ISM Research Memorandum
No.
1026
Title:
On the Stability of Public Opinion Data of Chinese Value Survey with respect to Sampling Methods
---A Note for the development of Cultural Manifold Analysis (CULMAN)
Author(s):
Horoiwa, Akira(National Institute of Science and Technology Policy,@The Ministry of Education, Science, Culture & Sports);
Yoshino, Ryozo(The institute of Statistical Mathematics);
Zheng Yuejun(Research Institute for Humanity and Nature)
Key words:
Chinese Value Survey; cultural linkage analysis; cultural manifold analysis;@CULMAN; data science; East Asia Value Survey; national character; cross-national comparison; nationwide statistical sampling; quota sampling.
Abstract:
A main objective of this paper is to show an aspect of our research methodology for cross-national survey, Cultural Manifold Analysis, in the investigation on the stability of response data of China 2002 Survey carried out by the cross-national survey committee of Institute of Statistical Mathematics. A main focus is on the reliability of response data of Beijing and Hong Kong. We supposed those data to be collected by three-stage random samplings: sampling of survey points proportionally to the ratios of population at the first stage, sampling of households at each of the selected points at the second stage, and sampling of a respondent at each of the selected households by a sort of birthday rule or the Kish method at the third stage. The outcomes, however, suggested that each of the final samples might have been made to be proportional to the ratios of population as if the selected sampling points were the total population, i.e., the selection probability of the numbers of households at each selected point might have been double.
We investigate the impact of probability sampling by comparing the originally collected data and the modified data which we made by re-sampling of the same number of respondents at each of selected points (which we may assume closer to the correct probability sample). The result confirmed the stability of those data, i.e., there was no significant difference between both data in both univariate tabulation and multivariate analysis (Hayashifs quantification method III). Finally, some comments were provided for the future development of practical sampling theory in public opinion poll.