2. INDEPENDENT VARIABLES ..................................................................................................11
2.1. INF .................................................................................................................................11
2.2. S .....................................................................................................................................12
2.3. L .....................................................................................................................................13
2.4. DUM ..............................................................................................................................14
RESULTS .................................................................................................................................................15
1. EVIEW TABLE RESULTS .........................................................................................................15
1.1. Linear-Linear function ..................................................................................................15
1.2. Log-Linear function ......................................................................................................16
1.3. Linear-Log function ......................................................................................................16
1.4. Log-Log function ..........................................................................................................18
2. HYPOTHESIS TESTS ................................................................................................................19
2.1. Testing individual partial coefficients ............................................................................19
2.2. Testing overall significances of all coefficients ..............................................................20
3. ERRORS IN THE MODEL ..........................................................................................................22
2.1. Heteroskedasticity ...........................................................................................................22
2.2. Multicolinearity ..............................................................................................................24
2.3. Autocorrelation ...............................................................................................................25
4. DISCUSSION: ..............................................................................................................................27
SUMMARY AND CONCLUSION.........................................................................................................29
REFERENCES .........................................................................................................................................30
1. SAMPLE OF QUESTIONNAIRE ...............................................................................................30
2. LIST OF RENSPONDETNS ........................................................................................................32
APENDIX .................................................................................................................................................33

Econometrics Project Page 4


House Renting of FMT – 07 Students

TABLE OF APPENDIXES
1. Dependent and independent variables
1. List of variables having in model

LIST OF TABLES
2. Statistic table
3. Real estate price table
4. Living Condition Evaluation

LIST OF FIGURES
1. House Rent
2. Income inflow
3. Area Of Room
4. Average Real Estate Price
5. Living Condition Evaluation

Econometrics Project Page 5


House Renting of FMT – 07 Students
INTRODUCTION

Nowadays, studying needs in centers and big cities such as Hanoi, HCM City, Da Nang, etc is
becoming most popular in Vietnam Youth life. In order to live in a big city like Hanoi where is
so far from hometown, many non-Hanoi students have to face with a huge amount of daily
difficulties, especially accommodation. In fact, according to the thoughts of many people,
house renting for non-Hanoi students is seemly affected by many main factors such as income
flow (including family’s support and part time job’s wages), the location in Hanoi and the
living conditions of renting house (WC, atmosphere, internet services, securities as well as
convenience of transportation). Nevertheless, there has not been any research done to test
whether these relationships exist or not. If they exist, we should find out how these factors have
influence on the house renting of non-Hanoi students in Hanoi. Moreover, finding the solution
to this problem based on causes can gain many benefits for those who are in concerns.

To answer these questions, we have conducted a one-month-research. 35 Hanu non-Hanoi


students renting house in Hanoi are randomly chosen to answer a short questionnaire. The result
than are collected and the raw material are carefully analyzed for testing hypothesis. After this
investigation, we have got some conclusion, base on this for some suggested recommendations.

We hope that the test result will give us the overall view about the rent house of not only the
Hanu non-Hanoi students but also non-local students of many other universities in Hanoi. In
addition, based on what we discover, we could provide some useful advice to Universities and
Government in order to give some helps for non-Hanoi students about accommodations. These
actions would make development and facilitate for the students in studying and daily lives.

Econometrics Project Page 6


House Renting of FMT – 07 Students
MODEL SPECIFICATION
In this project, we focus on how much a non-Hanoian student in FMT - 07 department has to
pay for his/her house rent monthly which is affected by three main factors such as the income
flow of students including family’s support and part time’s wages, the location of that renting
house in Hanoi, the area of the room on average and the facilities of renting house (WC,
atmosphere, internet, security and convenient for transportation). The model estimated is
supposed to be:

Where:
RNT: the house rent for one non-Hanoi student in Hanoi (VND million/month)
INF: the income flow of students including family’s support and part time’s wages (VND
million/month)
S: the area of house or room on average that the student rent (m 2 )

L: the average real estate price in Hanoi districts (VND million/ m 2 )


D: the evaluation of living condition (convenient transportation, security, WC)
 D  1 : good

 D  0 : notgood
1 ,  2 ,  3 ,  4 &  5 are parameters that we are trying to estimate.

In the model, RNT is the dependent variable whereas the four variables standing on the right
side are the independent ones. There exists an inter-relationship among dependent variable and
independent ones. Before going through the model into detail, we would like to provide some
ideas about these variables.

First of all, RNT stands for how much a non - Hanoian student pays for his/her renting house
per month which is measured in million VND, this number may vary from some hundred
thousand VND to some millions VND depending on four variables mentioned below.

The second concept is INF that is the income inflow of students including the amount of money
that student’s family supports every month and the amount of money that student can earn due
to his/her part time’s wages(depending). There is a common belief that there exists a positive
relationship between the price of the renting house and the money inflow of students which
means that if students have more money, they usually choose a good living condition with

Econometrics Project Page 7


House Renting of FMT – 07 Students
higher price. However, some exception may happen for the case of students who want to save
their money for other purposes instead of paying too much for their renting house.

Next is the average area of the room-S which is measured in meter square. It is quite obvious
that the larger the room is, the more students pay for his/her room.

Thirdly, L is the location of your renting house in Hanoi, or in other words, in which district
your renting house is located. For this kind of variable, we base on the land price per meter
square on each district to measure the average monthly payment for a renting house. We assume
that, the higher the land price in that district is, the more a student pays for his/her renting house
in that district.

Finally, D is the dummy variable in our model. It is the evaluation of living condition including
WC, internet and some other criteria such as the security and convenience for transportation of
that renting house. This type of variable is one example of qualitative data because we cannot
measure it, just evaluating “good” or “bad”, “convenient” or “inconvenient”. As a result, we
 D  1 : good
assume that: 
 D  0 : notgood

Above we have just provided you with some details about our five variables. Now it is time to
discuss the relationship among these variables.

Econometrics Project Page 8


House Renting of FMT – 07 Students
DATA
Before the study officially commenced, 50 questionnaires were given to 50 FMT-07 Hanu
students to speculate the house rent of non Hanoi students in Hanoi. Accurate data is 35
respondents of FMT-07 students of Hanoi University.

In this part, we would like to present in detail the status of rent house and the mutual effect
between house rent and other independent variables.

STATISTIC TABLE

RNT INF S L
Mean 0.737143 1.829714 15.42857 16.80857
Median 0.500000 1.700000 15.00000 17.90000
Maximum 4.500000 3.500000 30.00000 47.00000
Minimum 0.300000 1.000000 8.000000 7.000000

As can be seen from the table, the mean of RNT, VND 0.737143 million, is quite high in comparison
with the average level of students in Hanoi. This might be the result of high income inflow (VND
1.829714 million) and large area (15.42857 m2). Although their income inflow seems to be high as
mentioned above, most of FMT 07 student still chose the renting location which is suitable with their
pocket.

Econometrics Project Page 9


House Renting of FMT – 07 Students

1. Dependent variable: RNT

House rent
VND Mil/Month (VND million/month)
1.4

1.2

0.8
House rent
0.6 (VND million/month)

0.4

0.2
Observations
0
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35

The maximum and minimum price of the renting house are VND 1.3 million and VND 0.3 million
respectively. It is easy to notice that there exists a huge difference in the amount of money spent by
students for their accommodations.

Econometrics Project Page 10


House Renting of FMT – 07 Students
2. Independent variables
2.1.INF:

Income flow
Observations (VND million/month)
34
31
28
25
22
19 Income flow
16 (VND million/month)
13
10
7
4
1 Mil/Month
0 1 2 3 4

Income is the first factor students mostly pay attention when they rent a house. This amount comes
from family’s support and part-time job wages. There is common belief that FMT 07 students find
easier to rent a house if their income inflows are high.

Econometrics Project Page 11


House Renting of FMT – 07 Students
2.2.S:

Area of room
Observations (m2)
34
31
28
25
22
19
16
13
10
7
4
1
0.0 5.0 10.0 15.0 20.0 25.0 30.0
m2/room

The area of house ranges from 9m2 to 30m2 and there is difference between districts. Average area of
house in central district is narrower in comparison with outskirts such as Thanh Xuan, Ha Dong and
Tu Liem

Econometrics Project Page 12


House Renting of FMT – 07 Students
2.3.L:
REAL ESTATE PRICE TABLE

Average real estate price


Districts
(VND million/m2)

Ba Dinh 47.0
Cau Giay 23.0
Dong Da 27.3
Ha Dong 11.6
Hoang Mai 17.0
Thanh Tri 7.0
Thanh Xuan 17.9
Tu Liem 9.0

Average real estate price


(VND million/m2)
Mil/m2
50.0
40.0
30.0
20.0
10.0 Average real estate price
(VND million/m2)
0.0
District

Different district has different real estate price. Among the districts of Hanoi, Ba Dinh is valued the
highest average real estate price at 47VND mil/m2.Dong Da and Cau Giay above 20VND mil/m2.Tu
Liem and Thanh Tri accounts for relatively low under 10 VNDmil/m2.The result of research explains
for house rent in central place is too expensive. However, due to suitable location near their
universities, some students still have to rent house.

Econometrics Project Page 13


House Renting of FMT – 07 Students

2.4.DUM (D):

LIVING CONDITION EVALUATION

Evaluation Respondents Percentages


Not Good 5 14.29%
Good 30 85.71%
Total 35 1

Not good:
Evaluation
14.29%

Good:
85.71%

Among 35 students asked, only 5 of them counting for 14.29% dissatisfied with their living conditions.
In contrast, more than 85% of respondents highly appreciate the living conditions and that is the reason
why the above means and standard deviations of RNT, S and L are so large.

Econometrics Project Page 14


House Renting of FMT – 07 Students

RESULTS
1. EVIEW TABLE RESULTS
1.1. Linear-Linear function

Dependent Variable: RNT


Method: Least Squares
Date: 12/03/09 Time: 23:59
Sample: 1 35
Included observations: 35

Variable Coefficient Std. Error t-Statistic Prob.

C 0.122118 0.168316 0.725526 0.4738


INF 0.237722 0.067617 3.515694 0.0014
S -0.000233 0.007455 -0.031255 0.9753
L 0.001315 0.005704 0.230574 0.8192
DUM 0.055142 0.120366 0.458120 0.6502

R-squared 0.334991 Mean dependent var 0.622857


Adjusted R-squared 0.246323 S.D. dependent var 0.257917
S.E. of regression 0.223909 Akaike info criterion -0.023588
Sum squared resid 1.504061 Schwarz criterion 0.198605
Log likelihood 5.412791 Hannan-Quinn criter. 0.053113
F-statistic 3.778040 Durbin-Watson stat 2.017337
Prob(F-statistic) 0.013254

The model based on the eview table:

The eview table above shows that of the model ( is so low; and the p-value in contrast is
quite high. Therefore, some other functional forms of multiple regression functions that were run in
order to improve the result are log-log, log-linear, linear-log model; the following eview tables were
obtained:

Econometrics Project Page 15


House Renting of FMT – 07 Students

1.2. Log-Linear function

Dependent Variable: LOG(RNT)


Method: Least Squares
Date: 12/03/09 Time: 23:59
Sample: 1 35
Included observations: 35

Variable Coefficient Std. Error t-Statistic Prob.

C -1.322106 0.257657 -5.131267 0.0000


INF 0.365250 0.103508 3.528708 0.0014
S -0.000663 0.011411 -0.058125 0.9540
L 0.001940 0.008732 0.222132 0.8257
DUM 0.093679 0.184256 0.508419 0.6149

R-squared 0.337784 Mean dependent var -0.551138


Adjusted R-squared 0.249488 S.D. dependent var 0.395649
S.E. of regression 0.342759 Akaike info criterion 0.827984
Sum squared resid 3.524509 Schwarz criterion 1.050177
Log likelihood -9.489727 Hannan-Quinn criter. 0.904685
F-statistic 3.825602 Durbin-Watson stat 1.979594
Prob(F-statistic) 0.012530

1.3. Linear-Log function

Dependent Variable: RNT


Method: Least Squares
Date: 12/04/09 Time: 00:00
Sample: 1 35
Included observations: 35

Variable Coefficient Std. Error t-Statistic Prob.

C 0.226191 0.390235 0.579626 0.5665


LOG(INF) 0.466068 0.127299 3.661212 0.0010
LOG(S) 0.013936 0.120933 0.115237 0.9090
LOG(L) 0.023982 0.102742 0.233423 0.8170
DUM 0.040095 0.123223 0.325386 0.7471

R-squared 0.350766 Mean dependent var 0.622857


Adjusted R-squared 0.264201 S.D. dependent var 0.257917
S.E. of regression 0.221238 Akaike info criterion -0.047595
Sum squared resid 1.468383 Schwarz criterion 0.174598
Log likelihood 5.832913 Hannan-Quinn criter. 0.029106
F-statistic 4.052067 Durbin-Watson stat 2.159101
Prob(F-statistic) 0.009609

Econometrics Project Page 16


House Renting of FMT – 07 Students
1.4.Log-Log function

Dependent Variable: LOG(RNT)


Method: Least Squares
Date: 12/04/09 Time: 00:01
Sample: 1 35
Included observations: 35

Variable Coefficient Std. Error t-Statistic Prob.

C -1.081965 0.588269 -1.839235 0.0758


LOG(INF) 0.744579 0.191899 3.880047 0.0005
LOG(S) -0.000726 0.182302 -0.003981 0.9968
LOG(L) 0.018757 0.154880 0.121108 0.9044
DUM 0.078474 0.185754 0.422458 0.6757

R-squared 0.373041 Mean dependent var -0.551138


Adjusted R-squared 0.289447 S.D. dependent var 0.395649
S.E. of regression 0.333509 Akaike info criterion 0.773273
Sum squared resid 3.336857 Schwarz criterion 0.995465
Log likelihood -8.532274 Hannan-Quinn criter. 0.849974
F-statistic 4.462508 Durbin-Watson stat 2.141702
Prob(F-statistic) 0.005996

For the purpose of selecting the best model among 4 models above, CV index is used:

Econometrics Project Page 17


House Renting of FMT – 07 Students

The absolute value of is the smallest. Therefore, the linear-log model is the most preferred
equation that should be used.

Dependent Variable: RNT


Method: Least Squares
Date: 12/04/09 Time: 00:00
Sample: 1 35
Included observations: 35

Variable Coefficient Std. Error t-Statistic Prob.

C 0.226191 0.390235 0.579626 0.5665


LOG(INF) 0.466068 0.127299 3.661212 0.0010
LOG(S) 0.013936 0.120933 0.115237 0.9090
LOG(L) 0.023982 0.102742 0.233423 0.8170
DUM 0.040095 0.123223 0.325386 0.7471

R-squared 0.350766 Mean dependent var 0.622857


Adjusted R-squared 0.264201 S.D. dependent var 0.257917
S.E. of regression 0.221238 Akaike info criterion -0.047595
Sum squared resid 1.468383 Schwarz criterion 0.174598
Log likelihood 5.832913 Hannan-Quinn criter. 0.029106
F-statistic 4.052067 Durbin-Watson stat 2.159101
Prob(F-statistic) 0.009609

And the final equation is:

̂ ( ( (

It can be seen from the linear-log eview table that the p-values of some coefficients of independent
variables (0.9090, 0.8170, 0.7171) whereas R-square ( is not high. Therefore, we do the
hypothesis testing to find the most relevant variables for our model.

̂
̂
̂
̂

Econometrics Project Page 18


House Renting of FMT – 07 Students

2. HYPOTHESIS TESTS
2.1. Testing individual partial coefficients
Note:

(
a. Holding S, L & DUM constant: Whether INF has the effect on Y?

̂

Compare with the critical value

| |
Answer: Yes, ̂ is statistically significant and significantly different from zero.

b. Holding INF, L & DUM constant: Whether S has the effect on Y?

̂

Compare with the critical value

| |

Answer: No, ̂ is not statistically significant and significantly different from zero.

Econometrics Project Page 19


House Renting of FMT – 07 Students

c. Holding INF, S & DUM constant: Whether L has the effect on Y?

̂

Compare with the critical value

| |
Answer: No, ̂ is not statistically significant and significantly different from zero.

d. Holding INF, S & L constant: Whether DUM has the effect on Y?

̂

Compare with the critical value

| |
Answer: No, ̂ is not statistically significant and significantly different from zero.

2.2. Testing the overall significance of all coefficients


5-variable case:
( ( (
(
(

( (

( ( ( (

 ( ( (

 Since
 Conclusion: At least one independent variable has the effect on dependent variable.

Econometrics Project Page 20


House Renting of FMT – 07 Students
2.3. Testing restriction on variables (Drop)
Because of too high p-value (0.9090) of the coefficient of log(S), we drop it and then we do the
dropping variable test in the regression model.

𝑹𝑵𝑻𝒊 𝜷𝟏 𝜷𝟐 𝑳𝑶𝑮(𝑰𝑵𝑭 𝜷𝟑 𝑳𝑶𝑮(𝑺 𝜷𝟒 𝑳𝑶𝑮(𝑳 𝜷𝟓 𝑫𝑼𝑴 𝒖𝒊

Dependent Variable: RNT


Method: Least Squares
Date: 12/04/09 Time: 00:00
Sample: 1 35
Included observations: 35

Variable Coefficient Std. Error t-Statistic Prob.

C 0.226191 0.390235 0.579626 0.5665


LOG(INF) 0.466068 0.127299 3.661212 0.0010
LOG(S) 0.013936 0.120933 0.115237 0.9090
LOG(L) 0.023982 0.102742 0.233423 0.8170
DUM 0.040095 0.123223 0.325386 0.7471

R-squared 0.350766 Mean dependent var 0.622857


Adjusted R-squared 0.264201 S.D. dependent var 0.257917
S.E. of regression 0.221238 Akaike info criterion -0.047595
Sum squared resid 1.468383 Schwarz criterion 0.174598
Log likelihood 5.832913 Hannan-Quinn criter. 0.029106
F-statistic 4.052067 Durbin-Watson stat 2.159101
Prob(F-statistic) 0.009609

𝑹𝑵𝑻𝒊 𝜷𝟏 𝜷𝟐 𝑳𝑶𝑮(𝑰𝑵𝑭 𝜷𝟒 𝑳𝑶𝑮(𝑳 𝜷𝟓 𝑫𝑼𝑴 𝒖𝒊

Dependent Variable: RNT


Method: Least Squares
Date: 12/04/09 Time: 02:03
Sample: 1 35
Included observations: 35

Variable Coefficient Std. Error t-Statistic Prob.

C 0.260144 0.251768 1.033269 0.3095


LOG(INF) 0.467213 0.124875 3.741456 0.0007
LOG(L) 0.023715 0.101068 0.234649 0.8160
DUM 0.044183 0.116112 0.380521 0.7062

R-squared 0.350478 Mean dependent var 0.622857


Adjusted R-squared 0.287621 S.D. dependent var 0.257917
S.E. of regression 0.217688 Akaike info criterion -0.104295
Sum squared resid 1.469033 Schwarz criterion 0.073459
Log likelihood 5.825168 Hannan-Quinn criter. -0.042935
F-statistic 5.575806 Durbin-Watson stat 2.154624
Prob(F-statistic) 0.003533

Econometrics Project Page 21


House Renting of FMT – 07 Students

Test the dropping of variable LOG(S) whether it is relevant or not in the regression model?
Unrestricted model: ( ( (
Restricted model : ( (
F-test:

(
( (
(
( (

( (

Since => Not reject


Conclusion: LOG(S) is a relevant variable in the regression model.

3. ERRORS IN THE MODEL

3.1. Heteroskedasticity:

The first error we checked in our model is heteroskedasticity. This error will happen when variances of
residuals in any model change according to changes in dependent and independent variables.
Heteroskedasticity leads to bigger variances of coefficients and unreliable t and F statistics.

For detection of this error, White test was used, testing the hypotheses:

Econometrics Project Page 22


House Renting of FMT – 07 Students
Heteroskedasticity Test: White

F-statistic 2.399476 Prob. F(13,21) 0.0359


W=Obs*R-squared 20.91770 Prob. Chi-Square(13) 0.0746
Scaled explained SS 12.56630 Prob. Chi-Square(13) 0.4818

Test Equation:
Dependent Variable: RESID^2
Method: Least Squares
Date: 12/04/09 Time: 03:02
Sample: 1 35
Included observations: 35
Collinear test regressors dropped from specification

Variable Coefficient Std. Error t-Statistic Prob.

C -2.346698 0.839863 -2.794144 0.0109


LOG(INF) -0.006804 0.501763 -0.013561 0.9893
(LOG(INF))^2 -0.044964 0.083099 -0.541091 0.5941
(LOG(INF))*(LOG(S)) -0.087854 0.107709 -0.815654 0.4239
(LOG(INF))*(LOG(L)) 0.105999 0.155528 0.681542 0.5030
(LOG(INF))*DUM 0.105405 0.210013 0.501898 0.6210
LOG(S) 1.254197 0.458924 2.732907 0.0125
(LOG(S))^2 -0.208207 0.071864 -2.897245 0.0086
(LOG(S))*(LOG(L)) -0.056535 0.083587 -0.676359 0.5062
(LOG(S))*DUM 0.076132 0.184623 0.412363 0.6843
LOG(L) 0.616459 0.266607 2.312236 0.0310
(LOG(L))^2 -0.103241 0.043377 -2.380121 0.0269
(LOG(L))*DUM 0.032650 0.128378 0.254326 0.8017
DUM -0.298027 0.547303 -0.544538 0.5918

R-squared 0.597649 Mean dependent var 0.041954


Adjusted R-squared 0.348574 S.D. dependent var 0.054435
S.E. of regression 0.043935 Akaike info criterion -3.123054
Sum squared resid 0.040535 Schwarz criterion -2.500915
Log likelihood 68.65345 Hannan-Quinn criter. -2.908292
F-statistic 2.399476 Durbin-Watson stat 1.901339
Prob(F-statistic) 0.035937

W=Obs*R-squared=20.91770

( (

=> Reject
Conclusion: There is the heteroskadasticity error existing in the model.

Econometrics Project Page 23


House Renting of FMT – 07 Students
Therefore, we need to remedy it.

Dependent Variable: RNT


Method: Least Squares
Date: 12/04/09 Time: 03:31
Sample: 1 35
Included observations: 35
White Heteroskedasticity-Consistent Standard Errors & Covariance

Variable Coefficient Std. Error t-Statistic Prob.

C 0.226191 0.203688 1.110476 0.2756


LOG(INF) 0.466068 0.145468 3.203924 0.0032
LOG(S) 0.013936 0.075629 0.184268 0.8550
LOG(L) 0.023982 0.061385 0.390689 0.6988
DUM 0.040095 0.082511 0.485936 0.6305

R-squared 0.350766 Mean dependent var 0.622857


Adjusted R-squared 0.264201 S.D. dependent var 0.257917
S.E. of regression 0.221238 Akaike info criterion -0.047595
Sum squared resid 1.468383 Schwarz criterion 0.174598
Log likelihood 5.832913 Hannan-Quinn criter. 0.029106
F-statistic 4.052067 Durbin-Watson stat 2.159101
Prob(F-statistic) 0.009609

3.2. Multicolinearity

The error that we checked secondly in our model is multicollinearity. This phenomenon occurs when
there are some functional relationships existing among independent variables. If a model has this type
of error, it will have less accurate coefficients, insignificant t-statistics…
To detect multicollinearity, auxiliary regression was used. We ran the regression showing the
relationship among an independent variable - INF - and other remaining independent ones and got an
eview table as follows:

Econometrics Project Page 24


House Renting of FMT – 07 Students
Dependent Variable: LOG(INF)
Method: Least Squares
Date: 12/04/09 Time: 03:43
Sample: 1 35
Included observations: 35

Variable Coefficient Std. Error t-Statistic Prob.

C -0.131141 0.550077 -0.238405 0.8131


LOG(S) 0.074128 0.170103 0.435786 0.6660
LOG(L) 0.148246 0.142491 1.040386 0.3062
DUM 0.095930 0.172998 0.554516 0.5832

R-squared 0.083468 Mean dependent var 0.556151


Adjusted R-squared -0.005228 S.D. dependent var 0.311330
S.E. of regression 0.312143 Akaike info criterion 0.616500
Sum squared resid 3.020432 Schwarz criterion 0.794254
Log likelihood -6.788755 Hannan-Quinn criter. 0.677861
F-statistic 0.941053 Durbin-Watson stat 0.533759
Prob(F-statistic) 0.432701

From the eview table above, we obtain the equation:


(̂ ) ( (

Testing the hypotheses:


There is no relationship among independent variables

There is relationship among independent variables

( (
( ( ( (
( (

Since
=> Not reject
=> There is no relationship among independent variables.

3.3. Autocorrelation

Finally, we check the autocorrelation error that is defined as “correlation between members of series of
observations ordered in time (as in time series data) or space (in cross- sectional data).

In order to detect this type of error, the Breusch-Godfrey (BG) Test of higher order autocorrelation is
used at 5% level of significance.

Econometrics Project Page 25


House Renting of FMT – 07 Students

Testing the hypotheses:


No autocorrelation

Autocorrelation exists

Run the residual test then we got the following table of eview table:
Breusch-Godfrey Serial Correlation LM Test:

F-statistic 0.648029 Prob. F(4,26) 0.6333


BG-statistic =Obs*R-squared 3.173045 Prob. Chi-Square(4) 0.5293

Test Equation:
Dependent Variable: RESID
Method: Least Squares
Date: 12/04/09 Time: 03:51
Sample: 1 35
Included observations: 35
Presample missing value lagged residuals set to zero.

Variable Coefficient Std. Error t-Statistic Prob.

C 0.073938 0.413203 0.178938 0.8594


LOG(INF) -0.033424 0.136614 -0.244661 0.8086
LOG(S) -0.026173 0.136481 -0.191773 0.8494
LOG(L) 0.015963 0.109970 0.145160 0.8857
DUM -0.037783 0.131558 -0.287200 0.7762
RESID(-1) -0.136678 0.205057 -0.666537 0.5109
RESID(-2) -0.192576 0.203537 -0.946149 0.3528
RESID(-3) -0.294415 0.228736 -1.287140 0.2094
RESID(-4) -0.060641 0.235914 -0.257045 0.7992

R-squared 0.090658 Mean dependent var -1.24E-16


Adjusted R-squared -0.189139 S.D. dependent var 0.207817
S.E. of regression 0.226619 Akaike info criterion 0.085942
Sum squared resid 1.335262 Schwarz criterion 0.485889
Log likelihood 7.496016 Hannan-Quinn criter. 0.224003
F-statistic 0.324015 Durbin-Watson stat 2.052689
Prob(F-statistic) 0.949299

BG-statistic = Obs*R-squared = 3.173045


(
Since BG-statistic <

=> Not reject

=> The autocorrelation error does not exist in the model.

Econometrics Project Page 26


House Renting of FMT – 07 Students

4. DISCUSSION

Dependent Variable: RNT


Method: Least Squares
Date: 12/04/09 Time: 03:31
Sample: 1 35
Included observations: 35
White Heteroskedasticity-Consistent Standard Errors & Covariance

Variable Coefficient Std. Error t-Statistic Prob.

C 0.226191 0.203688 1.110476 0.2756


LOG(INF) 0.466068 0.145468 3.203924 0.0032
LOG(S) 0.013936 0.075629 0.184268 0.8550
LOG(L) 0.023982 0.061385 0.390689 0.6988
DUM 0.040095 0.082511 0.485936 0.6305

R-squared 0.350766 Mean dependent var 0.622857


Adjusted R-squared 0.264201 S.D. dependent var 0.257917
S.E. of regression 0.221238 Akaike info criterion -0.047595
Sum squared resid 1.468383 Schwarz criterion 0.174598
Log likelihood 5.832913 Hannan-Quinn criter. 0.029106
F-statistic 4.052067 Durbin-Watson stat 2.159101
Prob(F-statistic) 0.009609

Our model is:


̂ ( (
(

The value 0.350766 of R-square that means approximately 35% of the variance in the house renting
cost will be explained by the changes in the students’ income flow, the area of room rent, the average
real estate price and the living condition.

Except LOG (INF), P-values of coefficients of all the other independent variables are greater than α at
the 10%, 5% and 1% level of significance, therefore the coefficients of LOG(S), LOG(L) and
LOG(DUM) are statistically insignificant at the three level of α in the model.
The positive slope coefficients of all independent variables show the positive relationship between
them and the dependent variable. The below explanation will carry out with holding the other variables
constant.
̂
When the income flow increases by 1%, the house rent cost that one non-hanoian student is
willing to pay will increase by approximately VND 4,500 (=0.01*VND 0.466068 million) per

Econometrics Project Page 27


House Renting of FMT – 07 Students
month and vice versa. Now, for example, the monthly income flow of one non-hanoian student is
VND 1million, he/she will be willing to pay VND 233,000 ((=0.50*VND 0.466068 million) more
for renting house if his/her monthly income flow is 1.5 million.
̂
One non-hanoian student has to pay about VND 14,000 per month more if the area of his/her
room doubles and vice versa.
̂
If the average real estate price of 1m2 in the district of Hanoi decreases by 50%, one non –
hanoian student renting house can save approximately VND 12,000 (0.50*VND 0.023982
million) per month and vice versa.
̂
The number 0.040095 shows that the room or house rent with good and convenient condition
living will cost about VND 40,000 more of one student monthly and vice versa.

 The monthly income flow of one student and the living condition of house rent affect on the house
rent cost of his/her per month. Whereas, there is a little relationship between the area of
room/house rent, the average price estate in Hanoi districts and the monthly house rent cost that
one non-hanoian student has to pay.

SUMMARY AND CONCLUSION

This project was conducted to investigate the influences of students’ income flow including family’s
supports and part time job’s wages, the location of that renting house in Hanoi, the area of the room on
average and the living condition (WC, atmosphere, internet, security and convenient for
transportation).

We attained 40 questionnaires in order to get the data. However, only 35 accurate respondents used to
fulfill this project. Along with whole-hearted instruction of econometrics-course lecturer, the
functional model showing the relationship among these variables and RNT was established. At first, we
ran ordinary least square method and obtained a linear equation. However, to improve the accuracy and
practical fitness as well as to reduce errors in the model, we transferred it to linear-log form and used
this model to evaluate the stated effects.

The following conclusions are drawn from the analysis of the data of all variables from 35

Econometrics Project Page 28


House Renting of FMT – 07 Students
observations:

 The change in the area of room or house rent, the average real estate price and monthly house
renting cost have the positive relationship. Especially, when the monthly income flow of one
non-hanoian student and the living condition of house rent fluctuate then they will positively
affect on the monthly house renting cost.
 There are not only four factors mentioned in this report but also lots of other ones that have
influences on house rent for students; specially inflation that may us find difficulty in predicting
the house rent for students in different time.

The results from this project may encourage house hosts improve their renting room or house like
adding facilities or creating more convenience for students to increase monthly house rent. Moreover,
non-hanoian student can choose accommodation that most suitable with their pocket and interest. In
addition, Universities and Colleges as well as Government should pay attention more to the
accommodations of students such as build more hostels and may be rearranging the location of
Universities and Colleges in order to reduce accommodation - burden cost for non-local students.

We are not sure whether this report is highly evaluated or not in term of its practical application of the
result model but the most interesting and useful is that we could found and applied the theory of
ecometrics to reality as well as understand and explain its numbers and data. From my point of view, it
is the most important thing that teachers had expected us gain after doing this research. And we are
winners because of this achievement.

Econometrics Project Page 29


House Renting of FMT – 07 Students

REFERENCES
1. Sample questionnaires

QUESTIONAIRE
Hello! We are come from Tutorial 2 – BA07. .......................................................... This survey is
conducted in order to investigate what and how some factors affect on the house rent of Non-Hanoi
students of BA-07. Could you please answer some questions below?
Name: ................................................
Class: .................................................
E-mail: ...............................................
Phone number: ...................................
1. Which district are you living on in Hanoi?

...............................................................................................................................
2. What is your income flow including family’s support and part time’s wages?

...............................................................................................................................
3. How much money do you pay for your current renting room or house?

...............................................................................................................................
4. How big is your current renting room or house approximately?
..............................................................................................................................

5. What is the condition of your current renting room or house?

A. Good (Convenient for transportation, Security, WC…)

B. Bad (Not meet criteria above)

6. Are you living alone or living with?

A. Alone C. Your sisters/brothers/partners/relatives


B. Schoolmates D. Others

Econometrics Project Page 30


House Renting of FMT – 07 Students
7. Are you satisfied with your current renting house?
A. Satisfied
B. Acceptable
C. Unsatisfied
Please give more detailed reasons:
...............................................................................................................................................

8. In your opinion, how much does the living condition have an impact on student’s life?
A. High
B. Medium
C. Small
D. Hardly
9. Do you think which is more advantaged for students?
A. Hostel
B. Renting a house
C. Your own idea
(Please give your detailed opinion)...……………………………………………………....
……………………………………………………………………………………………...

Econometrics Project Page 31


House Renting of FMT – 07 Students

2. List of respondents

1 Bùi Tỵ BA - 07 greenweed57@gmail.com
2 Đặng Thị Thanh Tâm BA - 07 thanhtam89_3k07@yahoo.com 0164 9583 522
3 Đào Duy Khương BA - 07 daokhuong_hanu07@yahoo.com
4 Đỗ Đức Thụ BA - 07 doducthu89@gmail.com 0166 818 8718
5 Đoàn Lê Thoa BA - 07 doanlethoajt@gmail.com 0168 8770 4740
6 Đoàn Thị Thu Mai BA - 07 doanmai1kt07@yahoo.com 0169 4515 024
7 Nguyễn Quang Vinh BA - 07 quangvinh.nguyen88@gmail.com 0169 3977 765
8 Nguyễn Thị Huệ BA - 07 nguyenthihue1989@gmail.com 0166 9588 129
9 Nguyễn Thị Lan Anh BA - 07 lananh_nt1102@gmail.com 0975 904 191
10 Nguyễn Thị Thanh Nga BA - 07 thanhngahanu@yahoo.com 0125 437 4830
11 Nguyễn Thị Vân BA - 07 cherryxanh1010@gmail.com 0168 826 9495
12 Phạm Thị Hương BA - 07 huong.phamt@yahoo.com 0974 244 819
13 Phùng Tiến Đức BA - 07
14 Tô Thị Quỳnh Trang BA - 07 trangpus.tg@gmail.com 0915 811 889
15 Trần Huyền Trang BA - 07
16 Trần Lê Thu Thảo BA - 07 thaotranlethu@gmail.com 0986 179 972
17 Trần Ngọc Lan BA - 07 0973 351 602
18 Trần Thị Quỳnh Trang BA - 07 lovelydollytran@yahoo.com.vn 098 6765 216
19 Đỗ Thùy Trang FB - 07 zondy_leenfans@yahoo.com
20 Nguyễn Thanh Vân FB - 07 nguyenthanhvanhl@gmail.com 0915 510 668
21 Nguyễn Thị Vân Hải FB - 07 vanhai@gmail.com
22 Phạm Thị Vân FB - 07 hoalocvung60@yahoo.com 0979 428 125
23 Ngô Thị Thúy Vân KT - 07 phuongvan_89@gmail.com
24 Phạm Khánh Ly KT - 07 lilypham2610@gmail.com 0979 606 018
25 Trần Thị Quế KT - 07 quetran050788@yahoo.com
26 Đỗ Thị Huệ TC - 07 onlylove558@yahoo.com
27 Nguyễn Diệu Tuyết TC - 07 snowhanu_6107@yahoo.com 0943 801 201
28 Nguyễn Thị Quyên TC - 07 quyen4907@gmail.com 0169 700 209
29 Vũ Thị Thu Hằng TC - 07 vuthithuhang@gmail.com
30 Bùi Thế Vũ TR - 07
31 Đào Ngọc Lình TR - 07
32 Đào Thị Phương TR - 07 daophuong89@yahoo.com 0975 612 302
33 Dương Hồng Hạnh TR - 07
34 Ngô Thị Lan Hương TR - 07 ngolanhuong1989@yahoo.com
35 Nguyễn Thị Khuyên TR - 07 vanhkhuyen@yahoo.com 0982 482 019

Econometrics Project Page 32


House Renting of FMT – 07 Students

APENDIX
1. Dependent and independent variables

House rent Income flow Average real


Area of
Observation (VND (VND estate price Living
District room
s million/month million/month 2 (VND condition
(m ) 2)
) ) million/m
1 Ba Dinh 0.8 2.5 15 47 Good
2 Cau Giay 0.5 1.3 20 23 Good
3 Dong Da 0.45 1.7 18 27.3 Good
4 Dong Da 1 2 12 27.3 Good
5 Ha Dong 0.5 1.5 30 11.6 Good
6 Ha Dong 0.6 1.5 10 11.6 Good
7 Ha Dong 0.4 1.5 9 11.6 Not good
8 Ha Dong 0.8 2 10 11.6 Not good
9 Ha Dong 0.5 2 20 11.6 Good
10 Ha Dong 0.8 2 10 11.6 Good
11 Hoang Mai 0.8 2 15 17 Good
12 Thanh Tri 0.3 1.20 12 7 Not good
13 Thanh Tri 0.5 1 17 7 Not good
14 Thanh Tri 0.5 1.6 12 7 Good
15 Thanh Tri 0.5 1.7 10 7 Good
16 Thanh Xuan 0.35 1 14 17.9 Good
17 Thanh Xuan 0.35 1.2 20 17.9 Good
18 Thanh Xuan 0.4 1.2 20 17.9 Good
19 Thanh Xuan 0.3 1.2 12 17.9 Good
20 Thanh Xuan 0.4 1.3 10 17.9 Good
21 Thanh Xuan 0.5 1.5 12 17.9 Good
22 Thanh Xuan 0.9 1.5 15 17.9 Good
23 Thanh Xuan 0.8 1.5 12 17.9 Good
24 Thanh Xuan 0.35 1.5 17 17.9 Good
25 Thanh Xuan 1 1.64 15 17.9 Good
26 Thanh Xuan 0.6 1.8 8 17.9 Good
27 Thanh Xuan 0.6 2 20 17.9 Good
28 Thanh Xuan 0.5 2 10 17.9 Not good
29 Thanh Xuan 1.2 2.3 15 17.9 Good
30 Thanh Xuan 0.9 2.5 30 17.9 Good
31 Thanh Xuan 0.4 2.5 17 17.9 Good
32 Thanh Xuan 0.6 3 18 17.9 Good
33 Thanh Xuan 0.5 3 12 17.9 Good
34 Thanh Xuan 1.3 3.5 18 17.9 Good
35 Tu Liem 0.9 2.4 25 9 Good

Econometrics Project Page 33


House Renting of FMT – 07 Students

2. DATA SUMMARY:

List of variables having in model

Variable name Specification of variables Unit


Dependent variable
RNT Monthly house rent of one student (VND million/month)
Independent variables
INF Income flow of students
including family’s support &
part time’s wages (VND million/month)
RNT House rent for
one non-Hanoi student in Hanoi (VND million/month)

S Area of renting house or room (m 2 )

L Average real estate price

in Hanoi districts (VND million/ m 2 )

 D  1 : good
D Evaluation of living conditions 
 D  0 : notgood

THE END

Econometrics Project Page 34

Vous aimerez peut-être aussi