1970 HUNGARIAN CENSUS OF POPULATION Information on the data collection and processing (1977)

I. THE COMPREHENSIVE REWIEV OF THE DATA COLLECTION AND PROCESSING - 6. Sampling techniques applied in the census

The sampling method The selection was based on the substance of knowledge published in the leaflet entitled "Preliminary conspectus of the communities and towns.

1

1 From the point of view of the selection, the communities have been divided in two subsets (strata): I. Communities having less than 2 000 inhabitants II. Communities having more than 2 000 inhabitants, and towns. During the process of the selection, the census districts have been further stratified according to districts of downtown or outskirts' areas, then the districts of the outskirts were broken down according to the number of inhabitants. \ Separate census districts were formed by the institutional household having more than' 100 persons or 100 living accomodations respectively (nurseries, children's homes, students' hostels, workers homes, hospitals, hotels, rest-houses etc.). Of the members of the institutional households having more than 100 living accomodations a nominal roll has been made by the warden. In such cases, the selection has been accomplished by the census-taker, by means of selecting each fourth person figuring on the list. The initial number of the selection was 2 or 3, according to the even or odd serial number of the census district. The selection of the census districts to be included to the sample of 25 per cent representativity was performed according to counties, towns of county rank - in Budapest by districts -, in the manner that taking in turn the counties, districts and communities (at first in the downtown districts, later on in the outskirts), each fourth census district has been selected. 1, 2, 3 or 4 have been the random initial numbers in each county. On account of the variability of the number of inhabitants, not exactly 25 per cent of the inhabitants were included to the sample. A slight deviation was tolerated from the provided' index number, i.e. from 4. It was 0, 05 on the level of the counties and towns having county rank; 0,10 in the case of towns having district rank and in Budapest, while 0,15 in the districts. If the deviation was greater, the selecting was corrected by means of the change of the census districts within the sample. The main data of the sample are completed by using the results obtained in the full-scale survey. It means that when using the combinations of the main criteria for stratification purposes, index numbers (multipliers) are worked out in order to perform the projection of the data. b/ THE PROCESSING OF THE PRELIMINARY RESULTS BY MEANS OF REPRESENTATIVE TECHNIQUES On the purpose of the preliminary processing of the material of the census of 1970, a representative sample has been taken. It aimed at the quick estimation of the results concerning the larger scope of the population, the family, the household and the flats. 47