>>Is there perhaps a problem with selection bias? > 1) A house to house survey in the evening >>Movie goers might not be home in the evening.
> 4) A household survey based on a population census or register >>Everybody is in but some might take more follow up to get a response. >>See selection bias. ;-) indeed a house to house survey in the evening must have a bias, underestimating the cinema goers, but household surveys are done only during the day- or should they be conducted during the day in this particular case? What do you mean by selection bias in the household survey? George Washington wrote: >>Is "population" intended to >>mean "the population of all cinema-going people?" No I think it's clear the statistic shaught is ratio: [#cinemagoers in some period]/total population [people who can buy tickets, i.e. above some young age] >>I'm not beaurocratically sophisticated enough to know exactly what is >>meant by a register, Yes I am not a burocrat either, maybe I will be:) but that seems a good definition to me for a register. Another respondent mentioned that another difference is that census is annonymous (depends on the country) and register is a list of names addresses by default. If that is the case then how does one access people from the census?? (there is a problem of confidentiality here? eventhough cinema going is/seems quite inocuous) Thanks for the responses, great help. Georges . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
