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

I. THE COMPREHENSIVE REWIEV OF THE DATA COLLECTION AND PROCESSING - 11. The control of the reliability of the census

Table 2 contains the comparison of the results of the census of 1970 and the post-enumeration control under (a/) where the indentical declarations are on the diagonal of the table. Part (b/) compares the percentage distributions while the main index-numbers can be found under (c/). Table 3 contains the most important relative numbers broken down into five-year age groups. In Hungary from all the census criteria it is the age which shows the highest accuracy, which is evidently connected with the fact that the year of birth is always known from the identity card. Inquiry after the year of birth precludes the conspicuousness of round years (of age) experienced in a number of countries. In our country errors of the declaration of age may occur mainly, when another person gives the response instead of an absent person. Broken down into five-year age groups, the percentage distribution shows deviation from the data of post-enumeration control regarded as correct only in the second decimal for the whole of the country. Even this deviation fluctuates be-tween 0, 01 and 0, 03 only. The connection of breakdown (grouping) with accuracy is very meaningful: in case of larger groups the extent of error is less because one portion of the errors remains within the group. Thus in the case of age the total number of items erroneously to be found in, or missing from, the group, i. e. the gross error: in case of breakdown into years of age 4,16 p. c. according to five-year age groups 1,48 p. c. in large age groups (-14, 15-39, 40-59, 60-) 0, 33 p.c. Table 3 contains gross and net errors broken down into age groups. 100