中国人民大学 抽样设计 2010综合社会抽样调查方案

nullSampling Design for 2010 CGSSSampling Design for 2010 CGSSYongjin Jin School of Statistics Renmin University of China Email: jinyongj@public.bta.net.cn Website: http://stat.ruc.edu.cn/en/faculty OutlineOutlineBackground1Discussion2Sampling Design3The Final Result4OutlineOutlineBackground1Discussion2Sampling Design3The Final Sample4BackgroundBackground1To fully understand social development of urban and rural areas 1. Survey ObjectivesBackgroundBackground1To fully understand social development of urban and rural areas 2To make comparisions between urban and rural groups1. Survey ObjectivesBackgroundBackground1To fully understand social development of urban and rural areas 2To make comparisons between urban and rural groups3To reflect regional discrepancy of the development in China, 1. Survey ObjectivesBackgroundBackground 2. Target PopulationThree-Stage stratified probability sampling A respondents selected randomly from the ultimate unit (household)3. Sampling MethodAll the household in 31 provinces (excluding Hong Kong, Macao and Taiwan) OutlineOutlineBackground1Discussion2Sampling Design3The Final Sample4DiscussionDiscussionCategoryCategory 1 Certainty unite Self-representative 必选层Category 2 Selected unite 抽选层Discussion——stratificationDiscussion——stratificationSelf-representativeImportant unites 36 Municipalities, provincial capitals and sub-provincial cities.Discussion——stratificationDiscussion——stratificationSelf-representative36 Municipalities, provincial capitals and sub-provincial cities.ConsiderationEconomic level Educational level Degree of opennessDiscussion——stratificationDiscussion——stratificationSelf-representative36 Municipalities, provincial capitals and sub-provincial cities.indexGDP Number of teachers FDI Actual used foreign investmentConsiderationEconomic level Educational level Degree of opennessDiscussion——stratificationDiscussion——stratificationSelf-representative36 Municipalities, provincial capitals and sub-provincial cities.indexGDP Number of teachers FDI Actual used foreign investmentConsiderationEconomic level Educational level Degree of opennessTop Five： Beijing, Shanghai, Guangzhou, Shenzhen, Tianjingfactor analysisDiscussion——stratificationDiscussion——stratificationselected categoryOther regions excluding the self-representativesDiscussion——stratificationDiscussion——stratificationselected categoryOther regions excluding the self-representativesConsideration District level（ urban） and county level（ rural） Futher stratificationDiscussion——stratificationDiscussion——stratificationselected categoryOther regions excluding the self-representativesindexDensity of population Proportion of non-agricultural population GDP per capitaConsideration District level（and country level Discussion——stratificationDiscussion——stratificationselected categoryOther regions excluding the self-representativesindexDensity of population Proportion of non-agricultural population GDP per capitaConsideration District level and country levelDistrict level : 19 stratum Country level : 31 stratumcluster analysisSampling stage Administrative Divisions of ChinaSampling stage Administrative Divisions of ChinaDiscussion——stageDiscussion——stagesDiscussion——stagesSelf-representativeSubdistrict or streetNeighborhood committeehouseholdselected stratumDistrict- or county-level unitsNeighborhood committee Villagers’ committeehouseholdDiscussion——sample size and allocationDiscussion——sample size and allocationTotal sample size: 12 000 unitsDiscussion——sample size and allocationDiscussion——sample size and allocationTotal sample size: 12 000 unitsOperational definitionNeighborhood committee consisted of urban household Villagers’ committee consisted of rural householdSome consideringLarger discrepancy among urban individuals Urban-rural ratioDiscussion——sample size and allocationDiscussion——sample size and allocationTotal sample size: 12 000 unitsConsidering operabilityNeighborhood committee consisted of urban household Villagers’ committee consisted of rural household7 200 Urban household4 800 Rural householdConsidering actual situationLarger discrepancy among urban individuals Urban-rural ratioDiscussion——sample size and allocationDiscussion——sample size and allocationStage 140 PSUs streets1. Self-representativeDiscussion——sample size and allocationDiscussion——sample size and allocationStage 2Stage 1 40×2 SSUs Neighborhood committee40 PSUs streets1. Self-representativeDiscussion——sample size and allocationDiscussion——sample size and allocationStage 3Stage 2Stage 140×2×25 USUs Household（household member) 40×2 SSUs Neighborhood committee40 PSUs streets1. Self-representative40 x 2 x 25 = 2000 housholdsDiscussion——sample size and allocationDiscussion——sample size and allocationStage 1100 PSUs District, county2. Selected stratum Discussion——sample size and allocationDiscussion——sample size and allocationStage 2Stage 1 100×4 SSUs Neighborhood committee (Villagers’ committee)100 PSUs District, county2. Selected stratum Discussion——sample size and allocationDiscussion——sample size and allocationStage 3Stage 2Stage 1100×4×25 USUs Household（household member) 100×4 SSUs Neighborhood committee (Villagers’ committee)100 PSUs District, county2. Selected stratum 100 x 4 x 25 = 10000 HouseholdsOutlineOutlineBackground1Discussion2Sampling Design3The Final Sample4Sampling DesignSampling Design Beijing, Shanghai, Guangzhou, Shenzhen, Tianjin; The samples are all urban households; Primary sampling units (PSUs) are sub-districts in the five cities above; We use PPS to select 40 sub-districts as the PSUs in this stratum. Sampling DesignSampling Design Sampling frame of the second stage: list of neighborhood committees in the sub-districts selected in the first stage; In the third stage, the households are ranged by house number; We’ll sample 50 households in each neighborhood committee in case of the nonresponce; Deliver the questionnaire in batches based on the response rate.Sampling DesignSampling DesignSample Distribution of Self-representativeSampling DesignSampling DesignAccording to The China 2009 Statistical Yearbook , there are 792 districts and 2,003 counties left in the selected category. Based on the population density, the rate of non-agricultural population and per capita Gross Regional Product, stratify the unites in selected category into fifty strata ( 19 district strata and 31 county strata). Select 2 PSUs in each stratum, resulting a total of 100 PSUsSampling DesignSampling DesignDeducting the 2,000 urban households in the self-represent, the urban-rural ratio in 抽选层 should be 5,200:4,800, i.e. the ratio of neighborhood committees to villagers' committees is about 208:192. Challenge how to determine the distribution of samples between urban and rural areas in each PSUs Deducting the 2,000 urban households in self-representative, the urban-rural ratio in selected category should be 5,200:4,800We can calculate that the ratio of neighborhood committees to villagers' committees is about 208:192 According to the urban-rural ratio of 6:4, urban sampling size should be 7,200, and rural area should be 4,800.Sampling DesignSampling DesignOur thoughts: Divide the districts and counties into several intervals according to the level of urbanization(the rate of non-agricultural population ). For a PSU with a higher level of urbanization, we should allocate more neighborhood committees to that PSU . Sampling DesignSampling DesignAllocation Criteria of Second UnitsSampling Design Sampling Design Construct second sampling frameDetermine the number of neighborhood/villager’s committees sampled in PSUSelects neighborhood / villager’s committees with PPSSample 25 households in each selected SSU,Sampling of Second UnitsConsidering the nonresponce, enlarge the sample size same as self-representative.OutlineOutlineBackground1Discussion2Sampling Design3The Final Resulte4The Final ResultThe Final ResultThe Final Sample Distributionnull