In: Math
i.e. H0: there no difference in the effects of Control and two other treatment groups
H1: H0 is not true.
One-way ANOVA: C1 versus C2
Source DF SS MS F P
C2 2 376.47 188.23 19.63 0.000
Error 27 258.90 9.59
Total 29 635.37
S = 3.097 R-Sq = 59.25% R-Sq(adj) = 56.23%
Since p-value<0.05, hence there are significant difference between the effects of three groups (Control, Rapid Smoking, Patch 14 MG). Hence we want to perform post hoc test. Here we use Tukey's test.
Individual 95% CIs For Mean Based on
Pooled StDev
Level N Mean StDev -------+---------+---------+---------+--
Control 10 15.200 3.084 (----*-----)
Patch14MG 10 6.600 2.951 (-----*-----)
Rapidsmoking 10 9.900 3.247 (----*-----)
-------+---------+---------+---------+--
7.0 10.5 14.0 17.5
Pooled StDev = 3.097
Grouping Information Using Tukey Method
C2 N Mean Grouping
Control 10 15.200 A
Rapidsmoking 10 9.900 B
Patch14MG 10 6.600 B
Means that do not share a letter are significantly different.
Tukey 95% Simultaneous Confidence Intervals
All Pairwise Comparisons among Levels of C2
Individual confidence level = 98.04%
C2 = Control subtracted from:
C2 Lower Center Upper
----+---------+---------+---------+-----
Patch14MG -12.037 -8.600 -5.163 (------*------)
Rapidsmoking -8.737 -5.300 -1.863 (-----*------)
----+---------+---------+---------+-----
-10.0 -5.0 0.0 5.0
C2 = Patch14MG subtracted from:
C2 Lower Center Upper
----+---------+---------+---------+-----
Rapidsmoking -0.137 3.300 6.737 (------*-----)
----+---------+---------+---------+-----
-10.0 -5.0 0.0 5.0
From the above confidence intervals, we conclude that participants smoked less after receiving the rapid smoking treatment and PATCH 14 MG treatment as compared to those participants in a control condition (since the corresponding confidence intervals contain all negative values) whereas there is no significant difference between the effects of rapid smoking treatment and PATCH 14 MG treatment since the corresponding interval contains zero.