On Hacking's fiducial theory of inference

Fisher's theory of fiducial inference is known to lead to mathematical inconsistencies. Hacking (1965) puts forward a new basis for fiducial inference. In this paper we have presented Hacking's theory retaining his original terminology but replacing his notation by more usual mathematical notation. His condition of irrelevance is derived in an explicit mathematical form, making it more comprehensible to statisticians. Further an example is constructed to show that Hacking's theory also leads to mathematical inconsistencies.     

Strength of fertility motivation and contraceptive use in Nepal

The study's purpose was to test whether new survey questions on strength of fertility motivation, included in Nepal's 1986 Fertility and Family Planning Survey, enable improved prediction of current contraceptive use. Intent to use contraception in the future was also tested, over and above the effects of socioeconomic background. While controlling selected demographic and socioeconomic background characteristics of the respondents, the authors found the effect of the strength of fertility motivation on current contraceptive use to be substantial and highly significant statistically. Nevertheless, the background factors largely captured the effect of motivational strength on current use when motivational strength was deleted from the model, inasmuch as measures of global fit declined only slightly as a consequence of the deletion. These findings indicate that respondents' demographic and socioeconomic background characteristics affect motivational strength, so that motivational strength does not have a large independent effect on use. These results raise the question of whether strength of fertility motivation can be affected by educational efforts mounted by family planning programs to increase contraceptive use. The analysis shows that strength of motivation does have some independent effect on contraceptive use, and it is quite possible that this independent effect could be enhanced by educational programs operating independently of the socioeconomic characteristics of program recipients. Because the 1986 survey lacks relevant data, we have not been able to explore this possibility empirically.