开发者:上海品职教育科技有限公司 隐私政策详情

应用版本:4.2.11(IOS)|3.2.5(安卓)APP下载

wishwind · 2018年11月21日

问一道题:NO.PZ2017092702000147 [ CFA I ]

问题如下图:

如果样本量很大,但是non-normally distributed,是不是也可以当成是normal distributed,可以用参数检验,比如z或者t检验。 

   

选项:

A.

B.

C.

解释:



1 个答案
已采纳答案

菲菲_品职助教 · 2018年11月21日

同学你好,对于样本服从非正态分布的情况,如果样本量很大,总体方差已知用z,方差未知用t或者z都可以。

不是说可以当做正态分布,是对于样本服从非正态分布的情况,样本量够大的情况下,都可以进行检验。

但是样本太小,小于30的时候,我们就没办法通过参数检验了。

  • 1

    回答
  • 1

    关注
  • 571

    浏览
相关问题

NO.PZ2017092702000147 问题如下 analyst is examining the monthly returns for two fun over one year. Both fun’ returns are non-normally stribute To test whether the mereturn of one funis greater ththe mereturn of the other fun the analyst cuse: A.a parametric test only. B.a nonparametric test only. C.both parametric annonparametric tests. B is correct. There are only 12 (monthly) observations over the one yeof the sample anthus the samples are small. Aitionally, the fun’ returns are non-normally stribute Therefore, the samples not meet the stributionassumptions for a parametric test. The Mann–Whitney U test (a nonparametric test) couluseto test the fferences between population means这道题检验的是两个均值之间的关系。如果对应的两个总体都是正态分布的话,那么我们需要使用t检验,也就是参数检验(对于t检验而言,参数就是自由度)。但这道题为非正态总体“Both fun’ returns are non-normally stribute,所以t检验就不能用了。这个时候只能使用非参数检验。 非正态分布,样本足够大不是也可以用Z检验吗?

2024-04-30 19:59 1 · 回答

NO.PZ2017092702000147 问题如下 analyst is examining the monthly returns for two fun over one year. Both fun’ returns are non-normally stribute To test whether the mereturn of one funis greater ththe mereturn of the other fun the analyst cuse: A.a parametric test only. B.a nonparametric test only. C.both parametric annonparametric tests. B is correct. There are only 12 (monthly) observations over the one yeof the sample anthus the samples are small. Aitionally, the fun’ returns are non-normally stribute Therefore, the samples not meet the stributionassumptions for a parametric test. The Mann–Whitney U test (a nonparametric test) couluseto test the fferences between population means这道题检验的是两个均值之间的关系。如果对应的两个总体都是正态分布的话,那么我们需要使用t检验,也就是参数检验(对于t检验而言,参数就是自由度)。但这道题为非正态总体“Both fun’ returns are non-normally stribute,所以t检验就不能用了。这个时候只能使用非参数检验。 如题,谢谢

2022-09-28 12:08 1 · 回答

NO.PZ2017092702000147 问题如下 analyst is examining the monthly returns for two fun over one year. Both fun’ returns are non-normally stribute To test whether the mereturn of one funis greater ththe mereturn of the other fun the analyst cuse: A.a parametric test only. B.a nonparametric test only. C.both parametric annonparametric tests. B is correct. There are only 12 (monthly) observations over the one yeof the sample anthus the samples are small. Aitionally, the fun’ returns are non-normally stribute Therefore, the samples not meet the stributionassumptions for a parametric test. The Mann–Whitney U test (a nonparametric test) couluseto test the fferences between population means这道题检验的是两个均值之间的关系。如果对应的两个总体都是正态分布的话,那么我们需要使用t检验,也就是参数检验(对于t检验而言,参数就是自由度)。但这道题为非正态总体“Both fun’ returns are non-normally stribute,所以t检验就不能用了。这个时候只能使用非参数检验。 是说,图里这三个检验,都需要前提是两个样本符合正态分布?

2022-09-28 11:53 1 · 回答

NO.PZ2017092702000147 a nonparametric test only. both parametric annonparametric tests. B is correct. There are only 12 (monthly) observations over the one yeof the sample anthus the samples are small. Aitionally, the fun’ returns are non-normally stribute Therefore, the samples not meet the stributionassumptions for a parametric test. The Mann–Whitney U test (a nonparametric test) couluseto test the fferences between population means我记得视频中讲test参数的都可以用参数检验,如果是test排序、符号等问题的才需要非参数检验。这道题是不是虽然提到了mean,但是本质是要看mean的大小(也就是类似排序或者符号)所以要用非参数检验?

2021-05-05 21:43 1 · 回答

是不是所有学过的参数检验的前提就是一定要符合正态分布?不符合的就是非参数检验,这样理解对吗?

2020-04-10 15:05 1 · 回答