Checking Assumptions
Given that the validity of conclusions drawn from a statistical analysis depend on the validity of any assumptions made, it is clearly important that these assumptions should be reviewed at some stage. In some instances, for example where data are lacking, this may have to be restricted to just making a judgement about whether an assumption is reasonable. This can be expanded slightly to try to judge what effect a departure from the assumptions might have. Where more extensive data are available, various types of procedure for statistical model validation are available, in particular for regression model validation.
Read more about this topic: Statistical Assumption
Famous quotes containing the word assumptions:
“Unlike Boswell, whose Journals record a long and unrewarded search for a self, Johnson possessed a formidable one. His life in London—he arrived twenty-five years earlier than Boswell—turned out to be a long defense of the values of Augustan humanism against the pressures of other possibilities. In contrast to Boswell, Johnson possesses an identity not because he has gone in search of one, but because of his allegiance to a set of assumptions that he regards as objectively true.”
—Jeffrey Hart (b. 1930)