ANOVA Analysis of Variance

October 20, 2013

An example ANOVA situation

Subjects: 25 patients with blisters Treatments: Treatment A, Treatment B, Placebo Measurement: # of days until blisters heal Data [and means]: A: 5,6,6,7,7,8,9,10 B: 7,7,8,9,9,10,10,11 P: 7,9,9,10,10,10,11,12,13

[7.25] [8.875] [10.11]

Are these differences significant?

Firstsource 2010 | confidential | October 20, 2013 | 2

Informal Investigation

Graphical investigation: side-by-side box plots Whether the differences between the groups are significant depends on the difference in the means the standard deviations of each group the sample sizes ANOVA determines P-value from the F statistic
Firstsource 2010 | confidential | October 20, 2013 | 3

Side by Side Boxplots

13 12 11 10

days

9 8 7 6 5 A B P

treatment

Firstsource 2010 | confidential | October 20, 2013 | 4

At its simplest (there are extensions) ANOVA tests the following hypotheses:
H0: The means of all the groups are equal. Ha: Not all the means are equal

What does ANOVA do?

doesnt say how or which ones differ. Can follow up with multiple comparisons

Note: we usually refer to the sub-populations as groups when doing ANOVA.

Firstsource 2010 | confidential | October 20, 2013 | 5

Assumptions of ANOVA

each group is approximately normal

check this by looking at histograms and/or normal quartile plots, or use

assumptions

can handle some non normality, but not severe outliers In case of severe outliers , please resort to Moods Median test

standard deviations of each group are approximately equal

rule of thumb: ratio of largest to smallest sample st. dev. must be less than 2:1

Firstsource 2010 | confidential | October 20, 2013 | 6

Standard Deviation Check

Variable days

treatment A B P

N 8 8 9

Mean 7.250 8.875 10.111

Median 7.000 9.000 10.000

Std Dev 1.669 1.458 1.764

Compare largest and smallest standard deviations: largest: 1.764 smallest: 1.458 1.458 x 2 = 2.916 > 1.764 Ratio of largest to smallest Std dev is 1.21 < 2
Note: variance ratio of 4:1 is equivalent.
Firstsource 2010 | confidential | October 20, 2013 | 7

Notation for ANOVA

n = number of individuals all together I = number of groups x = mean for entire data set is Group i has ni = # of individuals in group i xij = value for individual j in group i xi = mean for group i si = standard deviation for group i

Firstsource 2010 | confidential | October 20, 2013 | 8

How ANOVA works (outline)

ANOVA measures two sources of variation in the data and compares their relative sizes variation BETWEEN groups for each data value look at the difference between its group mean and the overall mean variation WITHIN groups for each data value we look at the difference between that value and the mean of its group

x i x
ij

xi

Firstsource 2010 | confidential | October 20, 2013 | 9

The ANOVA F-statistic is a ratio of the Between Group Variaton divided by the Within Group Variation:

Between MSG F Within MSE

A large F is evidence against H0, since it indicates that there is more difference between groups than within groups.
Firstsource 2010 | confidential | October 20, 2013 | 10

Minitab ANOVA Output

Analysis of Variance for days Source DF SS MS treatment 2 34.74 17.37 Error 22 59.26 2.69 Total 24 94.00

F 6.45

P 0.006

Firstsource 2010 | confidential | October 20, 2013 | 11

How are these computations made?

We want to measure the amount of variation due to BETWEEN group variation and WITHIN group variation For each data value, we calculate its contribution to: 2 BETWEEN group variation: x x

WITHIN group variation:

Firstsource 2010 | confidential | October 20, 2013 | 12

( xij xi )

An even smaller example

Suppose we have three groups

Group 1: 5.3, 6.0, 6.7 Group 2: 5.5, 6.2, 6.4, 5.7 Group 3: 7.5, 7.2, 7.9

We get the following statistics:

SUMMARY Groups Column 1 Column 2 Column 3

Firstsource 2010 | confidential | October 20, 2013 | 13

Count

Sum Average Variance 3 18 6 0.49 4 23.8 5.95 0.176667 3 22.6 7.533333 0.123333

Computing ANOVA F statistic

WITHIN difference: data - group mean plain squared -0.70 0.490 0.00 0.000 0.70 0.490 -0.45 0.203 0.25 0.063 0.45 0.203 -0.25 0.063 -0.03 0.001 -0.33 0.109 0.37 0.137 1.757 0.25095714 BETWEEN difference group mean - overall mean plain squared -0.4 0.194 -0.4 0.194 -0.4 0.194 -0.5 0.240 -0.5 0.240 -0.5 0.240 -0.5 0.240 1.1 1.188 1.1 1.188 1.1 1.188 5.106 2.55275

data group 5.3 1 6.0 1 6.7 1 5.5 2 6.2 2 6.4 2 5.7 2 7.5 3 7.2 3 7.9 3 TOTAL TOTAL/df

group mean 6.00 6.00 6.00 5.95 5.95 5.95 5.95 7.53 7.53 7.53

overall mean: 6.44 xi

Firstsource 2010 | confidential | October 20, 2013 | 14

F = 2.5528/0.25025 = 10.21575

Minitab ANOVA Output

Analysis of Variance for days Source DF SS MS treatment 2 34.74 17.37 Error 22 59.26 2.69 Total 24 94.00

F 6.45

P 0.006

# of data values - # of groups 1 less than # of groups (equals df for each group added together)

1 less than # of individuals (just like other situations)

Firstsource 2010 | confidential | October 20, 2013 | 15

Minitab ANOVA Output

Analysis of Variance for days Source DF SS MS treatment 2 34.74 17.37 Error 22 59.26 2.69 Total 24 94.00

F 6.45

P 0.006

(x
obs

ij

xi )

( x
obs

ij

x)

( x
obs

x)

SS stands for sum of squares ANOVA splits this into 3 parts

Firstsource 2010 | confidential | October 20, 2013 | 16

Minitab ANOVA Output

Analysis of Variance for days Source DF SS MS treatment 2 34.74 17.37 Error 22 59.26 2.69 Total 24 94.00

F 6.45

P 0.006

MSG = SSG / DFG MSE = SSE / DFE

F = MSG / MSE

P-value comes from F(DFG,DFE)

(P-values for the F statistic are in Table E)

Firstsource 2010 | confidential | October 20, 2013 | 17

So How big is F?

Since F is

Mean Square Between / Mean Square Within = MSG / MSE

A large value of F indicates relatively more difference between groups than within groups (evidence against H0) To get the P-value, we compare to F(I-1,n-I)-distribution I-1 degrees of freedom in numerator (# groups -1) n - I degrees of freedom in denominator (rest of df)
Firstsource 2010 | confidential | October 20, 2013 | 18

Pooled estimate for st. dev

One of the ANOVA assumptions is that all groups have the same standard deviation. We can estimate this with a weighted average:
2 2 2 ( n 1) s ( n 1) s ... ( n 1) s 1 1 2 2 I I s2 p nI

(df1) s (df 2 )s ... ( df I )s s df1 df 2 ... df I

2 p 2 1 2 2

2 I

SSE 2 sp MSE DFE

so MSE is the pooled estimate of variance

Firstsource 2010 | confidential | October 20, 2013 | 19

In Summary

SST ( x ij x ) s ( DFT )
2 2

SSE ( x ij x i ) si (df i )
2 2 obs groups 2

obs

SSG ( x i x )
obs

n (x
i groups

x)

SS MSG SSE SSG SST; MS ; F DF MSE

Firstsource 2010 | confidential | October 20, 2013 | 20

R2 Statistic

R2 gives the percent of variance due to between group variation

SS[Between ] SSG R SS[Total ] SST

2

We will see R2 again when we study regression.

Firstsource 2010 | confidential | October 20, 2013 | 21

Wheres the Difference?

Once ANOVA indicates that the groups do not all appear to have the same means, what do we do?
Analysis of Variance for days Source DF SS MS treatmen 2 34.74 17.37 Error 22 59.26 2.69 Total 24 94.00 F 6.45 P 0.006

Level A B P

N 8 8 9

Mean 7.250 8.875 10.111 1.641

StDev 1.669 1.458 1.764

Pooled StDev =

Individual 95% CIs For Mean Based on Pooled StDev ----------+---------+---------+-----(-------*-------) (-------*-------) (------*-------) ----------+---------+---------+-----7.5 9.0 10.5

Clearest difference: P is worse than A (CIs dont overlap)

Firstsource 2010 | confidential | October 20, 2013 | 22

THANK YOU
Firstsource (NSE: FSL, BSE: 532809, Reuters: FISO.BO, Bloomberg: FSOL@IN) is a global provider of customised BPO (business process outsourcing) services to the Banking & Financial Services, Telecom & Media and Healthcare sectors. Its clients include FTSE 100, Fortune 500 and Nifty 50 companies. Firstsource has a rightshore delivery model with operations in India, US, UK and Philippines. (www.firstsource.com)