标签

2016年3月30日星期三

Statistics: Error bars, T-test & ANOVA

1. Error bars are used to show the distribution of data, indicate the error, or uncertainty in a reported measurement, and give a general idea of how precise a measurement is.

image

Descriptive error bars give information describing the data and show how the data are spread.

Inferential error bars are used to conclude whether the groups are significantly different, or whether the differences might just be due to random fluctuation or chance.

image

It is highly suggested using larger n, to achieve narrower inferential error bars and more precise estimates of true population values.

image

Statistic hypothesis test

It is used to test the significance of group differences between two or more groups.

• T test (Student test)

looks at differences between two groups on some variable of interest

• ANOVA (Analysis of variance)

tests the significance of group differences between two or more groups

2. T test

image

image

Paired two sample means: from same samples

Two-sample assuming equal variances: from different samples with equal variances

Two-sample assuming unequal variances: from different samples with unequal variances

image

image

3. ANOVA

image

image

image

image

image

image

image

image

 

image

没有评论:

发表评论