Skip to main content

Table 5 Parameters used to estimate sample size, and the estimated size of reductions or increases that would be detectable

From: A cluster randomised controlled trial of the community effectiveness of two interventions in rural Malawi to improve health care and to reduce maternal, newborn and infant mortality

Parameter Source of estimate DHS parameter estimates (2006)
Number of clusters Geopolitical subdivisions and logistical efficiency 48
Population per cluster (Calculated) 3,000
Crude birth rate (per 1000 population) National data from MDHS* 42
Time frame (years) Funding period 2
Births per cluster within study period (Calculated) 252
Inter-cluster coefficient of variation (k) Hayes 1995 0.15-0.3
Statistical power of the study Probability of Type I error
Probability of Type II error
0.05
0.2
Neonatal mortality rate
(per 1000 live births)
National data from MDHS* 27
Size of reduction detectable (Calculated) 31-36%
Maternal mortality ratio
(per 100,000 live births)
National data from MDHS* 984
Size of reduction detectable (Calculated) 47-50%
Infant mortality rate (per 1000 live births) National data from MDHS* 76
Size of reduction detectable (Calculated) 21-28%
Exclusive breastfeeding (%) National data from MDHS* 27.5%
Size of increase detectable (Calculated) 16-30%
  1. * Malawi DHS data used is the national estimate, as data were not disaggregated for Mchinji District