Efforts to improve international migration statistics: a historical perspective

During the past decade, the international statistical community has made several efforts to develop standards for the definition, collection and publication of statistics on international migration. This article surveys the history of official initiatives to standardize international migration statistics by reviewing the recommendations of the International Statistical Institute, International Labor Organization, and the UN, and reports a recently proposed agenda for moving toward comparability among national statistical systems. Heightening awareness of the benefits of exchange and creating motivation to implement international standards requires a 3-pronged effort from the international statistical community. 1st, it is essential to continue discussion about the significance of improvement, specifically standardization, of international migration statistics. The move from theory to practice in this area requires ongoing focus by migration statisticians so that conformity to international standards itself becomes a criterion by which national statistical practices are examined and assessed. 2nd, the countries should be provided with technical documentation to support and facilitate the implementation of the recommended statistical systems. Documentation should be developed with an understanding that conformity to international standards for migration and travel statistics must be achieved within existing national statistical programs. 3rd, the call for statistical research in this area requires more efforts by the community of migration statisticians, beginning with the mobilization of bilateral and multilateral resources to undertake the preceding list of activities.     

Self reported morbidity in London and Manchester: Intra-urban and inter-urban variations

Evidence of self reported morbidity from two household surveys, carried out in London and Manchester is discussed. These data permitted intra-urban and interurban comparisons of patterns of morbidity reporting. The morbidity reported in response to two different instruments is compared: for the items used in the British General Household Survey (GHS) Health Section, and for the Nottingham Health Profile. The results from the London survey are analysed in more detail to examine the nature of self reported morbidity in the inner and outer city. The influence of interviewer effects is analysed, showing that the GHS items were more liable to interviewer effect than the NHP. The type and number of illnesses reported in response in response to the GHS also appeared to vary between the inner and outer London samples: The NHP appeared to be less affected by interviewer effects and variation in interpretation.     

Poisson regression with misclassified counts: application to cervical cancer

"Errors in disease classification can give misleading inferences for covariate effects when the probability of error is itself related to the covariates. More accurate inferences are possible using supplemental data on both true and fallible disease counts at various covariate levels. We present a method for incorporating such supplemental data into disease rate regression and use it to show that, although observed intercountry differences in European cervical cancer mortality rates are exaggerated by errors in death certification, they are not completely explained by such errors." The data concern Belgium, England and Wales, France, and Italy.