Enterprise Survey 2009

The sample for registered establishments in Côte d'Ivoire was selected using stratified random sampling. Three levels of stratification were used in the Côte d'Ivoire sample: firm sector, firm size, and geographic region.

Industry stratification was designed as follows: the universe was stratified into three manufacturing industries (food, textiles, and other), one services industry (retail) and one residual sector as defined in the sampling manual. The initial sample design had a target of 240 interviews in manufacturing and 120 interviews each in the services and residual categories, though this sample design was later adjusted to reflect the low prevalence of manufacturing establishments in Ivory Coast.

Size stratification was defined following the standardized definition used for the Enterprise Surveys: small (5 to 19 employees), medium (20 to 99 employees), and large (more than 99 employees). For stratification purposes, the number of employees was defined on the basis of reported permanent full-time workers.

Regional stratification was defined in terms of the geographic regions with the largest commercial presence in the country: Abidjan, San Pedro, and Yamoussoukro were the three metropolitan areas selected in Côte d'Ivoire. (Bouake was initially included, but was determined to be too unsafe to conduct survey work and Yamoussoukro was substituted before enumeration began).

Given the stratified design, sample frames containing a complete and updated list of establishments as well as information on all stratification variables (number of employees, industry, and region) are required to draw the sample for the Enterprise Surveys. It was determined that such lists were not available for Ivory Coast, and the sample frame for registered firms was created through block enumeration. The block enumeration exercise was conducted in September 2008 in the three regions selected for the stratified sample. First, detailed maps were obtained from aerial mappings projected to a usable scale for Abidjan, San Pedro, Bouake, and Yamoussoukro. The following multi-stage approach was then followed.

Using the maps each city was divided into "blocks" and using local knowledge the blocks were classified into strata defined by the predominant spatial use of each block. The classifications used for the blocks included industrial, commercial, commercial/residential (mixed), and residential. The accuracy of the classification was then tested by site visits to pilot blocks randomly selected from among all blocks for each of the classification types. Twenty pilot blocks in the selected cities and an additional 10 blocks in Bouake (the city that was dropped from the sample due to safety concerns) were enumerated in the pilot. After the classification system was determined to be accurate, another 304 blocks, stratified by classification type, were selected randomly from the list of blocks. Blocks classified as "residential" were undersampled relative to industrial and commercial blocks.

The selected blocks were then enumerated. In the enumeration process for each block, each separate unit-either a whole building or a floor or suite within a building-was identified and its use was classified. For units classified as business establishments, further details were collected on employee numbers, activity, name of business and manager, and contact phone number.

The quality of the frame was assessed at the onset of the project and was not immune from the typical problems found in establishment surveys: positive rates of non-eligibility, repetition, non-existent units, etc. Given the impact that non-eligible units included in the sample universe may have on the results, adjustments may be needed when computing the appropriate weights for individual observations. The percentage of confirmed non-eligible units as a proportion of the total number of sampled establishments contacted for the survey was 9.4% (102 out of 1,080 establishments for the ES and micro samples).