In: Statistics and Probability
A researcher is testing 4 different blood coagulation drugs. The drugs are labeled A,B,C and D. He is interested in how the drugs affect the blood coagulation rates of mice. The coagulation rate is the time in seconds that it takes for a cut to stop bleeding. He has 16 mice available for the experiment, so he will use 4 on each drug, randomized.
A | B | C | D |
62 | 63 | 68 | 56 |
60 | 67 | 66 | 62 |
63 | 71 | 71 | 60 |
59 | 64 | 61 | |
64 |
a. Perform CRD (completely randomized design) manually. You need to write the STEPS clearly.
Let yij be the jth observation of the ith drug ; i = a,b,c,d
Null Hypothesis
Alternative Hypothesis H!: Atleast two means are different.
Grand Total (G)
Raw Sum of Square (RSS)
Correction Factor (C.F.)
Total Sum of Square (TSS) = RSS - CF = 64907-64643.0625 = 263.9375
Between (drugs ) Sum of Squares
Within (drugs) sum of Squares = TSS - Between SS = 263.9375 -174.5708 =89.3667
Degrees of freedom
For TSS = N-1= 15
For Between Drugs SS = k-1= 4-1= 3
For ESS = 15-3 =12
ANOVA TABLE
Source of variation | df | SS | MSS | F ratio |
Between Drugs | 3 | 174.5708 | 174.5708/3 =58.1903 | 58.1903/7.4472 =7.814 |
Within Drug (Error) | 12 | 89.3667 | 89.3667/12 =7.4472 | |
Total | 15 | 263.9375 |
The Critical value of F for 3,12 df , at 5% significance level is 3.490
Since calculated F is gretare than tabulated F, Reject H0.
Hence, we reject H0 at 5% significance level and conclude that the drugs differ significantly.