拡張超幾何分布の正規近似

スポンサーリンク

概要

• 論文の詳細を見る

• The normal approximation of extended hypergeometric distribution is studied from the viewpoint of its mean, variance, skewness and kurtosis. The absolute and relative errors of the approximate moments are numerically evaluated and graphically displayed. The true values of those moments are computed by a newly devised method. It is observed that the relative errors of the mean and variance, and the absolute error of the kurtosis are decreased in the order of 1/n and that the absolute error of the skewness is of the order of 1/√<n>, where n denotes the size of the population. A formula empirically corrected for the approximate variance is proposed. In the appendix, several figures for the exact probabilities of extended hypergeometric distribution are given.

• 山梨大学の論文

著者

• 志村 健一

  山梨大学工学部

• 久世 紀之

  山梨大学工学部

関連論文

• 工程不良の確率モデルとしてのべータ二項モデルの実工程データに基づく妥当性の検討
• 制御のための回帰分析(回帰分析の有効活用)
• 拡張超幾何分布の正規近似

スポンサーリンク