文档介绍:作业 8:多因素方差分析
1, data0806-height 是从三个样方中测量的八种草的高度,问高度在三个取样地点,以及 八种草之间有无差异?具体怎么差异的?
打 开 spss 软 件 , 打 开 data0806-height 数
把 date 送入 Horizo ntal Axis, 把 dep th 送入 Separa te Lines,点击 Add,点击 Continue 回至 Univariate 对话框,点击 Options:
2
1
3
1
4
2
6
2
6
2
7
3
@
3
9
3
10
4
11
4
12:
4
13
5
14
5
16
5
16
e
17
6
heiqht
Horizontal Axis:
species
fnivariat e
§即日「日馆Lines: 铀 —
Separate Plots:
〔Continue J | Cancel Help
OK ] | Paste 11 Reset))Cancel 11 Help |
把 OVERALL,species, plot 送入 Display Means for 框,选择 Compare main effects,
Bonferroni, 点击 Continue 回至U Univariate 对话框,
输出结
果:
Tests of Between-Sulijects Effects
DependentWariafcde: weed height (cm)
Source
Type III Sum of Squares
df
Mean Square
F
Sig.
Corrected Model
"
9
.009
►
Intercept
1
.000
species
7
.034
plot
2
.005
Error
14
Total
24
Corrected Total
23
a. R Squared = .72S (Adjusted R Squared = .553)
可以看到:SSspecies=, dfspecies=7, MSspecies=; SSplot=, dfplot=7, MSplot=; SSerror=, dferror=14, MSerror=;
Fspecies=3. 089,p=0. 034<0. 05;Fplot=12. 130,p=0. 005<0. 01;
所以故认为在 5%的置信水平上,不同样地,不同物种之间的草高度是存在差异的。
Estimated Marginal Means
1. Grand Mean
ndentVariable: wEEd height (cm)
Mean
Std. Error
95% Confidence Interval
Lower Bound
Upper Bound
.253
2・ weed species
Estimates
Dependent 仙isble: weed height (cm)
weed species
Mean
Std. Error
95% Confidence Interval
Lower Eounci
Upper Eounci
1
.715
2
.715
3
.715
4
.715
5
.715
6
.715
7
.715
S
11.