Name: Honey Lee L.

Siega MAED-TRL
Course Title: EDUC 202/TRL 200 Statistics for Educational Research with Software
Application
Course Instructor: Professor Evelyn Ballenas

Test of Difference for More Than Two Independent Groups

ANOVA and KRUSKALL WALLIS H TEST
Activity Sheet 6
(Individual)
Objectives:
1. Compare parametric by highlighting their key differences and appropriate use cases.
2. Assess the assumptions required for conducting parametric tests when analyzing more
than two independent samples.
3. Apply parametric (ANOVA) to various data sets to test for differences across multiple
independent samples. Analyze and interpret the results, discussing their implications for
educational practices.
4. If significant differences are found, perform multiple comparison tests to identify which
groups differ significantly.
5. Evaluate the suitability of parametric and non-parametric tests based on data
characteristics, including normality and other distributional properties.

Problem 1:
1. A researcher wishes to try three different techniques to lower the blood pressure of
individuals diagnosed with high blood pressure. The subjects are randomly assigned
to three groups; the first group takes medication, the second group exercises, and
the third group follows a special diet. After four weeks, the reduction in each person's
blood pressure, measured in millimeters of mercury (mmHg), is recorded. Assume
that the data in each group is approximately normal. Is there a significant difference
between the techniques used to lower blood pressure at α=0.05? If you find a
difference, perform pairwise tests to determine where the difference lies.

Medication Group Exercise Group Diet Group

9 0 4
10 2 5
12 3 8
13 6 9
15 8 12

Ho (null hypothesis): There is no significant difference among the three techniques used to
lower blood pressure.
Ha (alternative hypothesis): There is a significant difference on either of the techniques
used to lower blood pressure.
 ANOVA
Scores

Sum of Squares df Mean Square F Sig.

Between Groups 160.133 2 80.067 9.168 .004

Within Groups 104.800 12 8.733
Total 264.933 14

Since the p-value is less than the value of alpha (0.05), therefore reject the Ho (null
hypothesis). There is at least one or more statistically scores between the different
techniques used to lower blood pressure. It means that there is significant difference on
either of the techniques.

Post Hoc Test

Multiple Comparisons
Dependent Variable: Scores

(I) Group (J) Group Mean Difference Std. Error Sig. 95% Confidence Interval
(I-J) Lower Bound Upper Bound
*
Exercise 8.000 1.869 .001 3.93 12.07
Medication
Diet 4.200* 1.869 .044 .13 8.27
*
Medication -8.000 1.869 .001 -12.07 -3.93
LSD Exercise
Diet -3.800 1.869 .065 -7.87 .27
*
Medication -4.200 1.869 .044 -8.27 -.13
Diet
Exercise 3.800 1.869 .065 -.27 7.87

*. The mean difference is significant at the 0.05 level.

Interpretation:
Medication vs. Exercise
Based on the result, there is a significant difference in the mean in the scores between
Mediation and Exercise having the p-value of .001 which is less than 0.05

Exercise vs. Diet

Based on the result, there is no significant difference between the score of Exercise and Diet
having the p-value of .065 which greater than 0.05

Diet vs. Medication

Based on the result, there is a significant difference between the scores of Diet and
Medication having the p-value of .044 which is less than 0.05
Homogeneous Subsets
Scores
Group N Subset for alpha = 0.05
1 2
Exercise 5 3.80
a
Tukey B Diet 5 7.60 7.60
Mediation 5 11.80
Exercise 5 3.80
Diet 5 7.60
Duncana
Mediation 5 11.80
Sig. .065 1.000

Means for groups in homogeneous subsets are displayed.

To further support the Post Hoc Test, it suggests in the Tukey and Duncan that there no
statistically significant difference between the scores of Diet and Exercise. However, there is
a significant difference between the scores of Diet vs. Medication and Exercise vs.
Medication.

Problem 2:
2. A researcher wishes to see whether there is any difference in the weight gains of
athletes following one of three special diets. Athletes are randomly assigned to three
groups and placed on the diet for 6 weeks. The weight gains (in pounds) are given.
Assume weight gains are normally distributed, and the variances are equal. At a 0.05
significance level, can the researcher conclude that there is a difference in the diets?
Diet A: 3, 6, 7,4
Diet B: 10, 12, 11, 14, 8, 6
Diet C: 8,3,2,5

Ho (null hypothesis): There is no significant difference in the weight gains among three
special diets.
Ha (alternative hypothesis): There is a significant difference in the weight among the three
special diets.

ANOVA
WeightGains

Sum of Squares df Mean Square F Sig.

Between Groups 101.095 2 50.548 7.740 .008

Within Groups 71.833 11 6.530
Total 172.929 13

Since the p-value is less than the value of alpha (0.05), therefore reject the Ho (null
hypothesis). Therefore, there is a significant difference in the weight on either of the three
special diets.
Post Hoc Test
Multiple Comparisons
Dependent Variable: WeightGains

(I) Group (J) Group Mean Difference Std. Error Sig. 95% Confidence Interval
(I-J) Lower Bound Upper Bound

Diet B -5.167* 1.650 .010 -8.80 -1.54

Diet A
Diet C .500 1.807 .787 -3.48 4.48

Diet A 5.167* 1.650 .010 1.54 8.80

LSD Diet B
*
Diet C 5.667 1.650 .006 2.04 9.30

Diet A -.500 1.807 .787 -4.48 3.48

Diet C
*
Diet B -5.667 1.650 .006 -9.30 -2.04

*. The mean difference is significant at the 0.05 level.

Diet A vs. Diet B

Based on the result, there is a significant difference on weight gains between Diet A and B
having p-value of .010 which is less than 0.05

Diet B vs. Diet C

Based on the result, there is a significant difference on weight gains between Diet B and C
having p-value of .006 which is less than 0.05

Diet C vs Diet A
Based on the result, there is no significant difference on weight fgains between Diet C and A
having p-value of .787 which is greater that 0.05

Homogeneous Subsets
WeightGains
Group N Subset for alpha = 0.05

1 2

Diet C 4 4.50
a,b
Tukey B Diet A 4 5.00

Diet B 6 10.17
Diet C 4 4.50

Diet A 4 5.00
Duncana,b
Diet B 6 10.17

Sig. .775 1.000

Means for groups in homogeneous subsets are displayed.

To further support the Post Hoc Test, it suggests in the Tukey and Duncan that there no
statistically significant difference between the scores of Diet A and Diet C. However, there is
a significant difference between Diet A vs Diet B and Diet C vs Diet A.