You are on page 1of 70

10475

104753140118
F224.0


Research on the Energy Efficiency of Henan Province and It's
Influencing Factors Based on Spatial Econometrics

A Dissertation Submitted to
the Graduate School of Henan University
in Partial Fulfillment of the Requirements
for the Degree of
Master of Economics

By
Luo Chaoyang
Supervisor:Prof. Dong Shuancheng
Date June, 2017

2017

2017

2017

LEDI

LEDI TFEE



2005 2008
LEDI

LEDI LEDI
Malmquist

I
18
18
0.43

: , , DEA ,

II
ABSTRACT

ABSTRACT

Energy is the material that supplies energy to nature and is the material basis of all human activities.
However, most of the energy, especially fossil fuels, are non-renewable resources, and the scarcity of en-
ergy has constrained human production and life. Therefore, energy-related issues have always been the
focus of academic attention. Economic development can not be separated from the energy input, with the
development of human society, especially in recent years, the rapid development of the global economy,
a series of energy problems began to increasingly prominent. From the supply level, both China and the
world are facing a more serious energy problem. There are three main ways to solve the contradiction
between energy supply and demand: First, "open source", that is, to increase energy supply to increase the
supply, which also includes the development and utilization of new energy sources, such as wind energy,
solar energy, nuclear energy, tidal energy; The second is "Throttling", that is, to limit the demand for en-
ergy. In that "throttling" will hinder the development of the economy, so "Throttling" is rather than a good
way; The third is "synergies", that is, to improve the efficiency of energy, use less energy inputs to bring
more outputs. Therefore, the development of new energy, optimize the management and effective alloca-
tion of energy resources, improve energy efficiency, reduce pollutant emissions has become an issue which
national economic development must be considered, and is also the standpoint of a country which want to
develop healthy in the world. Therefore, the scientific evaluation of energy efficiency, and to identify the
factors that affect energy efficiency for solving energy problems have a strong practical significance. In
this paper, I use a new low energy development index (LEDI) to evaluate the energy efficiency of Henan
Province, and to analyze the influencing factors of energy efficiency.

According to the empirical results of this paper, although the total energy efficiency (TFEE) has a
large difference in value, the two values have similar fluctuations and convergence characteristics. It can
be considered that the low energy consumption development index is a reasonable reflection of energy Ef-
ficiency indicators. This paper analyzes the spatial characteristics of low energy consumption development
in Henan Province, and finds out that the low energy consumption development index of Henan Province
is at the upper level of the whole country. In 2005-2008, the overall situation of Henan Province Which
is mainly affected by the development of heavy industry. From time point of view, the LEDI index of
Henan Province has gradually stabilized, and the radiation effect of provincial cities on neighboring cities
has gradually decreased. From the spatial point of view , Low energy consumption development index also
has obvious "agglomeration" effect, that is, the economic structure of the city's LEDI is also at the same
or similar level; Henan Province, LEDI level has an obvious regional imbalance. Finally, this dissertation

III
uses the Malmquist index to decompose the total factor productivity of Henan Province. The results show
that technological progress is an important index affecting the total factor production efficiency of Henan
Province. Henan Province, the industrialization of the "volume" on the increase, did not achieve the "qual-
ity" on a breakthrough, indicating that Henan Province has not yet made substantial progress at the view of
from extensive economic growth to intensive economic growth.
Through the spatial econometric model, this dissertation systematically analyzes the influencing fac-
tors of energy efficiency in 18 cities of Henan Province. According to the results of this study, the energy
efficiency between 18 cities of Henan Province has a strong positive spatial correlation. In the regres-
sion analysis, the spatial autocorrelation coefficient is 0.43, which indicates that the energy efficiency im-
provement of adjacent cities is helpful to improve the local energy efficiency; scientific and technological
progress, the tertiary industry accounted for a significant positive impact on energy efficiency, and property
rights system has a significant negative impact on energy efficiency; In addition, The impact of government
intervention, opening up and price doesn't have a significant effect on energy efficiency respectively, but
the combination of three variables has a significant impact on energy efficiency. Therefore, we should im-
prove the energy efficiency of Henan Province from the following aspects: encourage technology research
and development, increase investment in technology research and development; adjust the industrial struc-
ture, optimize industrial upgrading; encourage the development of market economy, reduce the proportion
of state-owned enterprises; Price supervision, the appropriate special subsidies for enterprises.

Key words: Energy Efficiency, Low Energy Development Index, DEA Model, Spatial Econo-
metric Model

IV

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . I

ABSTRACT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . III

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2

( ) . . . . . . . . . . . . . . . . . . . . . . . . . 2

1. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3

2. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3

( ) . . . . . . . . . . . . . . . . . . . . . . 5

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11

. . . . . . . . . . . . . . . . . . . . . . . 11

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12

. . . . . . . . . . . . . . . . . . . . . . . . . . . 13

. . . . . . . . . . . . . . . . . . . . . . . . . . . 15

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

( ) CCR BCC . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

( ) (TFEE) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17

( ) Malmquist . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

( ) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21

( ) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21

( ) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22

V
1. LEDI TFEE . . . . . . . . . . . . . . . . . . . . . . . . 23

2. LEDI . . . . . . . . . . . . . . . . . . . . . . . . . . 25

3.LEDI . . . . . . . . . . . . . . . . . . . . . . . . . . 27

( ) Malmquest . . . . . . . . . . . . . . . . . . . . . . . 29

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32

. . . . . . . . . . . . . . . . . . . . . . . . . . . . 33

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35

( ) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36

( ) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37

1. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37

2. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38

( ) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57

VI

2015 BP 2014
154979 403544

2015 EIA
GDP GDP 2014
70%

2014
2.27%
5.13%
UrbanAir
20 8

()

Patterson 1996

1.

-
2007b
1981
E / GDP

2.

Farrell 1957 Debreu


1951 Koopmans 1951
,
, Fare et al (2004)
DEA ,
Hu and Wang(2006) DEA
,
,
,
Sheng and Yang 2014
LEDI

3
Ferrier and Lovell(1990) Fare et al.(1994)
2008 1980 2005

2013
1990 2010
5
, 2013

,
Schmidt and sickles(1984)
, , ,
, ,
,

,
DEA - ,
,
,

Charnes, Cooper, Rhode( 1978) (CRS) DEA ,


Banker, Charnes Cooper( 1984) CRS ,
VRS) DEA
Hu and Wang 2006 DEA

2007
1995 2004
Honma and Hu (2008) DEA 1993
2003 TFEE EKC
Zhang and Cheng 2011
TFEE 23
22
2012 DEA

2009 2012 2014 2016


DEA

()

2002

2008

2007
2010 2010 2011
2013

Richard 1999 2002 2006 2010

2010
ECM

2012 Tobit

2008

Popp 2002

,
,
,
, , (2006)
, ,
2012 Tobit



Sheng and Yang 2014

Hu and Wang(2006)
TFEE 2005
2014 18

1-1


DEA




GDP

Malmquist

1-1

9
10

18 305 2-1

2008 2015 2007


600 1000 310.61 265.97
2007
73258.78
5219.19 1074.79
1
97.22

2-1

1
http://www.docin.com/p-137330246.html

11

2003 2014
12
( 2-2
:)

100 24

22
80
20


/%

60 18

40 16

14
20
12

0 10
2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014

2-2

2-2 2003 2012 2012


23467 2003 2.23 9.47%
2012

2-2 :
2014 77.7%
3.48 2006-2009
2010

12
2012 10%

8.4% 11.5%

GDP
2-3
2005 2012
1

25 1.6

1.4
20
1.2

1
15
0.8
10 0.6

0.4
5 /
0.2
0 0
2005 2006 2007 2008 2009 2010 2011 2012 2013 2014

2-3 2005-2014

2010 GDP

GDP GDP

20052009 GDP 2005 20102014 GDP 2010

GDP 2005

2013

13

2-4 2014

2-4 2014
1 /
1.54 / 3.5
2-4

14

2010

,
, Fre
(1985) DEA ,

DEA


Farrell(1957) Charnes, Copper,
Rhode 1978 CRS DEA CCR
Banker Charnes Cooper 1984 CRS
VRS DEA BCC

() CCR BCC

CCR DEA DMU

n DM Ui (i = 1, 2, ..., n) m j
xi = (x1i , x2i , ..., xmi ), (i = 1, 2, ..., n), yi = (y1i , y2i , ..., yji ), (i = 1, 2, ..., n)
v = (v1 , v2 , ..., vm ) u = (u1 , u2 , ..., uj )
xi , yi ,v u i DMU

15

j
T uj yji
u yi
hi = T = s=1
m , j = 1, 2, ..., n 3.1
v xi
vt xti
t=1

v u hi 1, i = 1, 2, ..., n, DM Ui
(x1 , y1 )
CRS


j


uj yj1

max h1 = s=1


m


vt xt1


t=1



j
uj yji
s.t. s=1

m 1, i = 1, 2, ..., n 3.2


vt xti


t=1



us 0, s = 1, 2, ..., j





vt 0, t = 1, 2, ..., m

DEA Charnes Cooper





min






n

s.t. k xk + s xi = 0


k=1
n

k yk s+ yi = 0 3.3




k=1



k 0, k = 1, 2, ..., n





s+ 0, s 0

s+ , s

i , s , s+ ,


= 1, s = 0, s+ = 0, DM Ui DEA
= 1, s , s+ DM Ui DEA
< 1, DM Ui DEA

16
BCC :


j

max hi = us ysi ui



s=1


m

s.t. vt xti = 1, i = 1, 2, ..., n
t=1 3.4

j m

u y vt xti ui 0


s si

s=1 t=1


u , v 1, s = 1, 2, , j; t = 1, 2, ..., m
s t

ui i ui = 0
ui 0 ui 0

() (TFEE)

Hu and Wang(2006) 3-1 CRS DEA

SS ,
,
Farrell ( 1957) ,A B OA /OA OB
/OB SS A A
CA C ( Farrell,1957)
A C A' A
A AA'
A'C AC=AA'+A'C A C
AC AC=0
1
Hu and Wang(2006) i t TFEE

AEIi,t LEIi,t T EIi,t


T F EEi,t = =
AEIi,t AEIi,t

i i t TFEE AEI
LEI TEI

17
E /Y
A
S

'
A
B

'
C B

'
S




/Y
D

3-1 CRS DEA

() Malmquist

Malmquist Malmquist.S. 1953


Caves Malmquist 1982 Malmquist
Caves
Malmquist Fare 1994
Malmquist Fare Malmquist

[ ] 12
Dt (xt+1 , y t+1 ) Dt+1 (xt+1 , y t+1 )
t
M (x , x t+1
,y ,y t t+1
)= 3.5
Dt (xt , y t ) Dt+1 (xt , y t )

Dt (xt , y t ) Dt+1 (xt+1 , y t+1 ) Dt (xt+1 , y t+1 )


t t+1 Dt+1 (xt , y t ) t+1 t
Fare Malmquist (EC)
(TC)

[ ]1
Dt+1 (xt+1 , y t+1 ) Dt (xt , y t ) Dt (xt+1 , y t+1 ) 2
M P I = EC T C = 3.6
Dt (xt , y t ) Dt+1 (xt , y t ) Dt+1 (xt+1 , y t+1 )

EC t t+1 EC > 1
EC < 1 t t+1
TC t t+1 MPI

18
MP I > 1 t t+1
TC t t+1
TC > 1

MPI MP I > 1 t
t+1

()

DMU
yang and sheng LEDI =
DMU / DMU
DMU DMU
1 DMU

3-2 DEA

K L E GDP
Y K, L E Y X = (K, L, E) R+
N
, Y R+
M

T(Y)

T (Y ) = {(K, L, E) : (K, L, E) Y } , Y R+
M

K, L, E
3-2 OB

1 OB 1 A
tan AOA1 = AA1 /OA1 AB
tan BOB1 = BB1 /OB1
tan AOA1 tan BOB1 AB HED

19
(LED) LEDI

tan AOA1 AA1 /OA1


LEDI = =
tan BOB1 BB1 /OB1

LEDI (0, 1] LEDI=1


LEDI
LEDI

{
Y

B 2 B

S Y
A 2 A

S
}
E

O B 1
A 1
E

3-2

DMU T(Y)
Chambers et al. 1996 LEDI
{ }
Y /E

D(K, L, E, Y ) = inf : (K, L, E SE , Y + SY ) T
(Y + SY )/(E SE )

SY GDP SE
, D(K, L, E, Y )
X = (K, L, E) 0 D(K,
L, E, 0) = 0

D(K, L, E, 0) X Y X Y

D(K, L, E, Y )

20





Y /E
Min (Yj +SY jj)/(Ejj SEj )






N

s.t. i Yi Yj + SY j




i=1
N
i Xi Xj 3.7




i=1

N

i Ei Ej SEj




i=1


N

i = 1
i=1

Yj Ej Ei Xj
Xi i DMU i

()

18 2005 2014 200

2005 2013


GDP
2005 GDP

21
,

Kit = Kit1 (1 it ) + Iit

i i t t Kit i t Kit1 i
t-1 it i t Iit i t

1998
2004 Ki1999 = Ii1999 /(giI + ) Ki1999 i 1999
Ii1999 i 1999 giI i 1999 2008
2004
= 9.6% I 2005
3-1

3-1


200 51860.24 228417.4 230.4928 1783928
200 4502.364 16915.6 38.58 79690
200 19735.55 77220.51 333.3619 426000
200 17139.75 68496.65 144.3279 430431.2

()

MaxDEA 18
2005 2014

3-2 2005 2014 LEDI LEDI


2010 2012 LEDI
LEDI 0.7875 LEDI 0.6843
LEDI

22
3-2
LEDI
LEDI
LEDI LEDI
LEDI

3-2 2005-2014 LEDI

2005 2006 2007 2008 2009 2010 2011 2012 2013 2014
0.658 0.635 0.652 0.629 0.593 0.691 0.701 0.732 0.756 0.797 10
0.853 0.816 0.771 0.758 0.740 0.680 0.651 0.689 0.939 0.979 12
0.984 0.720 0.883 0.900 0.697 0.620 1.000 1.000 0.862 1.000 8
1.000 0.988 1.000 0.955 0.913 0.866 1.000 1.000 0.861 0.956 2
1.000 1.000 0.925 0.929 0.730 0.636 0.883 0.930 0.926 1.000 6
0.598 0.631 0.617 0.564 0.547 0.470 0.597 0.622 0.652 0.817 16
0.534 0.465 0.405 0.341 0.313 0.317 0.509 0.529 0.541 0.625 20
0.833 0.775 0.636 0.514 0.514 0.507 0.519 0.565 0.562 0.668 17
0.590 0.501 0.485 0.485 0.500 0.504 0.733 0.778 0.755 0.862 14
0.819 0.652 0.503 0.401 0.421 0.416 0.657 0.694 0.729 0.844 15
0.496 0.502 0.523 0.496 0.525 0.501 0.693 0.665 0.718 0.896 18
1.000 0.964 0.900 0.806 0.795 0.711 1.000 0.953 0.891 1.000 5
1.000 1.000 1.000 1.000 0.997 0.941 1.000 0.988 1.000 1.000 1
0.551 0.449 0.407 0.408 0.453 0.430 0.553 0.607 0.632 0.690 19
0.913 0.893 0.851 0.802 0.801 0.772 1.000 1.000 1.000 1.000 4
0.843 0.805 0.734 0.666 0.645 0.640 0.694 0.698 0.730 0.868 11
0.708 0.625 0.625 0.593 0.587 0.523 0.773 0.523 0.775 0.551 13
0.880 0.982 0.881 0.827 0.816 0.746 1.000 0.968 0.854 0.853 7
0.908 0.963 0.951 0.886 0.865 0.797 0.891 0.888 0.765 0.586 9
0.668 0.984 0.888 0.830 1.000 0.936 1.000 0.949 0.989 1.000 3

1.LEDI TFEE

3-3 BCR TFEE


TFEE LEDI

LEDI

23
3-3 2005-2014 BCR

2005 2006 2007 2008 2009 2010 2011 2012 2013 2014
1.00 0.99 1.00 1.00 0.94 0.75 1.00 1.00 0.87 1.00 4
1.00 0.99 0.98 0.97 0.95 0.93 1.00 0.98 0.87 0.87 7
1.00 1.00 1.00 1.00 0.99 0.97 1.00 0.99 0.95 1.00 3
1.00 0.86 0.71 0.72 0.78 0.72 0.89 0.84 0.79 0.80 12
0.78 0.68 0.55 0.62 0.62 0.62 0.77 0.75 0.72 0.71 17
1.00 0.97 0.92 0.89 0.87 0.84 0.84 0.85 0.84 0.89 9
0.78 0.74 0.70 0.69 0.66 0.65 0.71 0.74 0.72 0.74 16
1.00 0.84 0.78 0.73 0.80 0.76 0.92 0.92 0.91 0.92 10
0.72 0.73 0.76 0.77 0.79 0.80 0.84 0.82 0.79 0.81 15
1.00 0.98 0.96 0.95 0.95 0.97 1.00 0.97 0.98 1.00 6
1.00 1.00 1.00 1.00 0.99 0.99 1.00 1.00 1.00 1.00 2
0.84 0.82 0.83 0.84 0.82 0.81 0.83 0.83 0.81 0.88 12
1.00 0.97 0.95 0.94 0.93 0.92 1.00 1.00 1.00 1.00 5
0.87 0.84 0.82 0.80 0.79 0.77 0.79 0.77 0.75 0.76 14
0.76 0.72 0.69 0.67 0.66 0.64 0.70 0.69 0.65 0.65 18
0.97 0.94 0.89 0.87 0.87 0.84 1.00 0.99 0.92 0.98 8
0.96 0.94 0.91 0.89 0.88 0.86 0.88 0.85 0.79 0.77 11
1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 1

3-4 LEDI TFEE


2005 LEDI 10 TFEE
LEDI 14 TFEE
2006-2014 LEDI
3-3

LEDI SHORCKS(1978)
LEDI

1 j
m
M (i, j) = |R Rm
i
|
n m=1 m

j
M (i, j) i j 18 LEDI Rm m
j
j LEDI Rm m i LEDI n

24
3-4 LEDI TFEE

2005 2006 2007 2008 2009 2010 2011 2012 2013 2014
LE TF LE TF LE TF LE TF LE TF LE TF LE TF LE TF LE TF LE TF
5 1 11 4 7 1 4 1 9 6 10 14 1 1 1 1 6 8 1 1
1 1 3 4 1 5 2 5 3 4 3 5 1 1 1 7 6 8 7 11
1 1 1 1 4 1 3 1 8 2 8 3 9 1 8 5 4 5 1 1
14 1 13 11 12 15 12 15 12 15 15 15 15 10 14 12 15 12 13 13
17 15 17 18 18 18 18 18 18 18 18 18 18 16 17 16 18 16 16 17
10 1 10 7 11 8 13 8 14 9 12 8 17 12 16 10 17 10 15 9
15 15 15 15 16 16 15 16 15 16 13 16 11 17 10 17 10 16 10 16
11 1 12 12 15 13 17 14 17 12 17 13 14 9 12 9 12 7 12 8
18 18 15 16 14 14 14 13 13 13 13 11 12 12 13 14 14 12 8 12
1 1 6 6 5 6 8 6 6 4 7 3 1 1 6 8 5 4 1 1
1 1 1 1 1 1 1 1 1 2 1 2 1 1 4 1 1 1 1 1
16 14 18 14 17 11 16 11 16 11 16 10 16 14 15 13 16 11 14 10
6 1 8 7 9 7 9 7 6 7 5 6 1 1 1 1 1 1 1 1
9 13 9 12 10 12 10 12 10 13 8 12 12 15 11 15 12 15 9 15
12 17 14 17 12 17 11 17 11 16 11 17 10 18 18 18 9 18 18 18
8 11 4 9 7 10 6 10 5 9 6 8 1 1 5 5 8 6 11 7
6 12 6 9 3 9 5 8 4 8 4 7 8 11 9 10 10 12 17 14
13 1 4 1 6 1 6 1 1 1 1 1 1 1 6 1 3 1 1 1

n=18
3-3
TFEE LEDI
2005 2014 4 LEDI
2 LEDI
LEDI

2. LEDI

LEDI 3-4
LEDI 3-4
LEDI 0.65 0.95 LEDI
5% 35% 2005 2011
LEDI
LEDI 2010 LEDI
0.95 1 LEDI

25
4
LEDI TFEE
3.5

2.5

1.5

0.5

0
2006 2007 2008 2009 2010 2011 2012 2013 2014

3-3 LEDI TFEE

2010 LEDI
2010 2009 25.6% 2005-2009 LEDI
2010 LEDI

2005 0.22 2009 0.34


2013 0.28 LEDI

1.00

0.90

0.80

0.70

0.60

0.50

0.40
2005 2006 2007 2008 2009 2010 2011 2012 2013 2014

3-4 LEDI

3-4 LEDI U

26


1
N
(LEDIi LEDI)2
C.V =
LEDI

:LEDIi i LEDI LEDI LEDI N

0.3

0.25

0.2

0.15

0.1
2005 2006 2007 2008 2009 2010 2011 2012 2013 2014

C.V LDEI C.V TFEE

3-5 LEDI TFEE

3-5 LEDI U LEDI


, 0.17 0.28 TFEE
TFEE
0.1 0.15 TFEE

3. LEDI

LEDI
2005 2008 2011 2014 LEDI
3-6 LEDI 3-6(a)
2005 LEDI 7 LEDI 7

27
3-6(b) 2005
3 LEDI 3-6(c) 3-6(d)
2011 2014 2011 2014 7
LEDI 2008 2011 2014 LEDI
2008 9 LEDI
0.7 2011 7 LEDI 0.7 2014 4 LEDI 0.7
2008 LEDI
LEDI LEDI

LEDI 2014 LEDI LEDI


LEDI 0.2
LEDI

(a) 2005 LEDI (b) 2008 LEDI

(c) 2011 LEDI (d) 2014 LEDI

3-6 LEDI

28
() Malmquest

Deap2.1 2005 2014


Effch (Techch) (Pech)
(Sech) (Tfpch) 3-5

Effch
2005-2014 1
3-7(a) 3-5
2005 - 2014
1 2010 - 2011
0.982
Techch 2005-2014
5.68% 1.02% 0.44% 0.56%
0.5% 0.4% 3-7(b)
2010-2011 2008

Pech
3-5 3-7(c)
3-7(a) 3-7(c)

Sech
3-7(d) 2005-2014

2010-2011 3-7(d) 3-7(a)

Tfpch

29
2010-2011 EFFCH
1.005
1
2008 3-7(b)
0.995
0.99
3-7(e)
0.985
0.98
05-06 06-07 07-08 08-09 09-10 10-11 11-12 12-13 13-14

EFFCH PECH
TECHCH
EFFCH
TECHCH
1.015
1.16
1.005
1.005 1.01
1 1.11
1 1.005
0.995 1.06
1
0.995
0.99 1.16 1.01
0.995
0.99
0.985 0.99
0.96
0.985
0.98
1.11 0.985
0.91
0.98 05-0606-07
06-0707-08
07-0808-09
08-0909-10
09-1010-11
10-11 11-12
11-12 12-13
12-13 13-14
13-14
05-06 06-07 07-08 08-09 09-10 10-11 11-12 12-13 13-14 05-06
1.06
05-06 06-07 07-08 08-09 09-10 10-11 11-12 12-13 13-14








1.01 (a) EFFCH (b) TECHCH

0.96 PECH
PECH SECH
TFPCH
1.015
1.015 1.005
1.01
1.01 0.91 1.16
1
1.005 1.11
1.005
11
05-06 06-07 07-08 08-09 09-10 10-11 11-12 12-13 13-14
0.995
1.06
0.99
0.995
0.995 0.985
1.01
0.99
0.99 0.98
0.96
0.985
0.985 0.975
05-06
05-06 06-07
06-07 07-08
07-08 08-09
08-09 09-10
09-10 10-11
10-11 11-12
11-12 12-13
12-13 13-14
13-14 0.91
05-06 06-07 07-08 08-09 09-10 10-11 11-12 12-13 13-14
05-06 06-07 07-08 08-09 09-10 10-11 11-12 12-13 13-14







(c) PECH (d) SECH

1.005
SECH
SECH TFPCH
1.005
11
0.995
0.995
1.16
0.99
0.99
0.985
0.985 1.11
0.98
0.98
0.975
0.975 1.06
05-06
05-06 06-07
06-07 07-08
07-08 08-09
08-09 09-10
09-10 10-11
10-11 11-12
11-12 12-13
12-13 13-14
13-14
1.01


0.96
0.91
05-06 06-07 07-08 08-09 09-10 10-11 11-12 12-13 13-14


(e) TFPCH

3-7 Malmquist

30
3-5

EFFCH 0.999571 0.9998 0.9996 0.9968 0.997909 1.044


TECHCH 0.990286 0.9788 0.982133 0.9763 0.971182 1.002
2005-2006 PECH 1.000357 1.000733 1.000333 1.0009 1.002 1
SECH 0.999286 0.999133 0.999333 0.996 0.996 1.044
TFPCH 0.989857 0.9786 0.981733 0.9731 0.969091 1.046
EFFCH 0.988571 0.9904 0.989333 0.9931 0.992364 1.031
TECHCH 1.001143 0.990733 0.994733 0.9834 0.989 1.039
2006-2007 PECH 0.998 0.997533 0.998133 0.9986 0.998909 1
SECH 0.990786 0.993 0.9914 0.9947 0.993545 1.031
TFPCH 0.9895 0.980933 0.983867 0.9763 0.981182 1.071
EFFCH 0.996786 0.996267 0.997 0.9945 0.993636 1.032
TECHCH 0.990571 0.989867 0.9884 1.0018 1.001545 1.031
2007-2008 PECH 0.993429 0.994467 0.993867 0.999 0.997455 1
SECH 1.003571 1.001933 1.003333 0.9956 0.996182 1.032
TFPCH 0.987071 0.985867 0.985133 0.996 0.994909 1.064
EFFCH 0.998071 0.999467 0.9982 1.002 1.002909 0.991
TECHCH 1.013286 1.0024 1.0078 0.9863 0.984545 1.055
2008-2009 PECH 1.006071 1.005267 1.005667 1.0056 1.005455 1
SECH 0.992214 0.9944 0.992733 0.9965 0.997545 0.991
TFPCH 1.011357 1.001867 1.006 0.9884 0.987455 1.045
EFFCH 0.994286 0.995133 0.994133 0.9973 0.997545 1.002
TECHCH 1.000357 0.992667 0.994933 0.9901 0.988909 1.045
2009-2010 PECH 0.990357 0.9922 0.991 0.9964 0.998545 1
SECH 1.003857 1.002867 1.003067 1.0009 0.999 1.002
TFPCH 0.9945 0.9876 0.988933 0.9872 0.986364 1.047
EFFCH 0.985071 0.9852 0.982667 0.9907 0.992727 0.765
TECHCH 1.158429 1.1554 1.154467 1.08 1.097727 1.33
2010-2011 PECH 1.003 1.004933 1.0028 1.0101 1.006545 1
SECH 0.981643 0.979933 0.979467 0.981 0.986364 0.765
TFPCH 1.137571 1.135333 1.1316 1.0702 1.09 1.017
EFFCH 1.002214 0.996533 0.9976 0.9914 0.992636 0.999
TECHCH 0.983571 0.979267 0.978333 0.9788 0.978 0.997
2011-2012 PECH 1.002786 0.9984 0.9992 0.9968 0.994636 1
SECH 0.999571 0.998133 0.998467 0.9946 0.997909 0.999
TFPCH 0.985571 0.975933 0.976 0.9707 0.971182 0.996
EFFCH 0.998071 0.992933 0.995667 1.0006 0.994182 1.029
TECHCH 0.968286 0.964333 0.9632 0.9641 0.961818 0.964
2012-2013 PECH 0.995571 0.9906 0.992733 0.9969 0.991636 1
SECH 1.003 1.002733 1.0034 1.0038 1.002455 1.029
TFPCH 0.966571 0.957733 0.959267 0.9649 0.956455 0.992
EFFCH 0.999071 0.998067 0.9978 0.9973 0.997455 0.971
TECHCH 0.986143 0.986267 0.986133 0.9933 0.991273 1.048
2013-2014 PECH 0.997071 0.995 0.9958 0.9977 0.996182 1
SECH 1.002214 1.003333 1.002267 0.9998 1.001455 0.971
TFPCH 0.985286 0.984533 0.984133 0.9908 0.989091 1.018
EFFCH 0.995746 0.994867 0.994667 0.995967 0.995707 0.984889
TECHCH 1.01023 1.004415 1.00557 0.9949 0.996 1.056778
2005-2014 PECH 0.998516 0.997681 0.997726 1.000222 0.99904 1
SECH 0.997349 0.997274 0.997052 0.995878 0.996717 0.984889
TFPCH 1.005254 0.998711 0.99963 0.990844 0.991747 1.032889
31

DEA 18 2005 2014


LEDI 18
TFEE LEDI TFEE

18 2005 2014
2005 2008
LEDI

LEDI LEDI
Malmquist

2006
2002 2008

3-2 2005 2014 LEDI


2010 LEDI 0.636
2014 LEDI 1 3-4 2005 2014
LEDI 2010
LEDI

32

2005 2014


18
2005 2014 Moran s I

18

Techch

33
DEA-Malmquist

Stri

Strii

Gov

Open

Price

34
2005

state

1
2005 2015
2005
4-1

Variable Obs Mean Std. Dev. Min Max


ledi 180 0.753406 0.195354 0.313385 1
tech 162 1.007031 0.079442 0.922 1.555
stri 180 0.269516 0.057791 0.17241 0.46324
strii 180 0.568536 0.103646 0.380434 0.756756
gov 180 0.110272 0.035257 0.0269 0.207406
open 180 0.063709 0.080741 0.005497 0.396394
state 180 0.290407 0.128283 0.034985 0.629039
price 180 1.045446 0.066557 0.904569 1.21976


1
2005-2015

35
()

Wij

Wij Wij
:

0 1 0 1 0 1/2 0 1/2


1 0 1 0 1/2 0 1/2 0

Wij = , Wij = (4.1)

0 1 0 1 0 1/2 0 1/2


1 0 1 0 1/2 0 1/2 0

rook contiguity
Wij = 1, Wij = 0
4-1(a) 5 W53 = 1,
queen contiguity
Queen
1
0 4-1(a) 5 W53 = 1 W54 = 1,
W32 = 1 W34 = 1 W35 = 1

1 0
18
Rook i

36
CHAPTER 1. INTRODUCTION 12

2
(4)
4

(3) (5) 8

10

12
(2)

14

16

(1)
18

0 2 4 6 8 10 12 14 16 18
nz = 72

Figure 1.6: An illustration of contiguity


(a) (b)
Queen contiguity: For entities that share a common side or vertex with
the region of interest dene Wij = 1. For region 3 we would have: W32 =
1, W34 = 1, W35 = 1 and all other row elements zero.
4-1
There are of course other ways to proceed when dening a contiguity matrix.
For a good discussion of these issues, see Appendix 1 of Kelejian and Robinson
(1995). Note also that the double linear and double rook denitions are some-
times referred to as second order contiguity, whereas the other denitions are
termed rst order. More elaborate denitions sometimes rely on the length
of shared borders. This might impact whether we considered regions (4) and
(5) in Figure 1.6 as contiguous or not. They have a common border, but it
is very short. Note that in the case of a vertex, the rook denition rules out
a contiguity relation, whereas the bishop and queen denitions would record a
relationship.

j Wij = 1 Wij = 0 18
4-1(b)

()

SAR SEM

1.

SAR SLM
WY

y = W1 y + X +

= W2 + (4.2)

N (0, 2 In )

y n1 X nk W1 W2
nn

37
W2 = 0,

y = W1 y + X +
(4.3)
N (0, In ) 2

2.

y = X +

= W + (4.4)

N (0, 2 In )

y n1 X nk W nn

()

4-2

4-2

H0 H1
Morans I H0 H0
1
LM LM
LM-error H0 LM
=0 , = 0 SEM ,
=0
2
LM-lag H0
=0 , = 0 SAR
=0
RLM-error H0 RLM
=0 = 0 SEM ,
3
RLM-lag H0
=0 = 0 SAR

38
4-2 Moran's I Moran,1950


n
n
Wij (xi x)(xj x)
n i=1 j=1
I=
n
n
n
Wij (xi x)2
i=1 j=1 i=1
n n
Wij (xi x)(xj x)
i=1 j=1
=
n (4.7)
S2 (xi x)2
i=1


n
n
xi i S2 = 1
n
(xi x)2 x= 1
n
xi n W
i=1 i=1
n Wij i j
Moran's I [1,-1] I = 1 I = 1
I=0

(a) 2007 Lisa (b) 2012 Lisa

LISA 2007
LISA 2012
High-High (1) High-High (2)
Low-Low (4)
Low-Low (2)
(13)
(14)

(c) 2007 Lisa (d) 2012 Lisa

4-2 Lisa

4-2(a) 4-2(b) 2007 2012 Moran's I

39
Moran's I 0.286 0.185
LEDI 4-2(c) 4-2(d) 2007 2012
Lisa
Moran's I 4-3
2013 2014 10%
4-4 Moran's I
Moran's I 1% Moran's
I 10% LEDI

4-3 LEDI Morans I

2005 2006 2007 2008 2009 2010 2011 2012 2013 2014
Morans I 0.363 0.290 0.286 0.261 0.218 0.207 0.217 0.185 0.066 -0.056
Z 2.451 2.206 2.614 1.926 1.874 2.044 2.127 1.420 0.882 -0.072
Possibility 0.02 0.02 0.01 0.05 0.05 0.04 0.03 0.07 0.17 0.5

4-4

Morans I LM-lag LM-error RLM-lag RLM-error


50.61 0.1971 12.58 11.42 1.17 0.0034
168.25 0.3068 34.38 27.68 7.05 0.3594
59.14 0.1109 4.73 3.61 1.79 0.793
203.48 -0.05 0.0031 0.0857 9.57 10.3730
* 10%** 5%*** 1%

4-2 Moran's I LM 4-4


LM LM-error LM LM-lag
LM RLM-error RLM-lag
LM 4-4
Moran's I LM

4-2 SAR

40


N
LEDIit = i + Wij LEDIjt + 1 T ECHit + 2 ST RIit + 3 OP ENit
j=1

+ 4 GOVit + 5 P RICEit + 6 ST AT Eit + it

W LEDI TECH
STRI GOV PRICE
OPEN STATE
4-5
4-5

c 0.531 0.073 0.162


tech 0.375 0.369 0.443 0.265 0.647 0.365
stri 0.15 0.814 0.494 0.554 0.581 0.774
gov 0.588 0.885 0.162 0.374 1.104 1.31
open 0.392 0.187 0.665 0.064 0.514 0.118
price -0.169 0.043 0.052 0.087 0.023 0.127
state -0.419 -0.255 3.227 -2.258 3.727 3.258
0.268 0.432 0.178 0.099

N 180 180 162 162 162 162


R2 0.1801 0.2629 0.2475 0.8486 0.2894 0.8762
Adj-R2 0.1483 0.1870 0.2998 0.1715 0.1824
55.541 186.145 60.887 203.485
1
* 10%** 5%*** 1%
2
OLS
3

stata Elhorst Matlab


OLS

41
LEDI 5%
1% 1%
18 LEDI 10%

tech

tech 0.265 1%
1 0.265

stri LEDI
1
0.554

gov

open

price 0.087

state

42

2.258 1%
1 2.258

4-5
4-6 1 8 1
2 1
tobit 4 6 1

4-6

1 2 3 4 5 6

tech 0.265 0.3 0.431 0.263 0.27 0.273
stri 0.554 0.042 0.549 0.626 0.631
strii -1.308
gov 0.374 0.588 0.902
open 0.064 0.054 0.383 0.061
price 0.087 0.134 -0.007 0.090 0.008
state -2.258 -2.655 -0.433 -2.340 -2.380 -2.314
0.432 0.347 0.028 0.442 0.442 0.442
N 162 162 162 162 162 162
R2 0.849 0.863 0.300 0.849 0.849 0.848
Adj-R2 0.300 0.423 0.241 0.355 0.246 0.241
186.145 191.944 53.764 181.007 181.1 181
1
* 10%** 5%*** 1%
2

3
3 stata sptobitmstarxt

1 2 2
0 1
Tobit Elhorst tobit
stata sptobitmstarxt
3 1 3
gov open
4 6 1

43
F F

(SSRr SSRur )/q 2


(Rur Rr2 )/q
F = =
SSRur /(n k 1) (1 Rur
2 )/(n k 1)

q n k
2
Rur Rr2
6 1 R2 OLS
F gov open pirce
gov open pirce
LR = 2(Lur Lr ) Lur Lr
1 6
gov open pirce L = 10.29
3 2.5%
9.35 LR = 10.29 > 9.35

18
18
0.43

44

DEA LEDI 18 2005


2014 LEDI
2005
2008
Hu Wang 2006 TFEE

Malmquist

2010

18 2005 2014

45
46

[1] Anselin L, Le Gallo J, Jayet H. Spatial panel econometrics. In The econometrics of panel data[M].
Springer Berlin Heidelberg, 2008: 625-660.
[2] Anselin L, James P. The theory and practice of spatial econometrics[M]. University of Toledo Ohio,
1999 28-33.
[3] Banker RD, Charnes A, Cooper WW. Some models for estimating technical and scale inefficiencies
in data envelopment analysis[J]. Management science, 1984, 30(9):1078-1092.
[4] Chambers R G, Chung Y, Fre R. Benefit and distance functions[J]. Journal of economic theory,
1996, 70(2): 407-419.
[5] Chang M C. A comment on the calculation of the total-factor energy efficiency (TFEE) index[J].
Energy policy, 2013, 53: 500-504.
[6] Charnes A, Cooper WW, Rhodes E. Measuring the efficiency of decision making units[J]. European
journal of operational research, 1978, 2(6): 429-444.
[7] Debreu G. The coefficient of resource utilization[J]. Econometrica: Journal of the Econometric
Society, 1951: 273-292.
[8] Elhorst J P. Matlab software for spatial panels[J]. International Regional Science Review, 2014,
37(3): 389-405.
[9] Elhorst J P. Spatial panel models[M]. Handbook of Regional Science. Springer Berlin Heidelberg,
2014: 1637-1652.
[10] Farrell M J. The measurement of productive efficiency[J]. Journal of the Royal Statistical Society.
Series A (General), 1957, 120(3): 253-290.
[11] Filippini M, Hunt L C. Energy demand and energy efficiency in the OECD countries: a stochastic
demand frontier approach[J]. Energy Journal, 2011, 32(2): 59-80.
[12] Frazier C, Kockelman K. Spatial econometric models for panel data: incorporating spatial and tem-
poral data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2005,
1902: 80-90.
[13] He F, Zhang Q, Lei J, et al. Energy efficiency and productivity change of China s iron and steel
industry: Accounting for undesirable outputs[J]. Energy Policy, 2013, 54: 204-213.
[14] Honma S, Hu J L. Total-factor energy efficiency of regions in Japan[J]. Energy Policy, 2008, 36(2):
821-833.
[15] Hu J L, Wang S C. Total-factor energy efficiency of regions in China[J]. Energy policy, 2006, 34(17):

47
3206-3217.
[16] Kumar S. Environmentally sensitive productivity growth: a global analysis using Malmquist
Luenberger index[J]. Ecological Economics, 2006, 56(2): 280-293.
[17] Lee L, Yu J. Estimation of spatial autoregressive panel data models with fixed effects[J]. Journal of
Econometrics, 2010, 154(2): 165-185.
[18] Lee L, Yu J. Some recent developments in spatial panel data models[J]. Regional Science and Urban
Economics, 2010, 40(5): 255-271.
[19] Long X, Zhao X, Cheng F. The comparison analysis of total factor productivity and eco-efficiency
in China's cement manufactures[J]. Energy Policy, 2015, 81: 61-66.
[20] Millo G, Piras G. splm: Spatial panel data models in R[J]. Journal of Statistical Software, 2012,
47(1): 1-38.
[21] Moran P A P. A test for the serial independence of residuals[J]. Biometrika, 1950, 37(1/2): 178-181.
[22] Patterson M G. What is energy efficiency? Concepts, indicators and methodological issues[J]. En-
ergy policy, 1996, 24(5): 377-390.
[23] Popp D. Induced innovation and energy prices[J]. The American Economic Review, 2002, 92(1):
160-180.
[24] Schmidt P, Sickles RC. Production frontiers and panel data[J]. Journal of Business & Economic
Statistics, 1984 , 2(4): 367-374.
[25] Sheng P, Yang J. Low-energy development in China[J]. Applied Economics Letters, 2014, 21(9):
617-621.
[26] Shorrocks A F. The measurement of mobility[J]. Econometrica: Journal of the Econometric Society,
1978: 1013-1024.
[27] Xu, Xingbai, and Lung-fei Lee. Maximum likelihood estimation of a spatial autoregressive Tobit
model[J]. Journal of Econometrics, 2015, 188(1): 264-280.
[28] Zhang X P, Cheng X M, Yuan J H, et al. Total-factor energy efficiency in developing countries[J].
Energy Policy, 2011, 39(2): 644-650.
[29] , , .
[J]. , 2012, 22(1): 130-137.
[30] . [J].
, 2014(1): 180-92.
[31] , et al. [J]. , 2010, 32(4): 9-14.
[32] , et al. [J]. , 2011(3): 46-49.
[33] , , . :

48

[J]. , 2014(1): 134-147.


[34] . [D]. , 2014.
[35] , , . FDI 30
[J]. , 2015(3): 007.
[36] , , . [J]. ,
2010(4): 011.
[37] , , .
[J]. , 2014(1): 23-38.
[38] . [J].
, 2012(6): 57-69.
[39] , , .
[J]. , 2010(7): 43-55.
[40] , , . [J]. ,
2013(5): 96-114.
[41] , . [J]. , 2013(9): 125-136.
[42] , , , .
[J]. , 2014(8): 004.
[43] , , . [J]. , 2015(5):
004.
[44] , , . [J]. ,
2012(12): 15-20.
[45] , , . DEA
Malmquist [J]. , 2011(11): 38-43.
[46] . - Malmquist [J].
, 2009(8): 29-43.
[47] , . [J]. , 2014(8): 76-85.
[48] , . , [J]. , 2013(6): 6-18.
[49] . [J]. , 2002(9): 49-56.
[50] . [J]. , 2006(10): 49-58.
[51] , , , .
[J]. , 2008(2): 35-43.
[52] , , . (1987-2005) ,
[J]. , 2011(11): 29-39.

49
[53] , , , . , [J]. ,
2012(9): 99-112.
[54] , . [J]. , 2014(7): 27-35.
[55] , . [J]. ,
2010(4): 43-49.
[56] , , . [J]. , 2010(5):
95-109.
[57] , , , . [J]. ,
2011(6): 741-749.
[58] , , . SFA [J].
, 2013(5): 37-42.
[59] , , . [J]. ,
2010(6): 69-74.
[60] , , . (1978 2003)[J].
, 2006(2): 55-66.
[61] , . DEA [J]. , 2007(8): 66-76.
[62] . [D]. , 2009.
[63] , . [J]. , 2010(1): 128-37.
[64] , et al. : [J].
, 2011(9): 1661-1667.
[65] , . [J]. , 2016(3): 73-83.
[66] , . [J]. , 2010(5): 164-171.
[67] . [D]. , 2009.
[68] , , . [J].
, 2014(2): 151-7.
[69] , . K [J]. , 2003(7): 675-699.
[70] . [J]. , 2015(8): 73-88.
[71] , et al.
[J]. , 2013, 21(2): 175-84.
[72] , .
[J]. , 2006(12): 82-92.

50

Matlab

Elhorst
LeSage Matlab jplv7

1 clear all ;
2 clc
3 l o a d m a t l a b . mat ;
4 T = 9 ; % number o f t i m e p e r i o d s
5 N = 1 8 ; % number o f r e g i o n s
6 n o b s = N*T ;
7 % rown o r m a l i z e W
8 W = normw (W) ; % f u n c t i o n o f LeSage
9 y = l e d i ; % column number i n t h e d a t a m a t r i x t h a t c o r r e s p o n d s t o t h e
10 % dependent variable
11 x = [ t e c h c h s t r 1 gov open p r i c e s t a t e 2 ] ; % column numbers i n t h e d a t a
12 % matrix that correspond to the independent variables
13 for t = 1:T
14 t 1 = ( t 1)*N+ 1 ; t 2 = t *N;
15 wx ( t 1 : t 2 , : ) = W*x ( t 1 : t 2 , : ) ;
16 end
17 x c o n s t a n t = o n e s ( nobs , 1 ) ;
18

19 % No f i x e d e f f e c t s + s p a t i a l l y l a g g e d d e p e n d e n t v a r i a b l e
20 info . l f l a g = 0; % required for exact r e s u l t s
21 i n f o . model = 0 ;
22 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
23 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
24 r e s u l t s = s a r _ p a n e l _ F E ( y , [ x c o n s t a n t x ] ,W, T , i n f o ) ;
25 vnames = s t r v c a t ( ' l e d i ' , ' x c o n s t a n t ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' ,
26 ' price ' , ' state2 ' );
27 % Print out c o e f f i c i e n t estimates
28 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
29 % Print out e f f e c t s estimates

51
30 p a n e l _ e f f e c t s _ s a r ( r e s u l t s , vnames ,W) ;
31

32 %
33 % No f i x e d e f f e c t s + s p a t i a l l y l a g g e d d e p e n d e n t v a r i a b l e +
34 % s p a t i a l l y independent variables
35 info . l f l a g = 0; % required for exact r e s u l t s
36 i n f o . model = 0 ;
37 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
38 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
39 r e s u l t s = s a r _ p a n e l _ F E ( y , [ x c o n s t a n t x wx ] ,W, T , i n f o ) ;
40 vnames = s t r v c a t ( ' l e d i ' , ' x c o n s t a n t ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' ,
41 ' s t a t e 2 ' , 'W* t e c h c h ' , 'W* s t r 1 ' , 'W* gov ' , 'W* open ' , 'W* p r i c e ' , 'W* s t a t e 2 ' ) ;
42 % Print out c o e f f i c i e n t estimates
43 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
44 % Print out e f f e c t s estimates
45 p a n e l _ e f f e c t s _ s d m ( r e s u l t s , vnames ,W) ;
46

47 %
48 % S p a t i a l f i x e d e f f e c t s + s p a t i a l l y lagged dependent v a r i a b l e
49 info . l f l a g = 0; % required for exact r e s u l t s
50 i n f o . model = 1 ;
51 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
52 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
53 r e s u l t s = s a r _ p a n e l _ F E ( y , x ,W, T , i n f o ) ;
54 vnames = s t r v c a t ( ' l e d i ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' , ' s t a t e 2 ' ) ;
55 % Print out c o e f f i c i e n t estimates
56 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
57 % Print out e f f e c t s estimates
58 p a n e l _ e f f e c t s _ s a r ( r e s u l t s , vnames ,W) ;
59

60 %
61 % S p a t i a l f i x e d e f f e c t s + s p a t i a l l y lagged dependent v a r i a b l e +
62 % s p a t i a l l y independent variables
63 info . l f l a g = 0; % required for exact r e s u l t s
64 i n f o . model = 1 ;
65 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
66 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
67 r e s u l t s = s a r _ p a n e l _ F E ( y , [ x wx ] ,W, T , i n f o ) ;
68 vnames = s t r v c a t ( ' l e d i ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' ,

52
69 ' s t a t e 2 ' , 'W* t e c h c h ' , 'W* s t r 1 ' , 'W* gov ' , 'W* open ' , 'W* p r i c e ' , 'W* s t a t e 2 ' ) ;
70 % Print out c o e f f i c i e n t estimates
71 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
72 % Print out e f f e c t s estimates
73 p a n e l _ e f f e c t s _ s d m ( r e s u l t s , vnames ,W) ;
74

75 %
76 % Time p e r i o d f i x e d e f f e c t s + s p a t i a l l y l a g g e d d e p e n d e n t v a r i a b l e
77 info . l f l a g = 0; % required for exact r e s u l t s
78 i n f o . model = 2 ;
79 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
80 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
81 r e s u l t s = s a r _ p a n e l _ F E ( y , x ,W, T , i n f o ) ;
82 vnames = s t r v c a t ( ' l e d i ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' , ' s t a t e 2 ' ) ;
83 % Print out c o e f f i c i e n t estimates
84 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
85 % Print out e f f e c t s estimates
86 p a n e l _ e f f e c t s _ s a r ( r e s u l t s , vnames ,W) ;
87

88 %
89 % Time p e r i o d f i x e d e f f e c t s + s p a t i a l l y l a g g e d d e p e n d e n t v a r i a b l e +
90 % s p a t i a l l y independent variables
91 info . l f l a g = 0; % required for exact r e s u l t s
92 i n f o . model = 2 ;
93 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
94 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
95 r e s u l t s = s a r _ p a n e l _ F E ( y , [ x wx ] ,W, T , i n f o ) ;
96 vnames = s t r v c a t ( ' l e d i ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' ,
97 ' s t a t e 2 ' , 'W* t e c h c h ' , 'W* s t r 1 ' , 'W* gov ' , 'W* open ' , 'W* p r i c e ' , 'W* s t a t e 2 ' ) ;
98 % Print out c o e f f i c i e n t estimates
99 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
100 % Print out e f f e c t s estimates
101 p a n e l _ e f f e c t s _ s d m ( r e s u l t s , vnames ,W) ;
102

103 %
104 % S p a t i a l and t i m e p e r i o d f i x e d e f f e c t s +
105 % s p a t i a l l y lagged dependent v a r i a b l e
106 info . l f l a g = 0; % required for exact r e s u l t s
107 i n f o . model = 3 ;

53
108 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
109 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
110 r e s u l t s = s a r _ p a n e l _ F E ( y , x ,W, T , i n f o ) ;
111 vnames = s t r v c a t ( ' l e d i ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' , ' s t a t e 2 ' ) ;
112 % Print out c o e f f i c i e n t estimates
113 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
114 % Print out e f f e c t s estimates
115 p a n e l _ e f f e c t s _ s a r ( r e s u l t s , vnames ,W) ;
116

117 %
118 % S p a t i a l and t i m e p e r i o d f i x e d e f f e c t s + s p a t i a l l y l a g g e d d e p e n d e n t
119 % variable + s p a t i a l l y independent variables
120 % No b i a s c o r r e c t i o n
121 i n f o . bc = 0 ;
122 info . l f l a g = 0; % required for exact r e s u l t s
123 i n f o . model = 3 ;
124 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
125 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
126 r e s u l t s = s a r _ p a n e l _ F E ( y , [ x wx ] ,W, T , i n f o ) ;
127 vnames = s t r v c a t ( ' l e d i ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' ,
128 ' s t a t e 2 ' , 'W* t e c h c h ' , 'W* s t r 1 ' , 'W* gov ' , 'W* open ' , 'W* p r i c e ' , 'W* s t a t e 2 ' ) ;
129 % Print out c o e f f i c i e n t estimates
130 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
131 % Print out e f f e c t s estimates
132 p a n e l _ e f f e c t s _ s d m ( r e s u l t s , vnames ,W) ;
133

134 %
135 % S p a t i a l and t i m e p e r i o d f i x e d e f f e c t s + s p a t i a l l y l a g g e d d e p e n d e n t
136 % variable + s p a t i a l l y independent variables
137 info . l f l a g = 0; % required for exact r e s u l t s
138 i n f o . model = 3 ;
139 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
140 i n f o . bc = 1 ;
141 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
142 r e s u l t s = s a r _ p a n e l _ F E ( y , [ x wx ] ,W, T , i n f o ) ;
143 vnames = s t r v c a t ( ' l e d i ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' ,
144 ' s t a t e 2 ' , 'W* t e c h c h ' , 'W* s t r 1 ' , 'W* gov ' , 'W* open ' , 'W* p r i c e ' , 'W* s t a t e 2 ' ) ;
145 % Print out c o e f f i c i e n t estimates
146 p r t _ s p ( r e s u l t s , vnames , 1 ) ;

54
147 % Print out e f f e c t s estimates
148 p a n e l _ e f f e c t s _ s d m ( r e s u l t s , vnames ,W) ;
149

150 % random e f f e c t s e s t i m a t o r by ML
151

152 % S p a t i a l random e f f e c t s and t i m e p e r i o d f i x e d e f f e c t s + s p a t i a l l y


153 % lagged dependent v a r i a b l e + s p a t i a l l y independent v a r i a b l e s
154 [ y w i t h , x w i t h , meanny , meannx , meanty , meantx ] = demean ( y , [ x wx ] , N, T , 2 ) ;
155 % 2 = t i m e dummies
156 i n f o . model = 1 ;
157 r e s u l t s = s a r _ p a n e l _ R E ( y w i t h , x w i t h ,W, T , i n f o ) ;
158 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
159 % Print out e f f e c t s estimates
160 p a n e l _ e f f e c t s _ s d m ( r e s u l t s , vnames ,W) ;
161

162 %
163 % S p a t i a l and t i m e p e r i o d f i x e d e f f e c t s + s p a t i a l l y l a g g e d d e p e n d e n t
164 % variable + s p a t i a l l y independent variables
165 % No b i a s c o r r e c t i o n
166 i n f o . bc = 0 ;
167 info . l f l a g = 0; % required for exact r e s u l t s
168 i n f o . model = 3 ;
169 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
170 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
171 r e s u l t s = s a r _ p a n e l _ F E ( y , [ x wx ] ,W, T , i n f o ) ;
172 vnames = s t r v c a t ( ' l e d i ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' ,
173 ' s t a t e 2 ' , 'W* t e c h c h ' , 'W* s t r 1 ' , 'W* gov ' , 'W* open ' , 'W* p r i c e ' , 'W* s t a t e 2 ' ) ;
174 % Print out c o e f f i c i e n t estimates
175 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
176 % Print out e f f e c t s estimates
177 p a n e l _ e f f e c t s _ s d m ( r e s u l t s , vnames ,W) ;
178

179 %
180 % S p a t i a l and t i m e p e r i o d f i x e d e f f e c t s + s p a t i a l l y l a g g e d d e p e n d e n t
181 % variable + s p a t i a l l y independent variables
182 info . l f l a g = 0; % required for exact r e s u l t s
183 i n f o . model = 3 ;
184 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
185 i n f o . bc = 1 ;

55
186 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
187 r e s u l t s = s a r _ p a n e l _ F E ( y , [ x wx ] ,W, T , i n f o ) ;
188 vnames = s t r v c a t ( ' l e d i ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' ,
189 ' s t a t e 2 ' , 'W* t e c h c h ' , 'W* s t r 1 ' , 'W* gov ' , 'W* open ' , 'W* p r i c e ' , 'W* s t a t e 2 ' ) ;
190 % Print out c o e f f i c i e n t estimates
191 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
192 % Print out e f f e c t s estimates
193 p a n e l _ e f f e c t s _ s d m ( r e s u l t s , vnames ,W) ;
194

195 %
196 % S p a t i a l and t i m e p e r i o d f i x e d e f f e c t s +
197 % s p a t i a l l y lagged dependent v a r i a b l e
198

199 info . l f l a g = 0; % required for exact r e s u l t s


200 i n f o . model = 3 ;
201 i n f o . f e = 0 ; % no p r i n t i n t e r c e p t and s p a t i a l f i x e d e f f e c t s
202 % New r o u t i n e s t o c a l c u l a t e e f f e c t s e s t i m a t e s
203 r e s u l t s = s a r _ p a n e l _ R E ( y , x ,W, T , i n f o ) ;
204 vnames = s t r v c a t ( ' l e d i ' , ' t e c h c h ' , ' s t r 1 ' , ' gov ' , ' open ' , ' p r i c e ' , ' s t a t e 2 ' ) ;
205 % Print out c o e f f i c i e n t estimates
206 p r t _ s p ( r e s u l t s , vnames , 1 ) ;
207 % Print out e f f e c t s estimates
208 p a n e l _ e f f e c t s _ s a r ( r e s u l t s , vnames ,W) ;

56

2017 5

57
58

You might also like