Survey Methodology

Data Source
The AudienceScapes quantitative data for Ghana are based on a national survey of 2051 adults 15 and older, interviewed face-to-face from July 14 to August 10, 2009. The target population for the survey is 11 million adults aged 15 and older. A total of 6720 contacts were attempted to achieve the 2051 interviews. The response rate for the survey was 78 percent of valid contacts. The margin of error is ±2.2% with a 95% confidence interval. Percentages for subgroups have larger margins of error, depending on the number of respondents in the group.

Sampling
In order to achieve a nationally representative sample of Ghanaian adults (age 15 and over), InterMedia chose a probability proportional to size (PPS) sampling plan based on Ghana Statistical Service Year 2000 Population and Housing Census. In the first stage of the stratified sampling design, the country was divided into 10 regions; these regions were then subdivided into districts, and further stratified into sampling sectors and sampling points. The total sample of 2051 interviews was allocated down to sampling sectors proportionally to their population size:
        

Two rural sampling points selected in the Bawku district of the Upper East region were substituted due to an on-going protracted chieftaincy dispute and ethnic conflict, which made the conduct of the survey in these locations impossible due to insecurity. Substitute settlements were selected randomly.

At each sampling point, dwelling structures were selected by a random walk procedure, with interviewers contacting every fifth dwelling (for high density areas) or third dwelling (for low density areas). Each sampling point was assigned a starting landmark, from which the first dwelling to be contacted was determined by the summation method (the date or the sum of the two digits of the date).

In the event of an unsuccessful interview, the interviewer moved on to the next dwelling until a successful interview was achieved. In cases with multiple households within a dwelling structure, a household selection grid was used to randomly select one household. Within selected households, respondents were selected randomly by a Kish grid method from a list of adults in the household.

Fieldwork
A total of 56 interviewers and 25 supervisors took part in the survey. InterMedia staff based in Washington, DC worked closely with the Ghanaian research partner throughout the fieldwork, and were present in Ghana for training and supervision.
The median interview time was 60 minutes. Interviewers attempted 2 call-backs if the selected survey respondent was not available at the first call.

Questionnaire
A standard AudienceScapes national survey questionnaire was adapted to reflect the Ghanaian environment, in collaboration with InterMedia’s local subcontractor. Feedback from interviewer training and pilot testing also helped ensure that the questions were culturally appropriate and understandable. The questionnaire was then translated from English into Ga, Akan, and Hausa. The questionnaire covered the following topics:
                            
Data Processing and Quality Control
Responses were recorded by hand in the field, and checked by Field Supervisors. Field Supervisors accompanied interviewers on 20 percent of the interviews, and 25 percent of interviews were verified through call-backs by the quality control team.
Completed questionnaires were coded into an SPSS database and subjected to rigorous quality control procedures and consistency checks by InterMedia’s Research and Analysis Unit. The data were weighted to ensure they would represent the sampled population in terms of gender, urban/rural location, and region of the country.

Problems Encountered/Solutions Applied
The fieldwork contractor reported that the rainy season delayed fieldwork by about a week, as transportation became difficult. Reaching certain selected rural sampling points was extremely challenging, requiring interviewers to use bicycles or even go on foot to reach settlements. As noted above, insecurity in the Upper East region led to the substitution of two selected sampling points. Finally, the contractor noted that the fieldwork was conducted immediately following the widely publicized visit of President Barack Obama to Accra, which may have impacted the media behavior of some respondents, for example raising interest in world news or increasing the frequency of getting or discussing news about current events.

This research has been carried out in conformity with the standards of the ICC/ESOMAR International Code of Marketing and Social Research Practice.