Skip to main content

Table 2 Panel OLS and 2SLS regression estimates

From: The cost-saving effect of continuity of care (COC): an analysis of institutional COC on diabetic treatment costs using panel 2SLS regressions

OLS model

OP costs

 

IP costs

 

Total costs

 

ln ICOC

-0.07

(0.005)

*

-1.71

(0.03)

**

-0.30

(0.006)

**

DCSI score

0.21

(0.002)

*

0.44

(0.01)

*

0.25

(0.002)

*

P4P

0.33

(0.005)

*

-0.27

(0.03)

*

0.26

(0.01)

*

Accreditation level (ref = community hospital)

Medical center

0.07

(0.01)

*

0.64

(0.06)

*

0.16

(0.01)

*

Regional hospital

0.08

(0.01)

*

0.49

(0.05)

*

0.12

(0.01)

*

Clinics

-0.40

(0.01)

*

-0.68

(0.05)

*

-0.45

(0.01)

*

Ownership (ref = for-profit)

Public

0.12

(0.01)

*

0.004

(0.05)

 

0.12

(0.01)

*

Non-profit

0.17

(0.01)

*

-0.11

(0.05)

*

0.16

(0.01)

*

constant

9.18

(0.01)

*

0.86

(0.04)

*

9.31

(0.01)

*

rho

0.50

 

0.20

 

0.39

 

Overall R2

0.25

 

0.10

 

0.26

 

2SLS model

ln ICOC

1.03

(0.26)

*

-11.62

(1.93)

**

-1.07

(0.31)

**

DCSI score

0.12

(0.01)

*

0.30

(0.07)

*

0.12

(0.01)

*

P4P

0.26

(0.01)

*

-0.40

(0.07)

*

0.16

(0.01)

*

Accreditation level (ref = community hospital)

Medical center

0.09

(0.01)

*

0.81

(0.09)

*

0.21

(0.01)

*

Regional hospital

0.05

(0.01)

*

0.85

(0.10)

*

0.16

(0.02)

*

Clinics

-0.47

(0.01)

*

-0.59

(0.06)

*

-0.51

(0.01)

*

Ownership (ref = for-profit)

Public

0.08

(0.01)

*

0.17

(0.07)

*

0.11

(0.01)

*

Non-profit

0.11

(0.01)

*

-0.03

(0.06)

 

0.101

(0.01)

*

F (15,152049)

3335

*

238

*

2283

*

Tests of instruments

Weak Instrument

(Anderson-Rubin Wald test F)

23.3

*

61.46

*

12.54

*

Wald test for endogeneity χ2(1)

30.56

*

46.68

*

5.75

†

  1. Note: *: p-value < 0.01; †: p-value < 0.05