Integrated Household Survey 2001-2002 - Pakistan

Abstract
---------------------------

The objective of the Pakistan Integrated Household Survey (PIHS), a national sample survey, is to provide household and community level data which can be used to monitor, evaluate, and assess the impact of Social Action Program (SAP). Policymakers need to know; whether the poor have benefited from the program or whether increased government expenditure on the social sectors has been captured by the better off. In order to do this, a measure of living standards is needed so that benefits from public investment in social services can be compared across different income groups. For this purpose, PIHS includes a measure of household consumption (expenditure on goods and services) against which many of the outcome variables are tabulated. More generally, data collected in this survey also provides a valuable data base that can also be used to carry out research on a wide range of topics and issues.

Geographic coverage
---------------------------

National

Analysis unit
---------------------------

- Households
- Individuals

Universe
---------------------------

The universe of PIH Survey consists of all urban and rural areas of all four provinces, Azad Jammu and Kashmir, FATA and Northern Areas as defined by the Provincial Governments. Military restricted areas have been excluded from the scope of the survey.

Kind of data
---------------------------

Sample survey data [ssd]

Sampling procedure
---------------------------

Sampling Frame:
Separate sampling frames have been used in the survey for urban areas and rural areas as under.

Urban area:
FBS has developed its own urban area frame. This frame has been developed adopting Quick Count Record Survey techniques. According to this method, all urban areas know as cities/towns of the urban domain of the sampling frame have been divided into small compact areas known as enumeration blocks (E.Bs). Each enumeration block comprises about 200-250 households. Each Enumeration block has been divided into low, middle and high-income group, keeping in view the status of the majority of households. It will be used for drawing samples from the urban areas. There are 22800 enumeration blocks in all urban areas of the country.

Rural areas:
With regard to the rural areas, the lists of villages/mouzas/dehs according to population Census, 1998 have been used as sampling frame. In this frame, each village/mouza/deh is identifiable by its name, Had Bast number and Cadastral map etc. There are 50,588 mouzas/villages/dehs in the rural sub-universe of the survey

Sample size and its Allocation:
In view of the variability for the characteristics for which estimates are prepared, population distribution, field resources available and reliability constraints a sample size of 1,6400 households was considered appropriate to provide reliable estimates of key characteristics. The entire sample of households ((SSUs) has been drawn from 1150 Primary Sampling Units (SSUs) out of which 500 are urban and 650 are rural. This sample size has been considered sufficient to produce estimates of key variables at national and provincial level at 95% level of confidence with 5% to 7% margin of error.
Due to security situation prevailing in FATA, 8 sample villages were not enumerated. Similarly, 90 sample households were not covered due to non-response/closed/non-contact and non-cooperation from the respondents in this Survey.The total number of sampling units covered is tabulated on page 21 of the HIES report

Stratification Plan:
Stratification scheme is adopted keeping in view the geographical level of estimates to be built-up and to control the variation in the under study characteristics of the survey population.The detail of the scheme is as under.

Urban Area:
With respect to the urban areas each of Karachi, Lahore, Gujranwala, Faisalabad, Rawalpindi, Multan, Sialkot, Sargodha, Bahawalpur, Hyderabad, Sukkur, Peshawar, Quetta and Islamabad being large size cities have been treated as independent stratum. Each of these cities has further been substratified according to low, middle, high-income groups based on the information collected in respect of each enumeration block. After excluding the population of large sized cities the remaining urban population in each defunct administrative division in all provinces has been grouped and treated as an independent stratum. Each of Azad Jammu & Kashmir, FATA and Northern Areas has been considered as independent strata separately.

Rural Area:
In the rural areas, the population of each district in Punjab, Sindh and N.W.F.P Provinces has
been grouped together to constitute a stratum. For Balochistan province each of defunct administrative Division has been taken as a stratum. Azad Jammu & Kashmir FATA and Northern
Areas have been considered as independent strata in rural areas separately.

Sample Design:
A two-stage stratified sample design has been adopted for this survey.
Selection of primary sampling Units (PSUs).
Enumeration blocks in the urban domain and mouzas/dehs/villages in rural domain have been taken as primary sampling units (PSUs). Sample PSUs from each ultimate stratum/sub-stratum have been selected by probability proportional to size (PPS) method of sampling scheme. In this survey population of rural areas and households for urban areas have been adopted as measure of size for selecting Primary Sampling Units (PSUs) from the strata/ sub-strata formed in urban and rural subuniverses of the survey.

Selection of Secondary Sampling Units (SSUs):
Households within each sample Primary Sampling Units (PSU) have been considered as secondary sampling units (SSUs). 16 and 12 households have been selected from each sample village and enumeration block respectively by random systematic sampling scheme with a random start.

Mode of data collection
---------------------------

Face-to-face [f2f]

Research instrument
---------------------------

The HIES questionnaire, revised to reflect integration with PIHS and improved data collection methods were used for the 2001-02 survey i.e. Income and Expenditure (Round- IV of PIHS). The questionnaire was split into two modules in order to obtain better quality of information separately from male and female respondents by the male and female enumerators respectively. Specifically, minor changes were made in the part containing the consumption expenditure items. To obtain the better quality of data from the well-informed female respondents, the relevant parts of consumption expenditure of food and non-food items have been included in the female part of the questionnaire. Information which is considered to be answered better by the male household respondents is included in the male part of the questionnaire. The structure of the new PIHS / HIES questionnaire used in 1998-99 and 2001-02 is shown in table 1.3 of the Survey Report

Response rate
---------------------------

90 sample households were not covered due to non-response/closed/non-contact and non-cooperation from the respondents in this Survey

摘要
---------------------------
巴基斯坦综合家庭调查（PIHS）的宗旨在于提供家庭和社区层面的数据，以用于监测、评估和衡量社会行动计划（SAP）的影响。政策制定者需了解；贫困人口是否从该计划中获益，以及政府在社会领域的增加支出是否为富裕阶层所捕获。为了实现这一目标，需要一个衡量生活水平的指标，以便能够比较不同收入群体从公共投资于社会服务中获得的收益。为此，PIHS包括家庭消费（商品和服务支出）的衡量标准，许多结果变量据此进行统计。更普遍地，本调查收集的数据也为开展广泛主题和问题的研究提供了一个宝贵的数据库。
地理覆盖范围
---------------------------
全国
分析单元
---------------------------
- 家庭
- 个人
总体
---------------------------
PIHS调查的总体包括所有四个省份、阿扎德查谟和克什米尔、FATA和北方地区，这些地区由省政府定义。军事限制区域已被排除在调查范围之外。
数据类型
---------------------------
样本调查数据 [ssd]
抽样程序
---------------------------
抽样框架:
调查中使用了分别针对城市和农村地区的单独抽样框架。
城市地区:
FBS开发了其自身的城市地区框架。该框架采用快速计数记录调查技术进行开发。根据此方法，所有被称为城市/镇的城市领域抽样框架区域都已被划分为称为统计区块（E.Bs）的小型紧凑区域。每个统计区块包含大约200-250户家庭。每个统计区块已被划分为低收入、中等收入和高收入群体，考虑到大多数家庭的情况。它将被用于从城市地区抽取样本。全国所有城市地区共有22800个统计区块。
农村地区:
关于1998年人口普查的村庄/地区/村庄名单已被用作抽样框架。在此框架中，每个村庄/地区/村庄都可通过其名称、Had Bast编号和地籍图等唯一识别。调查的农村子总体中有50,588个地区/村庄/村庄。
样本量和分配:
鉴于估计特征的可变性、人口分布、可用现场资源和可靠性限制，认为1,6400户家庭的样本量是适当的，以提供可靠的关键特征估计。整个家庭样本（SSUs）是从1150个一级抽样单位（SSUs）中抽取的，其中500个是城市，650个是农村。这个样本量被认为足以在95%的置信水平下，以5%至7%的误差范围产生国家和省级关键变量的估计。
由于FATA的安全状况，8个样本村庄未被统计。同样，由于调查中受访者未回应/关闭/无法接触和不合作，90个样本家庭未被涵盖。采样单位的总数在HIES报告的第21页上列出。
分层计划:
分层方案是根据要构建的估计的地理级别以及控制调查人口中研究特征的变异而采用的。该方案的详细信息如下。
城市地区:
就城市地区而言，卡拉奇、拉合尔、古杰兰瓦拉、费萨尔巴德、拉瓦尔品第、木尔坦、西阿尔科特、萨戈达、巴哈瓦尔布尔、海得拉巴、苏库尔、佩什瓦、奎达和伊斯兰堡等大型城市被视为独立的层。每个城市都进一步根据每个统计区块收集的信息，根据低收入、中等收入和高收入群体进行次分层。在排除大型城市的人口后，所有省份中每个失效的行政区域剩余的 urban population 已被分组，并被视为独立的层。阿扎德查谟和克什米尔、FATA和北方地区分别被视为独立的层。
农村地区:
在农村地区，旁遮普省、信德省和N.W.F.P省每个地区的 population 已被分组在一起，以构成一个层。对于俾路支省，每个失效的行政区域都被视为一个层。阿扎德查谟和克什米尔、FATA和北方地区在农村地区被视为独立的层。
样本设计:
本调查采用了两阶段的分层样本设计。
一级抽样单位（PSU）的选择。
城市领域的统计区块和农村领域的村庄/地区/村庄被选为一级抽样单位（PSU）。通过抽样方案的规模比例概率（PPS）方法从每个最终层/次层中选择了样本PSU。在调查的城市和农村子总体中，农村地区的 population 和城市地区的家庭被采用作为从层/次层中选择一级抽样单位（PSU）的规模。
二级抽样单位（SSU）的选择。
每个样本一级抽样单位（PSU）内的家庭被视为二级抽样单位（SSU）。通过随机系统抽样方案，每个样本村庄和统计区块分别随机选择16家和12家。
数据收集方式
---------------------------
面对面 [f2f]
研究工具
---------------------------
用于2001-02调查（PIHS的第四轮收入和支出）的HIES问卷，经过修订以反映与PIHS的整合和改进的数据收集方法。问卷被分为两个模块，以便通过男性和女性调查员分别从男性和女性受访者那里获得更好的信息质量。具体而言，消费支出项目的部分进行了细微的修改。为了从信息丰富的女性受访者那里获得更好的数据质量，食品和非食品消费支出的相关部分已包含在女性问卷部分中。被认为更适合由男性家庭受访者回答的信息包含在男性问卷部分中。新PIHS/HIES问卷的结构，如图表1.3所示的调查报告。
响应率
---------------------------
由于调查中受访者未回应/关闭/无法接触和不合作，90个样本家庭未被涵盖。