似然比卡方
一心以为没有（不该有）“似然比卡方”这么个说法。我们有“似然比”，有“对数似然比”，但我们没有“似然比卡方”这么个说法。
再说一遍：
‘likelihood-ratio’, ‘logarithmic likelihood-ratio’, possibly −2LLR, but never likelihood-ratio chi-square.
我们只能说：零模型（常数模型）和备择模型两者−2LLR的概率分布有时是（可视为）卡方分布。如WIKI上说的：
In many cases, the probability distribution of the test statistic is approximately a chi-squared distribution with degrees of freedom equal to df2−df1 , if the nested model with fewer parameters is correct.
那就不要说“似然比卡方检验”，不要说likelihood-ratio chi-square test了罢。
今儿还真遇到„Likelihood-Ratio-Chi-Quadrat“了。真是无话可说。
再说一遍：
‘likelihood-ratio’, ‘logarithmic likelihood-ratio’, possibly −2LLR, but never likelihood-ratio chi-square.
我们只能说：零模型（常数模型）和备择模型两者−2LLR的概率分布有时是（可视为）卡方分布。如WIKI上说的：
In many cases, the probability distribution of the test statistic is approximately a chi-squared distribution with degrees of freedom equal to df2−df1 , if the nested model with fewer parameters is correct.
那就不要说“似然比卡方检验”，不要说likelihood-ratio chi-square test了罢。
今儿还真遇到„Likelihood-Ratio-Chi-Quadrat“了。真是无话可说。
还没人转发这篇日记
