Two-Way Anova: (BS Chem 3B - Group 2)

You might also like

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 21

TWO-WAY ANOVA

(BS Chem 3B – Group 2)


Two-way ANOVA
◦ A statistical test that compares the mean differences between two independent factors or variables with at
least two levels

◦ Factors (variables) – e.g. Civil status


◦ Levels – e.g. Single, Married

◦ Independent – the levels are not related


◦ Dependent – the levels are related
Two-way ANOVA
1. State the null and alternative hypothesis
2. State the significant level to be used
3. Calculate degrees of freedom
4. State decision rule
5. Calculate test statistic
6. State results
7. State conclusion
Sample Problem
◦ Researchers
  want to test a new anti-anxiety medication. They measure the anxiety of 36 participants on
different dosages of the medication: 0mg, 50mg, and 100mg. Participants are also divided based on what
school they are attending, which researchers hypothesize will also affect anxiety levels. Anxiety is rated
on a scale of 1-10, with 10 being “high anxiety” and 1 being “low anxiety”. Use to conduct your
analysis.

0mg 50mg 100mg


3 5 7
4 4 8
High school 5 3 7
students 3 5 8
4 5 7
3 5 7
1 5 9
2 4 8
College 1 3 9
students 1 5 8
1 5 7
2 4 9
1. State the null and alternative hypotheses

   

 
2. State the significant level

∝=0.05
◦  
3. Calculate the degrees of Freedom
◦  
0mg 50mg 100mg
3 5 7
4 4 8
High 5 3 7
school
3 5 8
students
4 5 7
3 5 7
1 5 9
2 4 8

College 1 3 9
students 1 5 8
1 5 7
where: a and b – number of levels per factor
N – total number of measurement values 2 4 9
4. State Decision Rule
◦  
Get first the critical value F using the F table:

School

Dosage

Interaction (,

Decision Rule:

School : If F value is greater than 4.1709, reject the null hypothesis.

Dosage : If F value is greater than 3.3158, reject the null hypothesis.

Interaction : If F value is greater than 3.3158, reject the null hypothesis.


F Table
5. Calculate the test statistic F
SS df MS F
School 1
Dosage 2
Interaction 2
Error 30
Total 35
 

Where:
SS – Sum of squares
MS – Mean of Squares
Calculating for SS
◦     𝟗𝟑𝟐+ 𝟖𝟒𝟐 ( 𝟗𝟑+𝟖𝟒  )𝟐
𝟑𝟔 ¿ 𝟐 .𝟐𝟓
¿ −
( 𝟑) ( 𝟔)

  𝟑𝟎 𝟐+𝟓𝟑𝟐 +𝟗 𝟒 𝟐 ( 𝟑𝟎+𝟓𝟑+𝟗𝟒  )𝟐
¿
( 𝟑) (𝟔)

𝟑𝟔 ¿ 𝟏𝟕𝟓 .𝟏𝟔𝟔𝟔𝟔𝟔𝟕
◦  
Calculating for SS

 
•   𝟏𝟕𝟕  𝟐
¿ 𝟏𝟎𝟖𝟏 − 210.75
𝟑𝟔
Calculating for SS
SS df MS F
School 2.25 1
Dosage 175.1666667 2
Interaction 17.16666667 2
Error 16.16666663 30
Total 210.75 35

  𝑺𝑺 𝒆𝒓𝒓𝒐𝒓 = 𝑺𝑺𝒕𝒐𝒕𝒂𝒍 − ( 𝑺𝑺𝒔𝒄𝒉𝒐𝒐𝒍 +𝑺𝑺 𝒅𝒐𝒔𝒂𝒈𝒆 + 𝑺𝑺𝒊𝒏𝒕𝒆𝒓𝒂𝒄𝒕𝒊𝒐𝒏


   
Calculating for MS
 
Calculating for MS
SS df MS F
School 2.25 1 2.25
Dosage 175.1666667 2 87.58333335
Interaction 17.16666667 2 8.583333335
Error 16.16666663 30 0.5388888877
Total 210.75 35
Calculating for F
◦  
Calculating for F
SS df MS F
School 2.25 1 2.25 4.1753
Dosage 175.1666667 2 87.58333335 162.53
Interaction 17.16666667 2 8.583333335 15.93
Error 16.16666663 30 0.5388888877
Total 210.75 35
6. State Results
School : If F value is greater than 4.1709, reject the null hypothesis.
Since F = 4.1753, the null hypothesis is rejected.

Dosage : If F value is greater than 3.3158, reject the null hypothesis.


Since F = 162.53, the null hypothesis is rejected.

Interaction : If F value is greater than 3.3158, reject the null hypothesis


Since F = 15.93, the null hypothesis is rejected.
7. State Conclusions
◦  High school students and college students have significantly different anxiety
levels, F(1,30)=4.1753, p 0.05.

 There was a significant difference in the anxiety levels of participants taking


different dosage of medication, F(2,30)=162.53, p 0.05.

 An interaction effect was present between the school level and dosage of
medication with respect to the anxiety level, F(2,30)=15.93, p 0.05.
It means that, for example, the effect of school level on anxiety level depend on the dosage of the medication taken.
Two-Way Anova Using Excel
Thank you for listening.

You might also like