Scribd
Upload
19 views8 pages

Lecture 12 - ReKm - Parametric Tets - ANOVA

Uploaded by

rayta.rahman
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
19 views8 pages

Lecture 12 - ReKm - Parametric Tets - ANOVA

Uploaded by

rayta.rahman
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

Statistics

Parametric Tests- ANOVA

Reatul Karim
Assistant Professor
Department of Pharmaceutical Sciences
ANOVA (Aanalysis of Variance)

ANOVA or `F’ test used to analyze the variance for judging the
significance of more than 2 means. ANOVA replace the multiple t- test
with a single ‘F’ test.
2
Variance between the groups s1
F= or F = 2
Variance within the groups s2

The calculated value of F is compared with the table value of F for the
given degree of freedom at a certain critical level. If the calculated value
of F is greater than the table value of F, it indicates that the difference
in sample means is significant. On the other hand, if the calculated
value of F is less than the table value, the difference is not significant.
ANOVA –Calculation (Alternative way)

Variance is computed as the sum of squared deviations from the overall


mean, divided by n-1 (sample size minus one, ie., degree of freedom).

Variance between the groups Mean sum of squares between the groups
F= =
Variance within the groups Mean sum of squares within the groups

Calculation of degree of freedom (df):


df for between groups = Number of groups minus one = (k-1)

df for within groups = Number of cases in each group minus one and added, (1st
group – 1) + (2nd group – 1) + (3rd group – 1)

Df Sum of squares Mean sum of squares F


(variance) (MS)
MSB
Between groups (k – 1) SSB SSB / (k-1) F=
MSW
Within groups (n – k) SSW SSW / (n-k)
ANOVA - Exercise

Problem: Three different treatment are given to 3 groups of patients with anemia. Increase in
Hb% level was noted after one month and is given below. Find whether the difference in
improvement in 3 groups is significant or not.

Group A Group B Group C Group A Group B Group C


x1 x2 x3 x1 2 x22 x 32
3 3 3 9 9 9
1 2 4 1 4 16
2 2 5 4 4 25
0 3 4 0 9 16
1 1 2 1 1 4
2 3 2 4 9 4
2 2 4 4 4 16
 x 3 = 24  x 1 = 23  x2 2 = 40  x3 2 = 90
2
 x 1 = 11  x2 = 16
 X T =  x1 +  x 2 +  x 3  X =  x1 +  x 2 +  x 3
2 2 2 2
N = 7+7+7= 21
= 11+16+24 = 51 = 23+40+90 = 153
ANOVA - Exercise

Steps:

1. Calculation of total sum of squares (SST) (for all values)


2 ( X T ) 2 (51) 2
SST =  X − = 153 − = 153 − 123.86 = 29.14
N 21 (N= total numbers in all groups)
2. Calculation of ‘between’ sum of square (SSB) (ie, between group)
 ( x1 ) 2 ( x2 ) 2 ( x3 ) 2  ( X T ) 2
SS =  + + − (T= Total)
B  n1 n2 n3  N
 (11) 2 (16) 2 (24) 2  (51) 2
= + + − = (17.28 + 36.57 + 62.29) − 123.86 = 12.28
 7 7 7  21
3. Calculation of ‘within’ sum of squares (SSW) (ie, within group)
SSw = SST – SSB = 29.14 - 12.28 = 16.86

df Sum of squares Mean sum of squares F


(variance)
Between groups 2 (3-1) 12.28 6.14
6.53
Within groups 18 [(7-1)+ (7-1)+ (7-1)] 16.86 0.94
ANOVA - Excercise

Df Sum of squares Mean sum of squares F

Between groups 2 12.28 6.14 6.53


Within groups 18 16.86 0.94

Interpretation:

F- value in the table at 2, 18 df (n1=2, n2=18) is 3.55 (at 5% significance level).

Our calculated value is 6.53, which is more than table value (3.55). So it is significant
One-way ANOVA
A new antibiotic drug with three different doses (100, 200 and 300 mg/kg body
weight of rat) was tested in type I diabetic rats at BIRDEM. 20 rats randomly
assigned into groups: A, B, C and D of 5 rats each. The rats of B, C and D
group received orally 3 different doses of drug. The rats of group A, serving as
a control group, received only an inert placebo.

A (Placebo) B (100mg/kg) C (200 mg/kg) D (300mg/kg)

27.0 22.8 21.9 23.5

26.2 23.1 23.4 19.6

28.8 27.7 20.1 23.7

33.5 27.6 27.8 20.8

28.8 24.0 19.3 23.9


( X T ) 2
2
SST =  X −
N
 ( x1 ) 2 ( x2 ) 2 ( x3 ) 2  ( X T ) 2
SS = + +  −
BG  n1 n2 n3  N
SSwG = SST – SSBG

MSBG= SSBG/(k-1)

MSWG= SSWG/(n-k)

F= MSBG/MSWG

You might also like