After the MPNs are selected for the NCD Mobile Phone Survey under Options 1 and 2, the next phase of the sample design involves stratifying the final sample.
The prevalence of most chronic disease risk factors tends to increase with age and vary by sex. Therefore, survey results should include estimates for specific age groups for each sex in addition to the total survey population estimates to provide a more nuanced picture of the prevalence of chronic disease risk factors in your target population.
The recommended age groups are 18–29, 30–44, 45–59, and 60 years and older, though any age groups may be used. Estimates may be obtained only for the entire age span of the survey (e.g., 18 years and older) or for less age groups (e.g., 18-29, 30 years and older).
A country’s final sample design should include a detailed description of how a country plans to form a suitable sampling frame for the selection of MPNs, how the country will address frame incompleteness (such as new mobile phone operators opening for business during data collection), and how randomization will be used to select the sample of MPNs.
The planned allocation of the sample mobile phone users will be accomplished by explicitly stratifying the second-phase selection of users by age group (18-29, 30-44, 45-59, and 60 years and older) and sex (male and female) based on information received in the Demographic Module. Final respondent sample sizes in the strata will be proportional to the age group and sex distribution from the general population (as defined by the National Statistics Office or other reputable sources, such as the World Population Prospects: The 2012 Revision from United Nations Department of Economic and Social Affairs Population Division).
Randomly selected eligible mobile phone users should be enrolled into both the Demographic Module and the NCD Module until the sample size for each second-phase stratum is met.
Once a stratum sample size is met, selected members of that stratum should continue to be recruited to complete a Demographic Module until respondent sample size goals have been met in all strata or until the data collection period has expired. Counts of completed Demographic Modules and of those completing an NCD Module will be needed later for each second-phase stratum defined by age and sex to compute sampling weights.