Premium
On the Use of Incomplete Frames in Sample Surveys
Author(s) -
Singh R.
Publication year - 1983
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.19830250605
Subject(s) - frame (networking) , sampling frame , sample (material) , sampling (signal processing) , basis (linear algebra) , population , missing data , statistics , mathematics , computer science , econometrics , demography , computer vision , geometry , telecommunications , chemistry , filter (signal processing) , chromatography , sociology
The existence of a frame is the pre‐requisite for designing any sampling inquiry or census. The quality of frame not only provides a basis for chosing the appropriate sampling design but also affects the ultimate results obtained. However, the existence of an accurate frame is very rare and generally all the frames are subject to various shortcomings. The incompleteness of the frame is one of the most common defects of almost all frames, mainly due to the dynamic nature of the populations. Seal (1962), Hartley (1962), Hansen, Hurwitz and Jabine (1964) etc. have suggested various procedures to deal with the problem of incomplete frames. In the present investigation, procedure suggested by Hansen, Hurwitz and Jabine (1964) has been used for estimating the population total for the characteristic under study in the two situations namely (i) when the units missing from the frame are random and (ii) when the missing units differ from units available in the frame.