Joint effects of ill-health, health shocks and social protection on the intensive margin of labour supply: evidence from Malawi

Table 4 Regression results of the zero-inflated Poisson model^a

Variables	dy/dxb^b	SE	Z	P>\|Z\|	95%CI
Illness/Injury	-0.558***	0.027	-20.47	0.000	-0.612, -0.505
Hospitalisation	0.002	0.045	0.04	0.972	-0.086,0.090
Chronic illness	0.252***	0.040	6.33	0.000	0.174,0.33
Social protection	-0.112***	0.024	-4.56	0.000	-0.159,-0.064
Illness/Injury*Social protection	-0.077*	0.044	-1.76	0.078	-0.162, 0.009
Hospitalisation *Social protection	-0.154***	0.015	-10.02	0.000	-0.184,-0.123
Chronic illness*Social protection	-0.194***	0.061	-3.17	0.002	-0.314,-0.074
Control Variables	YES

N (number of observations)= 94,846
dy/dx Marginal effects
***P<0.01, ** P<0.05, * P<0.1
The table shows marginal effects estimated by the zero-inflated Poisson model
Figures in parentheses are standard errors
Control variables included sex, age, religion, marital status, and education level
Values in the table were rounded off to three decimal places
^aResults of the zero-inflated negative binomial model and those of a standard OLS are presented in Table 5 in Appendix A. Unlike the OLS results of, the result of the zero-inflated negative binomial model mimicked the results of the zero-inflated Poisson model that we report in this study
^bIn our analysis and discussion, we use marginal effects owing to the non-linear nature of the zero-inflated Poisson model. We present coefficients of the regression model in Table 6 in Appendix B

ISSN: 2191-1991