Moving in a given year: a study in research design and data analysis

"In this paper the distribution of the times between moves, or, equivalently, the relationship between duration of residence and the probability of moving [is examined]. Complete information on residence histories contained in the Population Register of Norway for the period 1965-1971 has been used to generate two data sets: the 'ideal' data set and the duration of residence at a specific point in time." The relationship between the probability of moving in a given year and stochastic models of mobility histories is then discussed. "In the subsequent section the feasibility of using the probability of moving in a given year, as measured by cross-sectional survey techniques, in lieu of complete residence histories, as contained in population registers, is evaluated. It could be demonstrated that cross-sectional data is sufficient for many purposes." In conclusion, "some comments are made regarding methodological problems arising out of the use of sparse tabular data, which is typical in socio-demographic studies where highly disaggregated projections are required."