Skip to main content

Table 4 Policy impact estimation on demand for hospital type (Multinomial logit - margins), from April 2016 to October 2017

From: Co-payments and equity in care: enhancing hospitalisation policy for Palestine refugees in Lebanon

 

(1)

(2)

(3)

 

PRCS

Private

Public

Policy

0.035***

0.037***

-0.019**

-0.017

-0.016***

-0.019**

 

(0.009)

(0.012)

(0.008)

(0.011)

(0.005)

(0.008)

Age

0.002***

0.002***

0.000

0.000

-0.003***

-0.003***

 

(0.000)

(0.000)

(0.000)

(0.000)

(0.000)

(0.000)

Age2

-0.000***

-0.000***

0.000

0.000*

0.000***

0.000***

 

(0.000)

(0.000)

(0.000)

(0.000)

(0.000)

(0.000)

Woman

0.007

0.007

-0.005

-0.005

-0.003

-0.003

 

(0.006)

(0.006)

(0.005)

(0.005)

(0.003)

(0.003)

Ramadan

-0.013

0.001

0.010

-0.011

0.003

0.010

 

(0.010)

(0.017)

(0.009)

(0.015)

(0.006)

(0.011)

Distance

0.031***

0.031***

0.021***

0.021***

-0.052***

-0.052***

 

(0.001)

(0.001)

(0.001)

(0.001)

(0.002)

(0.002)

Visit

-0.001

-0.000

-0.002

-0.002

0.002***

0.002**

 

(0.002)

(0.002)

(0.001)

(0.001)

(0.001)

(0.001)

Surgery

0.029***

0.029***

-0.007

-0.007

-0.022***

-0.022***

 

(0.007)

(0.007)

(0.006)

(0.006)

(0.005)

(0.005)

CLA

0.402***

0.402***

-0.446***

-0.446***

0.044***

0.043***

 

(0.015)

(0.015)

(0.017)

(0.017)

(0.007)

(0.007)

Month FE

 

Yes

 

Yes

 

Yes

Observations

33,469

33,469

33,469

33,469

33,469

33,469

Demand3 (%)

55.43

33.14

11.43

  1. 1*** p<0.01, ** p<0.05, * p<0.1. Robust standard errors in parentheses
  2. 2Note: The dependent variables are binary variables with the value 1 if the patient is at each hospital type and 0 otherwise. Note that all patients get treatment, thus for each observation at least one option must be selected. Coefficients show average marginal effects for multinomial logit regression results. Policy is a dummy variable that indicates the period after the last policy change (from June 2016 onwards). These model specifications control for individual and hospital specific variables
  3. 3Share of total visits by hospital type using full sample