SAMPLE DESIGN OF PSLM SURVEY
Universe: The universe of this survey consists of all urban and rural areas of the four provinces and Islamabad excluding military restricted areas.
Sampling Frame: Former FBS has developed its own urban area frame, which was updated in 2003. Each city/town has been divided into enumeration blocks consisting of 200-250 households identifiable through sketch map. Each enumeration block has been classified into three categories of income groups i.e. low, middle and high, keeping in view the living standard of the majority of the people. List of villages published by Population Census Organization obtained as a consequence of Population Census 1998 has been taken as rural frame.
NO. OF ENUMERATION BLOCKS AND VILLAGES AS PER SAMPLING FRAME
|Province||Number of Enumeration Blocks||Number of Villages|
A. Urban Domain: Islamabad, Lahore, Gujranwala, Faisalabad, Rawalpindi, Multan, Bahawalpur, Sargodha, Sialkot, Karachi, Hyderabad, Sukkur, Peshawar and Quetta, have been considered as large sized cities. Each of these cities constitutes a separate stratum and has further been sub-stratified according to low, middle and high-income groups. After excluding population of large sized cities, the remaining urban population in each defunct Division in all the provinces has been grouped together to form a stratum.
B. Rural Domain: Each district in Punjab, Sindh and NWFP provinces has been grouped together to constitute a stratum. Whereas defunct administrative Division has been treated as stratum in Balochistan province.
Sample Size and Its Allocation: Keeping in view the objectives of the National/Provincial Level survey the sample size has been fixed at approximately 17600 households comprising 1252 sample villages/ enumeration blocks, which is expected to produce reliable results at provincial level. For the District level survey the sample is fixed at approximately 79600 households comprising 5563 sample villages / enumeration blocks, which is expected to produce reliable results at district level.
|Level||Primary Sampling Units||Secondary Sampling Units|
Sample Design: A two-stage stratified sample design has been adopted in this survey.
Selection of Primary Sampling Units (PSUs): Villages and enumeration blocks in rural and urban areas, respectively, have been taken as Primary Sampling Units (PSUs). Sample PSUs have been selected from strata/sub-strata with Probability Proportional to Size (PPS) method of sampling technique.
Selection of Secondary Sampling Units (SSUs): Households within sample PSUs have been taken as Secondary Sampling Units (SSUs). A specified number of households i.e. 16 and 12 from each sample PSU of rural & urban area have been selected, respectively using systematic sampling technique with a random start.
At both individual and household level, the PSLM Survey collects information on a wide range of topics using an integrated questionnaire. The questionnaire comprises a number of different sections, each of which looks at a particular aspect of household behavior or welfare. Data collected under various Rounds include education, diarrhea, immunization, reproductive health, pregnancy history, maternity history, family planning, pre and post-natal care, access to basic services and income & expenditure.
DATA QUALITY AND RELIABILITY MEASURES
Each team comprising a supervisor and 2 male and 2 female enumerators, collect data from the field. Data quality in PSLM Survey has been ensured through a built in system of checking of field work by the supervisors in the field and also monitored through teams from the PBS headquarters. Regional/ Field offices ensure the data quality through preliminary editing at their office level. The entire data entry is carried out at the PBS headquarters, Islamabad and the data entry programme used had a number of in built consistency checks. Coefficient of Variation (CV’s) and Confidence Limit of important key indicators is also worked out to determine the reliability of the estimates.