CE311 Probability and Statistic

Topic 6.
Comparing Two Population
Means (2)
Prepared by Nabila Husna Shabrina
Outline
• Analysis of Variance

Nabila Husna Shabrina 2

Analysis of Variance

Nabila Husna Shabrina 3

 Analysis of Variance
• Analysis of Variance (ANOVA) is a statistical method, commonly used in all those
situations where a comparison is to be made between more than two population
means
• A hypothesis test that is used to compare the means of two populations is called
t-test. A statistical technique that is used to compare the means of more than
two populations is known as Analysis of Variance or ANOVA.

Types of ANOVA
• One-way ANOVA
• Two-way ANOV

Nabila Husna Shabrina 4

 Analysis of Variance
• one-way ANOVA is a hypothesis test in which only one categorical variable or
single factor is taken into consideration. With the help of F-distribution it enables
us to compare the means of three or more samples. The Null hypothesis (𝑯𝟎 ) is
the equity in all population means while an Alternative hypothesis is a
difference in at least one mean.
• Two-way ANOVA examines the effect of two independent factors on a
dependent variable. It also studies the inter-relationship between independent
variables influencing the values of the dependent variable, if any.
• For example, analyzing the test score of a class based on gender and age. Here
test score is a dependent variable and gender and age are the independent
variables. Two-way ANOVA can be used to find the relationship between these
dependent and independent variables.
Nabila Husna Shabrina 5
 Analysis of Variance
One-way ANOVA
• In general, if k samples are being analyzed, the following hypotheses are being
tested in a one-way ANOVA.
𝐻0 ∶ 𝜇1 = 𝜇2 = 𝜇3 = … . = 𝜇𝐾
𝐻𝑎 : At least one of the means is different from the others.
• The null hypothesis states that the population means for all treatment levels are
equal.
• Because of the way the alternative hypothesis is stated, if even one of the
population means is different from the others, the null hypothesis is rejected.

Nabila Husna Shabrina 6

 Analysis of Variance
Testing these hypotheses by using one-way ANOVA is accomplished by partitioning
the total variance of the data into the following two variances.
1. The variance resulting from the treatment (columns)
2. The error variance, or that portion of the total variance unexplained by the
treatment

Nabila Husna Shabrina 7

 Analysis of Variance

Nabila Husna Shabrina 8

 Analysis of Variance
• As part of this process, the total sum of squares of deviation of values around the
mean can be divided into two additive and independent parts.

SST = total sum of squares

SSC = sum of squares column (treatment)
SSE = sum of squares error
i = particular member of a treatment level
j = a treatment level

Nabila Husna Shabrina 9

 Analysis of Variance
C = number of treatment levels
𝑛𝑗 = number of observations in a given treatment level
𝑥ഥ = grand mean
𝑥𝑗ҧ = mean of a treatment group or level
𝑥𝑖𝑗 = individual value

Nabila Husna Shabrina 10

 Analysis of Variance
The formulas for computing a one-way ANOVA are given below

The conclusion can be obtained by comparing the observed F value and F table
If Observed F > 𝐹𝑡𝑎𝑏𝑙𝑒 then 𝐻0 is rejected
Observed F < 𝐹𝑡𝑎𝑏𝑙𝑒 then 𝐻0 is accepted

Nabila Husna Shabrina 11

 Analysis of Variance
Example.
The following table contains the valve
opening measurements for valves
produced under each operator. Is there a
significant difference in the mean valve
openings of 24 valves produced by the
four operators? (use 𝛼 = 0.05)

Nabila Husna Shabrina 12

 Analysis of Variance

Calculate SSC

Nabila Husna Shabrina 13

 Analysis of Variance
Calculate SSE

Calculate SST

Nabila Husna Shabrina 14

 Analysis of Variance

Nabila Husna Shabrina 15

 Analysis of Variance
• The observed F value is 10.18.
• The observed F value then compared to a critical value from the F table to
determine whether there is a significant difference in treatment or classification
(use 𝛼 = 0.05)
• The F table can be obtained using 𝐹0.05 (𝑑𝑓𝐶 , 𝑑𝑓𝐺 ) = 𝐹0.05 (3,20) = 3.10
• the observed F value of 10.18 is larger than the table F value of 3.10 therefore he
null hypothesis is rejected

Nabila Husna Shabrina 16

 Problems
Exercises : Black, Business Statistics for Contemporary Decision Making, 6th ed.,
Chapter 11 (Page 415)
Problem 11.5
Problem 11.6

Nabila Husna Shabrina 17

 References
• Black, Business Statistics for Contemporary Decision Making, 6th ed., Chapter 11
• Hayter, Probability and Statistics for Engineer and Scientists, 4th ed., Chapter 9

Nabila Husna Shabrina 18

 Next : Simple Linear Regression and
Correlation

Nabila Husna Shabrina 19