Sampling Procedure
Formal firms
The basic sample design used was a two-stage stratified cluster design. For formal manufacturing sector firms a stratified sampling procedure was used with size, industry and
location strata. The desired sample size for the survey was set at 240 manufacturing firms. The population for the survey consisted of manufacturing firms with at least 5 employees each.
Three different size strata were defined for the survey, namely 'small' (5-9 employees), 'medium' (10-99 employees), and 'large' (100+ employees).
Industry strata: The survey covered all manufacturing industries and distinguished between the following 6 industry strata based on 2-digit ISIC Rev.2:
31 - Manufacture of Food, Beverages and Tobacco
32 - Textile, Wearing Apparel and Leather Industries
33 - Manufacture of Wood and Wood Products, Including Furniture
35 - Manufacture of Chemicals, Petroleum, Coal, Rubber and Plastic Products
38 - Manufacture of Fabricated Metal Products, Machinery and Equipment
34,36,37,39 - Other manufacturing
Location strata: The survey imposed the following location strata:
(i) Harare and surrounds (towns within 50 km from Harare.)
(ii) Bulawayo
(iii) Gweru, Kwekwe and Redcliff (in Midlands)
(iv) Mutare (in Manicaland)
The sample oversampled firms outside the two location strata Harare and surrounds and Bulawayo, such that at least 20 firms were included in each of the location strata of Manicaland (Gweru / Kwekwe / Redcliff) and Midlands (Mutare). The sample also was designed to have an equal distribution of 80 firms each across the three size strata (5-19, 20-99, 100+ employees). This results in an oversampling of large firms and undersampling of small firms.
See the documentation on sampling for the full information.
Informal firms
For informal sector manufacturing sector firms, multi-stage sampling process was used. We identify main areas for each of the industry categories (Wood products, metal products, clothing/textiles/footwear, other) in Harare and Bulawo. We then divide up the areas into sub-areas (enumerating areas) with roughly equal numbers of firms. Then we randomly select a couple of clusters. For those clusters, we count and list the firms. Then we randomly select firms from that list.