A Network DEA Model with Super Efficiency and Undesirable Outputs: An Application to Bank Efficiency in China
Table 8
Regression results.
Variable
Overall efficiency
Efficiency of stage 1
Efficiency of stage 2
Model 1
Model 2
Model 3
Model 4
Model 5
Model 6
netloan_ta
0.362**
0.314
0.591***
0.555***
−0.063
−0.085
(−0.184)
(−0.195)
(−0.156)
(−0.163)
(−0.115)
(−0.120)
liqassets_stfund
0.660***
0.492**
0.543***
0.418**
0.323***
0.245**
(−0.186)
(−0.195)
(−0.158)
(−0.164)
(−0.117)
(−0.120)
net_int_margin
−2.326
−6.227***
2.557
−0.338
−6.442***
−8.253***
(−2.394)
(−2.380)
(−2.029)
(−1.993)
(−1.504)
(−1.460)
sharehold
12.483***
5.532
18.376***
13.217***
−4.006
−7.234**
(−4.764)
(−4.760)
(−4.039)
(−3.988)
(−2.992)
(−2.921)
list
22.257***
16.507***
10.334***
(−3.435)
(−2.878)
(−2.108)
ln_ta
7.175***
5.323***
3.331***
(−0.873)
(−0.740)
(−0.549)
g_gdp
0.043
−0.967
0.979
0.230
−0.634
−1.103
(−1.709)
(−1.799)
(−1.449)
(−1.507)
(−1.073)
(−1.104)
g_m2
0.004
−0.306
0.515*
0.285
−0.466**
−0.610***
(−0.316)
(−0.328)
(−0.268)
(−0.275)
(−0.198)
(−0.201)
hhi_gross_loan
138.769
−106.561
194.097
12.107
28.760
−85.150
(−213.555)
(−223.597)
(−181.055)
(−187.321)
(−134.150)
(−137.203)
Constant
−66.509**
61.524**
−78.720***
16.264
67.413***
126.861***
(−32.368)
(−28.782)
(−27.442)
(−24.113)
(−20.333)
(−17.661)
Log_likelihood
−795.508
−805.357
−764.967
−772.609
−709.495
−715.006
Wald_chi2
115.548
85.191
93.810
71.701
167.052
146.690
Note: we use the FGLS estimator with standard error (reported in brackets). ***, **, or *denotes significance at the level of 1%, 5%, or 10%, respectively. There are 185 observations for each model. Sample period is 2008–2012.