What statistical analysis should I use?

选取统计分析方法的一般性原则。 下面的表格根据自变量的性质,因变量的个数,相应给出一般性的分析方法可供选择。

Below are general guidelines for choosing a statistical analysis. Usually data could be analyzed in multiple ways, each of which could yield legitimate answers. The table below covers a number of common analyses and helps you choose among them based on the number of dependent variables , the nature of your independent variables .

下表显示选择统计分析的一般指导。这只是一般指导不是硬性规定。以因变量为主线结合自变量种类和因变量种类进行划分。 避免因为因变量自变量区分不清带来的麻烦。

Choosing the Correct Statistical Test

Number

of
Dependent*
Variables

Number
of
Independent**
Variables

Type
of
Dependent
Variable(s)

Type
of
Independent
Variable(s)

 Measure

Test(s)

1

 0
(1 population)

continuous normal

not applicable
(none)

 mean

one-sample t-test

 continuous non-normal

 median

one-sample median

 categorical

 proportions

 Chi Square goodness-of-fit, binomial test

 1
(2 independent populations)

normal

 2 categories

 mean

2 independent sample t-test

 non-normal

medians

 Mann Whitney,
Wilcoxon rank sum test

 categorical

 proportions

 Chi square test
Fisher’s Exact test

0
(1 population measured twice)
or
1
(2 matched populations)

normal

 not applicable/
categorical

means

paired t-test

 non-normal

 medians

Wilcoxon signed ranks test

 categorical

 proportions

McNemar, Chi-square test

1
(3 or more populations)

normal

categorical

means

one-way ANOVA

non-normal

medians

Kruskal Wallis

categorical

proportions

Chi square test

2 or more
(e.g., 2-way ANOVA)

normal

categorical

means

Factorial ANOVA

non-normal

medians

Friedman test

categorical

proportions

log-linear, logistic regression

0
(1 population measured
3 or more times)

normal

not applicable

means

Repeated measures ANOVA

1

normal

continuous

correlation
simple linear regression

non-normal

 non-parametric correlation

categorical

categorical or continuous

logistic regression

continuous

discriminant analysis

 2 or more

 normal

continuous

multiple linear regression

 non-normal

 

categorical

logistic regression

normal

mixed categorical and continuous

Analysis of Covariance
General Linear Models (regression)

 non-normal

 

categorical

logistic regression

2

2 or more

normal

categorical

MANOVA

2 or more

2 or more

normal

continuous

multivariate multiple linear regression

2 sets of
2 or more

0

normal

not applicable

canonical correlation

2 or more

0

normal

not applicable

factor analysis

因变量数

自变量类别

因变量类别

方法

一个

没有自变量

(一个总体)

尺度和名义

单样本T检验

次序或尺度

单样本中位数检验

分类(两个类别)

二项检验

分类

卡方优度拟合

一个自变量两个水平 (独立分组)

尺度和名义

两独立样本T检验

次序或尺度

Wilcoxon-Mann Whitney 检验

分类

卡方检验

Fisher精确检验

一个自变量两个以上水平

(独立分组)

尺度和名义

单因素方差分析

次序或尺度

Kruskal Wallis

分类

卡方检验

一个自变量两个水平

(独立/匹配分组)

尺度和名义

成对T检验

次序或尺度

Wilcoxon符号秩检验

分类

McNemar

一个自变量两个以上水平 (独立/匹配分组)

尺度和名义

单因素重复测量方差分析

次序或尺度

Friedman 检验

分类

重复测量逻辑回归

两个以上自变量

(独立分组)

尺度和名义

因子方差分析

次序或尺度

 

分类

因子逻辑回归

一个尺度自变量

尺度和名义

相关分析

简单线形回归

次序或尺度

非参数相关分析

分类

简单逻辑回归

一个或多个尺度自变量或 一个或多个分类自变量

尺度和名义

多重回归

方差分析

分类

多重逻辑回归

判别分析

两个以上

一个自变量两个以上水平

(独立分组)

尺度和名义

单因素多元方差分析

两个或两个以上自变量

尺度和名义

多元多重线性回归

两个以上 的两个集

没有自变量

尺度和名义

典型相关分析

两个以上

没有自变量

尺度和名义

因子分析

http://www.ats.ucla.edu/stat/sas/whatstat/default.htm

发表评论

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / 更改 )

Twitter picture

You are commenting using your Twitter account. Log Out / 更改 )

Facebook photo

You are commenting using your Facebook account. Log Out / 更改 )

Google+ photo

You are commenting using your Google+ account. Log Out / 更改 )

Connecting to %s

%d 博主赞过: