Relation To Sufficient Statistics
For some parametric families, a complete sufficient statistic does not exist. Also, a minimal sufficient statistic need not exist. (A case in which there is no minimal sufficient statistic was shown by Bahadur in 1957.) Under mild conditions, a minimal sufficient statistic does always exist. In particular, these conditions always hold if the random variables (associated with Pθ ) are all discrete or are all continuous.
Read more about this topic: Completeness (statistics)
Famous quotes containing the words relation to, relation, sufficient and/or statistics:
“... a worker was seldom so much annoyed by what he got as by what he got in relation to his fellow workers.”
—Mary Barnett Gilson (1877–?)
“We shall never resolve the enigma of the relation between the negative foundations of greatness and that greatness itself.”
—Jean Baudrillard (b. 1929)
“... most Southerners of my parents’ era were raised to feel that it wasn’t respectable to be rich. We felt that all patriotic Southerners had lost everything in defense of the South, and sufficient time hadn’t elapsed for respectable rebuilding of financial security in a war- impoverished region.”
—Sarah Patton Boyle, U.S. civil rights activist and author. The Desegregated Heart, part 1, ch. 1 (1962)
“July 4. Statistics show that we lose more fools on this day than in all the other days of the year put together. This proves, by the number left in stock, that one Fourth of July per year is now inadequate, the country has grown so.”
—Mark Twain [Samuel Langhorne Clemens] (1835–1910)