生物统计学答案 第九章 两因素与多因素方差分析.docVIP

第九章 两因素及多因素方差分析 9.1 双菊饮具有很好的治疗上呼吸道感染的功效，为便于饮用，制成泡袋剂。研究不同浸泡时间和不同的浸泡温度对浸泡效果的影响，设计了一个两因素交叉分组实验，实验结果(浸出率)见下表[52]： 浸泡温度 /℃ 浸泡时间/min 10 15 20 60 23.72 25.42 23.58 80 24.84 28.32 29.55 95 30.64 31.58 32.21 对以上结果做方差分析及Duncan检验。该设计已经能充分说明问题了吗？是否还有更能说明问题的设计方案？ 答：无重复二因素方差分析程序及结果如下： options linesize=76 nodate; data hermed; do temp=1 to 3; do time=1 to 3; input effect @@; output; end; end; cards; 23.72 25.42 23.58 24.84 28.32 29.55 30.64 31.58 32.21 ; run; proc anova; class temp time; model effect=temp time; means temp time/duncan alpha=0.05; run; The SAS System Analysis of Variance Procedure Class Level Information Class Levels Values TEMP 3 1 2 3 TIME 3 1 2 3 Number of observations in data set = 9 The SAS System Analysis of Variance Procedure Dependent Variable: EFFECT Sum of Mean Source DF Squares Square F Value Pr F Model 4 87.0707778 21.7676944 12.56 0.0155 Error 4 6.9321778 1.7330444 Corrected Total 8 94.0029556 R-Square C.V. Root MSE EFFECT Mean 0.926256 4.741881 1.31645 27.7622 Source DF Anova SS Mean Square F Value Pr F TEMP 2 78.7202889 39.3601444 22.71 0.0066 TIME 2 8.3504889 4.1752444 2.41 0.2058 The SAS System Analysis of Variance Procedure Duncans Multiple Range Test for variable: EFFECT NOTE: This test controls the type I comparisonwise error rate, not the experimentwise error rate Alpha= 0.05 df= 4 MSE= 1.733044 Number of Means 2 3 Critical Range 2.984 3.050 Means with the same letter are not significantly different. Duncan Grouping Mean N TEMP A 31.477 3 3 B 27.570 3 2 C 24.240 3 1 The SAS System Analysis of Variance Procedure Duncans Multiple Range Test for variable: EFFECT NOTE: This test controls the type I comparisonwise error rate, not the experimentwise error rate Alpha= 0.05 df= 4 MSE= 1.733044 Number of Means 2 3 Critical Range 2.984 3.050 Means with the same letter are not significantly different. Duncan Grouping Mean N TIME A 28.447 3 3 A A 28.440 3 2 A A 26.400 3 1 从方差分析结果可以得知，温度是极显著的影响因素，时间是不显著因素。在Duncan检验中，温度的三个水平之间差异是显著的。时间的三个水平间差异不显著。