DDI_MWI_2005_WMS-R1_v01_M Development Economics Data Group 2012-03-02 NADA Version 01: (March 2012) Welfare Monitoring Survey 2005 First Round WMS-R1 2005 MWI_2005_WMS-R1_v01_M National Statistical Office (NSO) NADA National Statistical Office Socio-Economic/Monitoring Survey [hh/sems] The WMS 2005 is a follow-up of the Core Welfare Indicators Questionnaire Survey (CWIQ) that was undertaken by the NSO in 2002. Unlike the CWIQ, which was basically a World Bank instrument, the WMS has been adapted to suit local requirements. The objective of the WMS is to provide rapid information on selected core indicators in the population including monitoring changes on a yearly basis. More specifically, the objectives of the WMS are to provide: - Indicators for monitoring the living conditions of people in the country - Indicators for monitoring the attainment of the Poverty Reduction Strategy (PRS), Malawian Growth and Development Strategy (MGDS) and other development programmes like the Millennium Development Goals (MDGs) - A regular database for socio-economic research The WMS is part of the Integrated Household Survey programme being implemented by the NSO. The programme includes the conduct of a comprehensive integrated household survey every five years and a lighter annual welfare monitoring survey between the five years. The sample of households covered in the WMS is therefore drawn from the larger sample of the Integrated Household Survey (IHS). Malawi National - Households - Individuals - Children under 5 years Sample survey data [ssd] The 2005 Malawi Welfare Monitoring Survey covered the following topics: - Household Identification and Interview Information - Characteristics of household members - Education - Health and Nutrition - Employment - Agricultural Activities and Crop production - Housing Condition and Amenities - Poverty Predictors - Child Information: Births and Anthropometrical Measures, Malaria Protection, Treatment and Vaccination (for children under 5 years) - HIV/AIDS knowledge National Statistical Office Sample Design The WMS sample is a subset of the sample that was selected for the second 2004/05 Integrated Household Survey (IHS2). The sample for IHS2 was drawn using a two-stage stratified sampling procedure from a sample frame using the 1998 Population Census enumeration areas (EAs), and the total sample size was 11,280 households (564 EAs x 20 households). Financial constraints led to a reduced sample size for WMS compared to IHS2. Since the sample for WMS was a subsample of the IHS2 sample, its design properties are basically equal: It was a two-stage stratified sample as follows: - First Stage: As in IHS2 there were 4 urban strata: Lilongwe, Blantyre, Mzuzu cities and Zomba Municipality, and 26 rural strata, the latter corresponding to the administrative districts in Malawi with the exception of Likoma Island. From each stratum 10 EAs were randomly selected with probability proportional to size among the EAs in IHS2, ranging from 12 EAs in small strata to 48 EAs in large strata. Second Stage: In each of the 300 EAs selected at the first stage, 2 out of the 20 households from IHS2 were discarded at random and used for replacement. Hence a total number of 300 x 18 = 5,400 households were identified for the WMS sample. Face-to-face [f2f] Training The training of field staff for the main Welfare Monitoring Survey was conducted over a two-week period in July 2005. The training took place at Chilema Ecumenical Lay Training Centre outside the Municipality of Zomba. A total of 54 field enumerators and supervisors were trained. The training course comprised of instructions in general interviewing techniques and field procedures, a detailed review of items on the questionnaires, instruction and practice in weighing and measuring under five children and group mock interviews of participants, and practical interviews in nearby villages. In-depth discussions of the translations were an important part of the training programme. The training also included 6 members of staff responsible for data processing with knowledge in the Eyes and Hands software for scanning the questionnaires. Data Collection The data collection commenced on 1st August 2005 and was completed on 20th September 2005. There were nine field teams, each team covering about 33 Enumeration areas (EAs). Two teams were located in the Northern region, three in the Central region and four were in the Southern region. The allocation of work areas to the teams was done in such a way as to minimize travelling time. The allocation of enumerators to teams took into account proficiency in the relevant local languages. The main rule was that enumeration plus travel time amounted to 2 days per Enumeration area, such that the fieldwork should be completed within 2 months. Extensive supervision was carried out to check some of the actual interviews, and to check the quality of the questionnaires before handing them to the data processing unit in Zomba. The Welfare Monitoring Survey 2005 strata subsamples are of equal size while number of households range from about 15,000 (Zomba Municipality) to 207,000 (Lilongwe rural). Household inclusion probabilities are correspondingly different. A set of household weights has been calculated to obtain unbiased estimates at national and regional level. The response rate is defined as a ratio that shows the number of households interviewed over the total sampled households. The 2005 WMS results show that out of the 5,400 households sampled, 5,234 were enumerated, giving an overall response rate of 97 percent. Note: Detailed information on response rate in the various regions as well as in urban and rural areas are given in Table 1.1, refer 2005 Malawi Welfare Monitoring Survey report. Use of the dataset must be acknowledged using a citation which would include: - the Identification of the Primary Investigator - the title of the survey (including country, acronym and year of implementation) - the survey reference number - the source and date of download The user of the data acknowledges that the original collector of the data, the authorized distributor of the data, and the relevant funding agency bear no responsibility for use of the data or for interpretations or inferences based upon such uses.