Question 0 - Number of strata from 100 to 10, use this information to determine an overall sample and how many households would need to be visited.

A = 10 ; B = 265 ; C = 4 ;D = 5 ; E = 1,17647058823529 et m = 10

completed interviews needed: 10600

Total number of households to visit to get the necessary completed interviews : 62353

Target number of households to visit in each stratum : 6236

Number of clusters needed per stratum : 106

Total households to visit per cluster: 59

Total number of clusters in the survey: 1060

Question 1: What additional info would you need?

On a donné un seuil programmatique (Programmatic threshold) de 90%

Delta: distance entre la couverture actuelle et le seuil programmatique (Ici delta=10%, la direction=Below)

Le comité de pilotage veut détecter les provinces ayant une couverture ne penta3 probablement en dessous de 90%

Question 2: What would be the overall sample size?

Alpha : 5%

Beta : 10%

Delta : 5%

Seuil programmatique : 90%

A=10 B=382 C=4 D=5 E= 1,17647058823529

A x B x C = N_cs = 15 280 Total completed interviews needed

N_cs x D x E = 89 883 Total number of households to visit
(total household sample size)

B x C x D x E = 8 989 Number of households to visit in each stratum
(household sample size per stratum)

B x C / m = 153 Number of clusters per stratum

D x E x m = 59 Number of households per cluster

Num. clusters per stratum x A = 1 530 =Total number of clusters

Question 3: What decision would you make regarding the survey scope and objectives ? Rationale for decision?

Nous remarquons que la taille de l’échantillon a considérablement diminué par rapport à celle concernant les 100 districts. Ceci aura aussi un impact sur le budget en termes de diminution et de temps de travail. La relative petite taille de cet échantillon permettra d’améliore la qualité du travail de façon générale (équipes restreintes et supervisions bien ciblées).

On peut également procéder à une estimation au niveau national