BUSINESS RESEARCH

METHODS
Prof.Radhika Kiran Kumar
Indira Institute of Business Management
 2

Analysis of Variance(ANOVA)
 3

Example : Single vs. Multiple

population
 4

Using t-test
» t-test is used to:

• To infer mean of a single population

• T-test can be used to compare two
populations

» However, t-test is not useful to compare mean of

more than two populations
 5

t-test
• Construct pairwise comparison on all means.

• For 5 populations 10 possible pairs.

• Considering , probability of correctly failing to reject the null hypothesis for

all 10 tests is , assuming that the tests are independent

• Thus the true value of α for this set of comparison is 0.4, instead of .05

• It inflates the Type 1 error.

 6

ANOVA(Analysis of Variance)
Definition:
Analysis involving the investigation of the effects of one
treatment variable on an interval-scaled variable.

Purpose:
To test differences in means(for group variables) for
statistical significance.
 7

Hypothesis in ANOVA
»Ho : 1=2=3=…..=k
»Ha : At least one k is different

»Use when you have one or more

independent variables and ONE dependent
variable.
 8
Variants of ANOVA
» Based on the number of Independent Variables and Dependent
Variable considered for the study, there are different variants of
ANOVA

1. One-way ANOVA: Only one independent variable (factor) with greater

than 2 levels.

2. Two-way ANOVA: Two independent variables (i.e., factors).

3. Three-way ANOVA: Three independent variables (i.e., factors).

4. Multivariate Anova: It is used to test the significance of the effect of

more independent variables.
 9

One-way ANOVA
 10

One-way ANOVA
» The purpose of the procedure is to compare sample means of populations.
» In general, One-way ANOVA technique can be used to study the effect of levels of a
single factor.

» To determine if different levels of the factor affect measured observations differently, the
following hypotheses are tested.

all
some
That is, at least one equality is not satisfied
where is the population mean for a level .
 11

𝑨𝑵𝑶𝑽𝑨
F-test:Used to determine whether there is more variability in the scores of one
sample than in the scores of another sample.

F= Variance between groups = MS between

Variance within groups MS within

Within group: Variances of the observations in each group weighted for group
size
Between group: Variance of the set of group means from the overall mean of all
observations
 12

Assumptions
» When applying one-way analysis of variance, there are
three key assumptions that should be satisfied as
follows.
1. The observations are obtained independently and
randomly from the populations defined by the factor
levels.
2. The population at each factor level is (approximately)
normally distributed.
3. These normal populations have a common variance, .
 13

One-way ANOVA Example

» A call center manager wants to know if there is a
significant difference in average handle times
amongst three different call operators.
» Independent Variable: Call operator
» Dependent Variable: Average Handle time
» Hypothesis:Ho: 1=2=3
Ha : At least one is different
An Example ANOVA
» An experimenter is interested in the effect of
music on memory for words. The data are shown
on the next slide. Each score represents the
number of words recalled. Analyze the data using
the appropriate statistical test.
An Example ANOVA
Country Classical Blues

3 5 9

2 3 8

5 5 9

2 2 7

2 9
Step 1. State the hypotheses.
A. Is it a one-tailed or two-tailed test?
» ANOVAs are always two-tailed
B. Research hypotheses
» Alternative hypothesis:
⋄ The mean number of words recalled in at least one
group differs from the mean number of words
recalled in at least one of the other groups.
» Null hypothesis:
⋄ The mean number of words recalled when listening
to country, classical, or blues music does NOT differ.
C. Statistical hypotheses:
» HA: not all s are equal
» H0: country = classical = blues
Step 2. Set the significance
level   = .05. Determine
Fcrit.
To look up Fcrit, need to know:
1. alpha level
2. dfbetween
3. dfwithin
Degrees of Freedom

dfTotal

dfBetween dfWithin
Terminology
» k: # of levels of the IV (# of groups)
» n: # of scores in each treatment
» N: # of scores in entire study
Calculate df
» dftot = Ntot – 1

» dfwithin = Ntot – k (k=# of groups)

» dfbetween = k – 1 (k=# of groups)

» Check: dftot = dfbetween + dfwithin

Calculate df
» dftot = Ntot – 1
= 14 – 1 = 13

» dfwithin = Ntot – k
= 14 – 3 = 11

» dfbetween = k – 1 (k=# of groups)

=3–1=2

» dftot = dfbetween + dfwithin

= 2 + 11 = 13
Step 2. Set the significance
level   = .05. Determine
FcritTo. look up F , need to know:
crit

1. alpha level  .05

2. dfbetween = 2
3. dfwithin = 11

Look up Fcrit in the table.

Step 3: Select and compute the
appropriate statistic.
» Calculate the F-ratio.
Sum of Squares

SSTotal

SSBetween SSWithin
Steps in Calculating the F ratio
1a. Calculate SStot
» This is the deviation of all scores from the grand
mean

SStot   ( X  X Tot ) 2

1. Calculate the grand mean

2. Subtract the grand mean from each score
3. Square each value
4. Add them together
SStot
Country
X1 X1 - MTot (X1 – MTot)2

3 -2.07 4.28

2 -3.07 9.42

5 -.07 .005

2 -3.07 9.42

2 -3.07 9.42
SStot

Classical
X2 X2 - MTot (X2 – MTot)2

5 -.07 .005

3 -2.07 4.28

5 -.07 .005

2 -3.07 9.42
SStot

Blues
X3 X3 - MTot (X3 – MTot)2
9 3.93 15.44
8 2.93 8.58
9 3.93 15.44
7 1.93 3.72
9 3.93 15.44
SStot

SStot  104.88
Steps in Calculating the F ratio
1b. Calculate SSwithin
» This is the sum of the deviation of each score
from the mean of its own group

SS within   ( ( X  X ) ) 2

1. Find the SS for each group

2. Add them together
SSwithin
Country
X1 X1 – M1 (X1 – M1)2
3 .2 .04
2 -.8 .64
5 2.2 4.84
2 -.8 .64
2 -.8 .64
M1 = 2.8 SS1 = 6.8
SSwithin
Classical
X2 X2 – M2 (X2 – M2)2
5 1.25 1.56
3 -.75 .56
5 1.25 1.56
2 -1.75 3.06
M2 = 3.75 SS2 = 6.74
SSwithin
Blues
X3 X3 – M3 (X3 – M3)2
9 .6 .36
8 -.4 .16
9 .6 .36
7 -1.4 1.96
9 .6 .36
M3 = 8.4 SS3 = 3.2
SSwithin

SS within   ( ( X  X ) )2

 6.8  6.74  3.2

 16.74
Steps in Calculating the F ratio
1c. Calculate SSbetween
» This is the deviation of each group’s mean from
the grand mean, weighted by group size

SStot  SS within  SSbetween

SSbetween  SStot  S within
SSbetween
SSbetween  SStot  S within
 104.88  16.74
 88.14
 Steps in Calculating the F ratio
2. Calculate the mean square (variance)

SS
s 2
X
df
Steps in calculating the F ratio
2. Calculate the mean square (variance)

Mean square (MS):

» the ANOVA term for variance

MSbetween = SSbetween / dfbetween

MSwithin = SSwithin / dfwithin

MS
MSbetween = SSbetween / dfbetween
= 88.14/2
= 44.07

MSwithin = SSwithin / dfwithin

= 16.74/11
= 1.52
MS
» MSbetween = between-groups variance

» MSwithin = within-groups variance

F-ratio
between - groups variance
F
within - groups variance
Steps in calculating the F ratio
3. Calculate the F value
MS between
Fobs 
MS within
 MS between
F ratio Fobs 
MS within
44.07

1.52
 28.99
 ANOVA Table
Mean Sum
Source of Sum of of Squares
variation d.f. squares F-statistic p-value

Between k-1 SSB SSB/k-1 Go to

SSB
(sum of squared k 1
(k groups) SSW Fk-1,nk-k
deviations of group nk  k
means from grand chart
mean)

Within nk-k SSW s2=SSW/nk-k

(sum of squared
(n individuals per
deviations of
group)
observations from
their group mean)

Total nk-1 TSS

variation (sum of squared deviations of
observations from grand mean) TSS=SSB + SSW
ANOVA Table
Source SS df MS F
Between
Groups
Within
Groups
Total
ANOVA Table
Source SS df MS F
Between 88.14 2 44.07 28.99
Groups
Within 16.74 11 1.52
Groups
Total 104.88 13 Fcrit =
3.98
Step 4. Make a decision.
» Determine whether the value of the test statistic is
in the critical region. Draw a picture.

Fcrit = ???
Step 4. Make a decision.

Fcrit = 3.98

» Fobt > Fcrit. Fobt = 28.99

» Reject H0
The F-Distribution
The F-distribution
» Sampling distribution that shows the various values of
F that occur when H0 is true
» Positively skewed – variance is always positive, so Fobt
can never be < 0
» Mean = 1 (most often when the H0 is true, MSbetween will
equal MSwithin and F will equal 1)
» The larger the F, the farther in the tail it is, so the less
likely it is to occur when the H0 is true
» If Fobt > Fcrit, reject the null
 52

THANKS!
Any questions?