Skip to main content

Advertisement

Table 8 Effect of P4P on service utilisation by subgroups –using the non–linear logit model

From: Who benefits from increased service utilisation? Examining the distributional effects of payment for performance in Tanzania

Subgrouping variables Institutional deliveries Uptake of IPT2
Average subgroup effect Differential effect test (p-value) Average subgroup effect Differential effect test (p-value)
N (dy/dx) N (dy/dx)
Marital status       
 Married 3385 9.2a (p = 0.503) 3253 9.2a (p = 0.935)
 Unmarried 1338 13.3a   1481 9.8c  
Maternal age       
 Younger below the median age 2361 11.2a (p = 0.492) 2336 9.2b (p = 0.830)
 Older above the median age 2325 9.1a   2421 9.5b  
Education       
 Some education 4021 10.9a (p = 0.070) 3877 8.6a (p = 0.793)
 No education/illiterate 900 9.1   816 16.5c  
Occupation       
 Farmer 2638 13.4a (p = 0.590) 2396 16.0a (p = 0.149)
 Non-farmer 2126 7.5b   2295 5.3  
Religion       
 Muslim 3991 10.8a (p = 0.497) 3614 9.7a (p = 0.554)
 Non-Muslim 980 5.6   1061 7.8  
Parity/births       
 One birth 1180 15.2a (p = 0.122) 1476 9.9c (p = 0.939)
 Two or more births 3436 9.3a   3247 10.0a  
Household size by members       
 Small size (< 5) 2381 7.3b (p = 0.320) 2464 7.6c (p = 0.903)
 Large size (≥5) 2299 12.8a   2281 9.1b  
Health insurance       
 Insured 171 −20.7 (p = 0.012) 315 18.3 (p = 0.900)
 Uninsured 4820 11.1a   4328 10.1a  
Household wealth status       
 Tercile 1 (poorest) 1656 13.4b (p = 0.894) 1508 13.2b (p = 0.145)
 Tercile 2 (middle) 1528 12.7a (p = 0.737) 1539 17.1a (p = 0.106)
 Tercile 3 (least poor) 1066 8.2b Reference 1599 2.4 Reference
Place of residence       
 Rural district 4387 11.3a (p = 0.152) 3851 11.2a (p = 0.268)
 Urban district 787 1.6   906 1.7  
  1. Non-linear logit model with FE, covariates, clustering at HF level; Logit with FE cuts down the sample size; dy/dx is the estimated partial P4P effect on a specific subgroup in terms of marginal effect after controlling for a year dummy, facility-fixed effects, and individual and household-level covariates (age, education, occupation, religion, marital status, parity, health insurance status, household size, and household wealth status); Each cell for dy/dx and differential effect reports the result from a separate regression; Differential effect test is a t-test of the null that the coefficient on the three-way interaction between the P4P effect and subgrouping indicator is zero; a denotes significance at 1%, bat 5%, and c at 10% level