Sampling Procedure
The information below is taken from "The Business Environment and Enterprise Performance Survey (BEEPS) 2005: A brief report on observations, experiences and methodology from the survey" prepared by Synovate, a research company that implemented BEEPS III instrument.
The general targeted distributional criteria of the sample for BEEPS III countries were to be as follows:
1) Coverage of countries: The BEEPS III instrument was to be administered to approximately 9,500 enterprises in 28 transition economies: 16 from CEEE (Albania, Bosnia and Herzegovina, Bulgaria, Croatia, Czech Republic, Estonia, FR Yugoslavia, FYROM, Hungary, Latvia, Lithuania, Poland, Romania, Slovak Republic, Slovenia and Turkey) and 12 from the CIS (Armenia, Azerbaijan, Belarus, Georgia, Kazakhstan, Kyrgyzstan, Moldova, Russia, Tajikistan, Turkmenistan, Ukraine and Uzbekistan).
2) Sector: In each country, the sectoral composition of the sample in terms of manufacturing (including agro-processing) (1) versus services (including commerce) (2)was to be determined by their relative contribution to GDP. Firms that operate in sectors subject to government price regulation and prudential supervision, such as banking, electric power, rail transport, and water and waste water, were to be excluded from the design of the sample.
3) Size: At least 10% of the sample was to be in the small (3) and 10% in the large size categories. Firms with only one employee or more than 10,000 employees were to be excluded.
4) Ownership: At least 10% of the firms were to have foreign control (4) and 10% state control (4).
5) Exporters: At least 10% of the firms were to be exporters (5), meaning that some significant share of their output is exported.
6) Location: At least 10% of firms were to be in the category "small city/countryside" (6).
7) BEEPS 2002 sample coverage: The BEEPS III survey instrument was to be administered to a given proportion of respondents who participated in BEEPS 2002 and had agreed in principle, at that time, to participate in future rounds of the BEEPS.
Enterprises, which began operations in 2002, 2003 and 2004, were to be excluded from the survey.
(1). Mining and quarrying (Section C: 10-14), Construction (Section F: 45), Manufacturing (Section D: 15-37)
(2). Transportation, storage and communications (Section I: 60-64), Wholesale, retail, repairs (Section G: 50-52), Real estate, business services (Section K: 70-74), Hotels and restaurants (Section H: 55), Other community, social and personal activities (Section O: selected groups)
(3). Small=2-49 employees, Medium=50-249, Large=250 - 9,999
(4). More than 50% shareholding
(5). Exports 20% or more of total sales
(6). Population under 50,000 inhabitants
8) In addition to Main BEEPS sample an overlay of manufacturing firms ("Manufacturing overlay BEEPS") was added in seven countries: Kazakhstan, Armenia, Azerbaijan, Poland, Hungary, Romania and Moldova. This sample was to be distributed between at least 2 major industrial regions within each country.
The survey was to be conducted among manufacturing enterprises only, operating within three sectors: garments, food processing and metal and machinery. The aim was to keep the sectoral composition as similar as possible across countries. Specifically, the sectors were to be constant at the 3-digit ISIC code. However, if it was not possible to obtain enough observations to complete the sampling overlay while limiting it to the 3-digit ISIC code, then firms could be selected from the sectors defined at the 2-digit level.
The sample within each country was to be distributed evenly between manufacturing sectors.
9) The following sources of information were used to prepare the sample frame for Poland:
Central Statistical Office of Poland data; Yellow Pages.