Annova RM Pulc

Download as pdf or txt
Download as pdf or txt
You are on page 1of 4

ANNOVA

Maria Roy Felix J


Mobile:+919884650147, email:[email protected]
PULC- Loyola College, Chennai - 600034

ge
ANNOVA test:

le
AN OV A, which stands for Analysis of Variance, is a statistical test used to

ol
analyze the difference between the means of more than two groups.
A one-way ANOVA uses one independent variable, while a two-way ANOVA

C
uses two independent variables.
Use a one-way ANOVA when you have collected data about one categorical
independent variable and one quantitative dependent variable. The independent
variable should have at least three levels (i.e. at least three different groups or
a
categories).
l
ANOVA tells you if the dependent variable changes according to the level of
yo

the independent variable.


For example:
Lo

• Your independent variable is social media use, and you assign groups to
low, medium, and high levels of social media use to find out if there is a
difference in hours of sleep per night.
• Your independent variable is brand of soda, and you collect data on Coke,
LC

Pepsi, Sprite, and Fanta to find out if there is a difference in the price per
100ml.
Note:
PU

The null hypothesis (H0 ) of ANOVA is that there is no difference among


group means. The alternative hypothesis (H1 ) is that at least one group differs
significantly from the overall mean of the dependent variable.

1
ge
• T = Sum of all sample items.

le
• Ti = Sum of all samples items for source i.

ol
• N = Total number of items.
• k = Total number of items of each source i.
• df1 = Degree of Freedom between groups.

• df2 = Degree of Freedom within errors. C


l a
Example:
yo

Three different techniques namely medication, exercises and special diet are
randomly assigned to (individuals diagnosed with high blood pressure) lower the
blood pressure. After four weeks the reduction in each person’s blood pressure
Lo

is recorded. Test at 5 % level, whether there is significant difference in mean


reduction of blood pressure among the three techniques.
Medication 10 12 9 15 13
LC

Exercise 6 8 3 0 2
Diet 5 9 12 8 4
Solution:
Let A be the entries of Medication, B be the entries of Exercise and C be the
PU

entries of Diet.
ΣA = 10 + 12 + 9 + 15 + 13 = 59
ΣB = 6 + 8 + 3 + 0 + 2 = 19
ΣC = 5 + 9 + 12 + 8 + 4 = 38
T = sum of all the sample items = 59 + 19 + 38 = 116
N = Total number of items in all the samples = 5 + 5 + 5 = 15
T2 1162
Correction Factor = = = 897.06
N 15
Sum of squares of observation:
ΣX 2 = 102 + 122 + 92 + ... + 82 + 42 = 1162

T2
Sum of Squares of deviation Q = ΣX 2 − = 1162 − 897.06 = 264.94
N

2
2
(ΣA)
Sum of squares of deviation for variance between the samples QT = +
N1
2 2
(ΣB) (ΣC) T2
+ −
N2 N3 N
592 192 382
= + + − 264.94 = 1057.2 − 897.06 = 160.14
5 5 5

ge
le
ol
C
As F = 9.17 > f0.05 (2, 12) = 3.8853, the null hypothesis is rejected. Hence, we
a
conclude that there exists significant difference in the reduction of the average
l
blood pressure in atleast one pair of techniques.
yo

Partial and Multiple Correlation:


Lo

Partial Correlation:

If r12.3 denote the correlation of X1 and X2 by eliminating the effect of X3 .


LC

Let r12 be the simple correlation between X1 and X2 .


Let r13 be the simple correlation between X1 and X3 .
Let r23 be the simple correlation between X2 and X3 .
PU

The formulae for them are


r12 − r13 r23
r12.3 p 2 )(1 − r 2 )
(1 − r13 23

r13 − r12 r32


r13.2 p 2 )(1 − r 2 )
(1 − r12 32

r23 − r21 r13


r32.1 p 2 )(1 − r 2 )
(1 − r21 13

3
Multiple Correlation:

s
2 2
r12 + r13 − 2r12 r13 r23
R1.23 = 2
1 − r23
s
2 2
r21 + r23 − 2r21 r23 r13
R2.13 = 2
1 − r13

ge
s
2 2
r31 + r32 − 2r31 r32 r12
R3.12 = 2
1 − r12

le
ol
C
l a
yo
Lo
LC
PU

You might also like