摘要:

A field experiment demonstrated the importance of procedural considerations in use of the method of ordered alternatives for measuring the latitudes of acceptance, rejection and noncommitment. In a2 × 2design, respondents completed ordered alternatives relating to the 1972 Presidential Election with either a one or four page form and with either mandatory or optional instructions. Both of these variables produced significant main effects on each of the three latitudes. The one-page mandatory form produced the largest latitudes of rejection and acceptance, and the four-page optional form produced the largest latitudes of noncommitment. The four-page optional form is recommended if one is trying to minimize the probability of false positives in selecting highly involved people.

ISSN:0037-7732    

DOI:10.1093/sf/52.4.538

出版商:The University of North Carolina Press    

年代:1974

数据来源: OUP

摘要:

One limitation in building empirically testable models in sociology is that many familiar statistical techniques such as least-squares regression analysis require interval-level measurements while sociologists often have only ordinal-level measurements. Fortunately there do exist statistical techniques that use ordinal measurements. In this article we consider several types of prediction procedures which use ordinal data, as input, including individual ordinal prediction procedures and pairwise ordinal prediction procedures. The latter were studied by Wilson (1971) who claimed that ordinal variables could neither be used to build empirically testable models nor to state substantive propositions rigorously. But his claims are weakened because (1) he states, but fails to prove, that a particular loss function is the only one that can be used in pairwise ordinal prediction procedures, (2) he ignores alternative types of ordinal prediction procedures, and (3) his main mathematical theorem is in error. We consider his arguments, salvage his theorem, and display a similar theorem for individual ordinal prediction procedures. We argue that, for the three reasons mentioned, Wilson's results do not show that it is unprofitable to use ordinal variables in prediction procedures. Finally we consider a generalized individual ordinal prediction procedure in which one ordinal variable is only useless for predicting a second ordinal variable if the two variables are statistically independent.

ISSN:0037-7732    

DOI:10.1093/sf/52.4.543

出版商:The University of North Carolina Press    

年代:1974

数据来源: OUP

摘要:

This study is concerned with the analysis of the size and complexity of the governmental bureaucracies of the50American states, and more generally with the “administrative sector” of all social systems. Four hypotheses are formulated and tested. All of the hypotheses are supported, and this is interpreted as supporting a systems perspective in the analysis of social structure.

ISSN:0037-7732    

DOI:10.1093/sf/52.4.549

出版商:The University of North Carolina Press    

年代:1974

数据来源: OUP

ISSN:0037-7732    

DOI:10.1093/sf/52.4.559

出版商:The University of North Carolina Press    

年代:1974

数据来源: OUP

ISSN:0037-7732    

DOI:10.1093/sf/52.4.562

出版商:The University of North Carolina Press    

年代:1974

数据来源: OUP

ISSN:0037-7732    

DOI:10.1093/sf/52.4.563

出版商:The University of North Carolina Press    

年代:1974

数据来源: OUP

ISSN:0037-7732    

DOI:10.1093/sf/52.4.564

出版商:The University of North Carolina Press    

年代:1974

数据来源: OUP

ISSN:0037-7732    

DOI:10.1093/sf/52.4.565

出版商:The University of North Carolina Press    

年代:1974

数据来源: OUP

ISSN:0037-7732    

DOI:10.1093/sf/52.4.566

出版商:The University of North Carolina Press    

年代:1974

数据来源: OUP

ISSN:0037-7732    

DOI:10.1093/sf/52.4.567-a

出版商:The University of North Carolina Press    

年代:1974

数据来源: OUP