In: Statistics and Probability
Control |
Condition 1 |
Condition 2 |
58 |
73 |
53 |
32 |
70 |
74 |
59 |
68 |
72 |
64 |
71 |
62 |
55 |
60 |
58 |
49 |
62 |
61 |
Is there sufficient evidence to indicate a difference among mean maze test scores for mice trained under the three different laboratory conditions. Use a=.05. Perform multiple comparisons if necessary. Please show all work. Please also show the computer software output if used.
Ho:
Ha:
level of significance = .05
value of the test statisitic
p-value
state your conclusion
Perform Tukey's procedure if necessary
excel data analysis tool for one factor anova,steps are: write
data>menu>data>data analysis>anova :one factor>enter
required labels>ok, and following o/p Is obtained,
Anova: Single Factor | ||||||
SUMMARY | ||||||
Groups | Count | Sum | Average | Variance | ||
Control | 6 | 317 | 52.83333 | 128.5667 | ||
Condition 1 | 6 | 404 | 67.33333 | 27.06667 | ||
Condition 2 | 6 | 380 | 63.33 | 66.27 | ||
ANOVA | ||||||
Source of Variation | SS | df | MS | F | P-value | F crit |
Between Groups | 673.00 | 2 | 336.5000 | 4.5493 | 0.029 | 3.68 |
Within Groups | 1109.50 | 15 | 73.967 | |||
Total | 1782.50 | 17 |
Ho: µ1=µ2=µ3
H1: not all means are equal
level of significance = .05
value of the test statisitic=4.549
p-value=0.029
conclusion : p-value<α , reject null hypothesis
there is sufficient evidence to indicate that there is a difference
among mean maze test scores for mice trained under the three
different laboratory conditions at α=0.05
-------------------------
Tukey's procedure
Level of significance | 0.05 |
no. of treatments,k | 3 |
DF error =N-k= | 15 |
MSE | 73.967 |
q-statistic value(α,k,N-k) | 3.6750 |
critical value = q*√(MSE/2*(1/ni+1/nj)) = 12.903
if absolute difference of means > critical value, means are
significnantly different ,otherwise not
population mean difference | critical value | result | |||||
µ1-µ2 | 14.500 | 12.9033 | means are different | ||||
µ1-µ3 | 10.500 | 12.9033 | means are not different | ||||
µ2-µ3 | 4.000 | 12.9033 | means are not different |