cjosephlu

  •  
  • 2008年8月31日
  • 注册于 2008年8月31日
  • According to Freedman et al. (1991, pages 494 and A-27),
    R. A. Fisher was one of the rst to publish such tables, and it seems to have been his idea to lay them out that way. There is a limited amount of room on a page. Once the number of levels was limited, .05 and .01 stood out as nice round numbers, and they soon acquired a magical life of their own. With computers everywhere, this kind of table is almost obsolete. So are the .05 and .01 levels.
    This history is on the authority of G. A. Barnard, formerly professor of statistics, Imperial College of Science and Technology, London; now retired.

    Freedman, D., Pisani, R., Purves, R., and Adhikari, A. (1991), Statistics, New York: Norton,
    2nd edition.
  • 嗬嗬, 好像没人注意到我想建议的其实是以 NH 与 AH 来替代目前所使用的 ... :-)
  • 通常是以 "H0 与 H1", 或是 "Ho 与 Ha" (此处之 o 系 little o, 而非如前者之 zero), 在式子里表述那 Null 与 Alternative 假设 (Hypothesis), 而这 "0 与 1", 或是 "o 与 a", 在文稿中又都(需)以下标 (subscript) 来呈现; 因此想建议何不就采用 NH 与 AH, 简单明了? ... 野人献曝也.