释义 |
Mann–Whitney, n. Statistics.|mænˈwɪtnɪ| [The names of Henry Berthold Mann (b. 1905), Austrian-born U.S. mathematician, and Donald Ransom Whitney (b. 1915), U.S. statistician.] Used attrib., esp. in Mann–Whitney (U) test, with reference to a method of testing whether the difference between independent observations from two populations has zero median, and hence whether the populations are in fact the same.
1951Ann. Math. Statistics XXII. 165 The large sample power of these tests and of the Mann-Whitney test are obtained by means of a theorem of Hoeffding. 1970Jrnl. Gen. Psychol. LXXXIII. 90 Mann-Whitney U comparisons..between all possible pairs of these groups shows [sic] all pairs significantly different save for Groups III. 1978Nature 8 June 470/1 The mean channel conductance in cells at 37°C was 38.8{pm}4.7 pS (6 cells, -70 mV) which is not significantly different from the value at room temperature (Mann–Whitney test, P>0.10). 1980Brit. Med. Jrnl. 29 Mar. 895/2 The results were analysed statistically with the Mann-Whitney U test for small samples or the paired t test. 1991Lancet 9 Mar. 592/2 Statistical testing was done with both the Student's t test and the Mann-Whitney U test for categorical variables. |