PORTFOLIO

in

II

SUBMITTED TO:

ENGR. BUENAVENTURADA D. LIBOT, PhD, EM,

HRM, PA

SUBMITTED BY:

EUFE RHODA R. GALON

PhD-EM
 UNIVERSITY OF BOHOL
PROFESSIONAL STUDIES

FINAL REQUIREMENTS: PORTFOLIO ON LEARNINGS & REFLECTIONS

DATE SUBMITTED: January 11, 2022

A Research Activity submitted to

ENGR. BUENAVENTURADA D. LIBOT, PhD, EM, HRM, PA
As partial fulfillment of the requirements in
EM303 STATISTICS II
1st Semester: School Year 2021 – 2022

EUFE RHODA R. GALON

PhD. E M
 TABLE OF CONTENTS

Activity 1: Focus Questions on Descriptive Statistics

Answer & Solutions to Activity 1

Learnings & Reflection of Activity 1

Activity 2: Focus Questions on Parametric Test – T - Test

……… T-Test for Independent Samples and Correlated Samples

Answer & Solutions to Activity 2

Learnings & Reflection of Activity 2

Activity 3: Focus Questions on Parametric Test

……… The Pearson Product Correlation of r & ANOVA

Answer & Solutions to Activity 3

Learnings & Reflection of Activity 3

Activity 4: Focus Questions on Non-Parametric Test

………Chi Square, P –Value, Kruskal Wallis Test

Answer & Solutions to Activity 4

Learnings & Reflection of Activity 4

 UNIVERSITY OF BOHOL
PROFESSIONAL STUDIES

Activity # 1: FOCUS QUESTIONS ON DESCRIPTIVE STATISTICS

DATE SUBMITTED: September 28, 2021

A Research Activity submitted to

ENGR. BUENAVENTURADA D. LIBOT, PhD, EM, HRM, PA
As partial fulfillment of the requirements in
EM303 STATISTICS II
1st Semester: School Year 2021 – 2022

EUFE RHODA R. GALON

PhD. E M
 ACTIVITY 1: ANSWERS & SOLUTIONS

Focus Questions on Descriptive Statistics

Given data:

The following is a list of scores resulting from an English examination

administered to 40 students:

46 42 77 69 98
45 50 78 43 85
54 49 68 73 91
59 70 92 100 89
62 59 51 52 94
66 96 59 83 48
76 99 90 93 62
54 62 46 61 91

1. Rank the students based on their scores.

2. Determine the ff:
2.1 measures of central tendency
2.2 point measures
2.3 measures of dispersion
2.4 Skewness
2.5 Kurtosis

NOTE: Add your assigned number to the first given data.

STATISTICS II - ACTIVITY 1      
           
Given data:        
           
The following is a list of scores resulting from an English
examination administered to 40 students.  
           
46 42 77 69 98  
45 50 78 43 85  
54 49 68 73 91  
59 70 92 100 89  
62 59 51 52 94  
66 96 59 83 48  
76 99 90 93 62  
54 62 46 61 91  
           
1. Rank the students based on their scores.  
2. Determine the ff:        
  2.1 measures of central tendency  
  2.2 point measures      
  2.3 measures of dispersion    
  2.4 Skewness      
  2.5 Kurtosis      
           
NOTE: Add your assigned number to the first given data.
           
TRADITIONAL WAY

1. Rank the students based on their scores  

  Plus Adjusted Sorting    
Given Assigned Given From CN RANK
Scores Number Scores Highest to  
      Lowest    
46 8 54 100 1 1
45   45 99 2 2
54   54 98 3 3
59   59 96 4 4
62   62 94 5 5
66   66 93 6 6
76   76 92 7 7
54   54 91 8 8.5
42   42 91 9 8.5
50   50 90 10 10
49   49 89 11 11
70   70 85 12 12
59   59 83 13 13
96   96 78 14 14
99   99 77 15 15
62   62 76 16 16
77   77 73 17 17
78   78 70 18 18
68   68 69 19 19
92   92 68 20 20
51   51 66 21 21
59   59 62 22 23
90   90 62 23 23
46   46 62 24 23
69   69 61 25 25
43   43 59 26 27
73   73 59 27 27
100   100 59 28 27
52   52 54 29 30
83   83 54 30 30
93   93 54 31 30
61   61 52 32 32
98   98 51 33 33
85   85 50 34 34
91   91 49 35 35
89   89 48 36 36
94   94 46 37 37
48   48 45 38 38
62   62 43 39 39
91   91 42 40 40
2. Determine the ff:        
2.1 Measures of Central Tendency    
           
MEAN = SUM ÷TOTAL SCORE      
  2790 ÷ 40 = 69.75      
  69.75        
MEDIAN = AVERAGE OF TWO MOST MIDDLE VALUES
  67        
MODE = VALUE THAT APPEARS MOST FREQUENTLY
  62,59, & 54      
  LONG METHOD
X= R = CN IF X
  SCORES appears once
1. Rank
the
Given
Given students
Plus Assign Number number after
based CN RANK
Data adding the
assign on their
number scores
46 8 54 100 1 1
45 45 99 2 2
54 54 98 3 3
59 59 96 4 4
62 62 94 5 5
66 66 93 6 6
76 76 92 7 7
54 54 91 8 8.5
42 42 91 9 8.5
50 50 90 10 10
49 49 89 11 11
70 70 85 12 12
59 59 83 13 13
96 96 78 14 14
99 99 77 15 15
62 62 76 16 16
77 77 73 17 17
78 78 70 18 18
68 68 69 19 19
92 92 68 20 20
MEDIAN
51 51 66 21 21
59 59 62 22 23
90 90 62 MODE 23 23
46 46 62 24 23
69 69 61 25 25
43 43 59 26 27
73 73 59 MODE 27 27
100 100 59 28 27
52 52 54 29 30
83 83 54 MODE 30 30
93 93 54 31 30
61 61 52 32 32
98 98 51 33 33
85 85 50 34 34
91 91 49 35 35
89 89 48 36 36
94 94 46 37 37
48 48 45 38 38
62 62 43 39 39
91 91 42 40 40
sum of all
2782   scores 2790
  MEAN = SUM ÷TOTAL SCORE
  2790 ÷ 40 = 69.75
  69.75
MEDIAN = AVERAGE OF TWO MOST
  MIDDLE VALUES
  67
  MODE = VALUE THAT APPEARS MOST FREQUENTLY
  62,59, & 54
 SHORT METHOD  
 
 
 
X F FX
 
 
100 1 100  
99 1 99  
98 1 98  
96 1 96  
94 1 94  
93 1 93  
92 1 92  
91 2 182  
90 1 90  
89 1 89  
85 1 85  
83 1 83  
78 1 78  
77 1 77  
76 1 76  
73 1 73  
70 1 70  
69 1 69  
68 1 68  
66 1 66  
62 3 186  
61 1 61  
59 3 177  
54 3 162  
52 1 52  
51 1 51  
50 1 50  
49 1 49  
48 1 48  
46 1 46  
45 1 45  
43 1 43  
42 1 42  
SUM 40 2790  
2.2 Point Measures          
   
   
 
QUARTILE DECILE  
 
 
100 1 100 1  
99 2 99 2  
98 3 98 3  
96 4   96 4 D9 = 95
94 5 94 5  
93 6 93 6  
92 7 92 7  
91 8.5   91 8.5 D8 = 91
91 8.5 91 8.5  
90 10 Q3 = 89.5 90 10  
89 11 89 11  
85 12   85 12 D7 = 84
83 13 83 13  
78 14 78 14  
77 15 77 15  
76 16   76 16 D6 = 75
73 17 73 17  
70 18 70 18  
69 19 69 19  
68 20 Q2 = 67 68 20 D5 = 67
66 21   66 21  
62 23 62 23  
62 23 62 23  
62 23 62 23  
61 25   61 25 D4 = 61
59 27 59 27  
59 27 59 27  
59 27 59 27  
54 30   54 30 D3 = 55
54 30 Q1 = 54 54 30  
54 30 54 30  
52 32 52 32  
51 33   51 33 D2 = 51
50 34 50 34  
49 35 49 35  
48 36 48 36  
46 37   46 37 D1 = 46
45 38 45 38  
43 39 43 39  
42 40 42 40  
   
2.2 Point Measures  
   
  QUARTILE DECILE  
  Q1 = N + 1 X 1 ÷ 4 = 10.25 D1 = N + 1 X 1 ÷ 10 = 4.1
  Q1 = 54 D1 = 46  
  Q2 = N + 1 X 2 ÷ 4 = 20.5 D2 = N + 1 X 2 ÷ 10 = 8.2
  Q2 = 67 D2 = 51  
  Q3 = N + 1 X 3 ÷ 4 = 30.75 D3 = N + 1 X 3 ÷ 10 = 12.3
  Q3 = 89.5 D3 = 55  
  D4 = N + 1 X 4 ÷ 10 = 16.4
  D4 = 61  
  D5 = N + 1 X 5 ÷ 10 = 20.5
  D5 = 67  
  D6 = N + 1 X 6 ÷ 10 = 24.6
  D6 = 75  
  D7 = N + 1 X 7 ÷ 10 = 28.7
  D7 = 84  
  D8 = N + 1 X 8 ÷ 10 = 32.8
  D8 = 91  
  D9 = N + 1 X 6 ÷ 10 = 36.9
  D9 = 95  
             

  2.3 Measures of Dispersion  

  STANDARD DEVIATION
  STEP 1:   STEP 2: STEP 3:
 
SQUARE OF DEVIATION
  X MEAN X - MEAN FROM THE MEAN
 
54 100 69.75 30.25 915.0625
45 99 69.75 29.25 855.5625
54 98 69.75 28.25 798.0625
59 96 69.75 26.25 689.0625
62 94 69.75 24.25 588.0625
66 93 69.75 23.25 540.5625
76 92 69.75 22.25 495.0625
54 91 69.75 21.25 451.5625
42 91 69.75 21.25 451.5625
50 90 69.75 20.25 410.0625
49 89 69.75 19.25 370.5625
70 85 69.75 15.25 232.5625
59 83 69.75 13.25 175.5625
96 78 69.75 8.25 68.0625
99 77 69.75 7.25 52.5625
62 76 69.75 6.25 39.0625
77 73 69.75 3.25 10.5625
78 70 69.75 0.25 0.0625
68 69 69.75 -0.75 0.5625
92 68 69.75 -1.75 3.0625
51 66 69.75 -3.75 14.0625
59 62 69.75 -7.75 60.0625
90 62 69.75 -7.75 60.0625
46 62 69.75 -7.75 60.0625
69 61 69.75 -8.75 76.5625
43 59 69.75 -10.75 115.5625
73 59 69.75 -10.75 115.5625
100 59 69.75 -10.75 115.5625
52 54 69.75 -15.75 248.0625
 83 54 69.75 -15.75 248.0625
93 54 69.75 -15.75 248.0625
61 52 69.75 -17.75 315.0625
98 51 69.75 -18.75 351.5625
85 50 69.75 -19.75 390.0625
91 49 69.75 -20.75 430.5625
89 48 69.75 -21.75 473.0625
94 46 69.75 -23.75 564.0625
48 45 69.75 -24.75 612.5625
62 43 69.75 -26.75 715.5625
91 42 69.75 -27.75 770.0625
  2790   V 13131.5
2.3 Measures of Dispersion    
RANGE = HIGHEST SCORE MINUS LOWEST SCORE
  100 - 42 = 58    
  58      
STANDARD DEVIATION    
Step 1: Find the X Mean    
  2790 ÷ 40      
  69.75      
Step 2: Find each scores deviation from the mean
Step 3: Square each Deviation from the Mean
Step 4: Find the Sum of Squares  
Step 5: Find the Variance (Sum of Squares ÷ (N-1)
  13131.5 ÷ (40-1)    
  13131.5 ÷ 39    
  336.7051      
Step 6: Find the Square Root of the Variance
  336.7051      
SD 18.34953      

2.4 Skewness            
2.4 Measures of Skeweness          
  MEAN IS GREATER THAN MEDIAN = NEGATIVELY SKEWED  
  69.75 > 67        
  NEGATIVELY SKEWED        
  RULES on How Skeweness is READ:      
Approximtely Symmetric or Fairly Symmetrical -0.5 0.5    
  Moderately Skewed   -1 -0.5    
        0.5 1    
  Highly Skewed   -1 more than 1  
Pearson's Coefficient of Skewness        
Formula:              
  Skew = 3 x (Mean - Median ) ÷ SD      
  Skew = 3 x (69.75 - 67 ) ÷ 18.35      
    = 3 x (2.75 ) ÷ 18.35        
    = 8.25 ÷ 18.35        
    0.449591          
    Fairly Symmetrical or Approximately Symmetric  
Interpreting Skewness and Kurtosis        
Skewness is right skewed if value is greater than +1.0    
  is left skewed if value is lesser than - 1.0    
Kurtosis is Leptokurtic if value is greater than +1.0    
  is Platykurtic if value is lesser than - 1.0    
  is mesokurtic if value is between leptokurtik & platykurtik
      if value looks like "normal curve"  
2.5 Kurtosis          
Kurtosis = n * Σni(Yi – Ȳ)4 / (Σni(Yi – Ȳ)2)2      
  STEP 1:   STEP 2:      
   
Variable Mean Deviation Deviation2 Deviation4
   
54 100 69.75 30.25 915.0625 837339.3789  
45 99 69.75 29.25 855.5625 731987.1914  
54 98 69.75 28.25 798.0625 636903.7539  
59 96 69.75 26.25 689.0625 474807.1289  
62 94 69.75 24.25 588.0625 345817.5039  
66 93 69.75 23.25 540.5625 292207.8164  
76 92 69.75 22.25 495.0625 245086.8789  
54 91 69.75 21.25 451.5625 203908.6914  
42 91 69.75 21.25 451.5625 203908.6914  
50 90 69.75 20.25 410.0625 168151.2539  
49 89 69.75 19.25 370.5625 137316.5664  
70 85 69.75 15.25 232.5625 54085.31641  
59 83 69.75 13.25 175.5625 30822.19141  
96 78 69.75 8.25 68.0625 4632.503906  
99 77 69.75 7.25 52.5625 2762.816406  
62 76 69.75 6.25 39.0625 1525.878906  
77 73 69.75 3.25 10.5625 111.5664063  
78 70 69.75 0.25 0.0625 0.00390625  
68 69 69.75 -0.75 0.5625 0.31640625  
92 68 69.75 -1.75 3.0625 9.37890625  
51 66 69.75 -3.75 14.0625 197.7539063  
59 62 69.75 -7.75 60.0625 3607.503906  
90 62 69.75 -7.75 60.0625 3607.503906  
46 62 69.75 -7.75 60.0625 3607.503906  
69 61 69.75 -8.75 76.5625 5861.816406  
43 59 69.75 -10.75 115.5625 13354.69141  
73 59 69.75 -10.75 115.5625 13354.69141  
100 59 69.75 -10.75 115.5625 13354.69141  
52 54 69.75 -15.75 248.0625 61535.00391  
83 54 69.75 -15.75 248.0625 61535.00391  
93 54 69.75 -15.75 248.0625 61535.00391  
61 52 69.75 -17.75 315.0625 99264.37891  
98 51 69.75 -18.75 351.5625 123596.1914  
85 50 69.75 -19.75 390.0625 152148.7539  
91 49 69.75 -20.75 430.5625 185384.0664  
89 48 69.75 -21.75 473.0625 223788.1289  
94 46 69.75 -23.75 564.0625 318166.5039  
48 45 69.75 -24.75 612.5625 375232.8164  
62 43 69.75 -26.75 715.5625 512029.6914  
91 42 69.75 -27.75 770.0625 592996.2539  
  2790     13131.5 7195542.781 sum
Kurtosis Formula:    
Kurtosis = n * Σni(Yi – Ȳ)4 / (Σni(Yi – Ȳ)2)2
Step 1: Compute for Mean    
  sum(Be9:Be48)/N    
  2790/40      
  69.75      
Step 2: Compute for Deviation 2 & Deviation 4
  Variable - Mean = Deviation  
  Deviation x Deviation = Deviation 2
  Deviation 2 x Deviation 2 = Deviation 4
Step 3: Compute for Second Moment Formula
  Second Moment = Σni(Yi – Ȳ)2 / n  
  13131.5 ÷ 40      
   328.29      
Step 4: Compute for Fourth Moment Formula
  Fourth Moment = Σni(Yi – Ȳ)4 / n  
  7195542.781 ÷ 40    
  179888.57      
Step 5: Kurtosis = Fourth Moment / (Second Moment)2
  179888.57 ÷ (328.2875)2  
  179888.57 ÷ 107774.32    
  1.66912276      
  1.67 Platykurtic      
Kurtosis is: Platykurtic when kurtosis is lesser than 3
  Mesokurtic when kurtosis is equal to 3
  Leptokurtic when kurtosis is greater than 3
EXCELL WAY
English Scores
54 skewness 0.21 Approximately Symmetric
45
54 Kurtosis -1.35 Platykurtic
59
62
66
76
54
42
50
49
70
59
96 Column1
99
62 Mean 69.75
77 Standard Error 2.901315
78 Median 67
68 Mode 54
92 Standard Deviation 18.34953
51 Sample Variance 336.7051
59 Kurtosis -1.34711
90 Skewness 0.205991
46 Range 58
69 Minimum 42
43 Maximum 100
73 Sum 2790
100 Count 40
52
83
93
61
98
85
91
89
94
48
62
91
 ACTIVITY 1: LEARNINGS & REFLECTION

The first activity was actually the easiest, but for me, it’s the most difficult one. Why? This is
the first time I hear again the terms from 29 years of enrolling Statistics 1 during the Masteral years. It
made me afraid, how to learn this difficult subject through online. It made me think, when I felt
difficulty before during the face to face classes, how much more, that we are through online classes?
But later on, I realize, I’ve learn much through online classes. Why? It is because, Online classes are
more challenging. You need to study, research and do the trial and error by yourself alone, against
the given example. Your professor may not be with you during the times that you do the actual
research, and if you ask question about it, she may not be aware coz, she might just scroll your
questions and not really into answering it. Or she may answer your querries, but by the time she will
answer to you, you have already done your individual research. These are some realities that I’ve
been through while learning this most challenging subject for me.

Actually, it is so funny, because the reason, I did not enroll Statistics II before, is that, for me
it’s the most difficult subject. So during the face to face classes, I did not enroll this subject. But the
chances are, I do enroll this subject this time, during the pandemic, which is for me, a very
challenging one. But being honest, I’m glad, I enrolled it now, because, it made me understand better
the things I’ve understand before through face to face discussions. Now, I am confident, I can even
discuss others all these things because, the way I learn it, I did the trial and error by myself, study
and research it by myself and learn by myself, which for me was more effective. And to be honest, I
would say, I’ve learned much this subject.

Talking with the first activity, It made me review and recall my past knowledge on how to
compute for the mean, mode and median, which was long forgotten already. It made me recall also
my background on computing the standard deviation. But the interpretation and of Skewness and
kurtosis is new for me. It takes me the whole night to have a research on some examples and
discussions online about skewness and kurtosis. But I’m glad, I learned how interpretation is done.

Another challenges I meet during this activity is about the application on trying to solve the
given activity through excell. My exposure before is more on the manual way of solving what is
asked. So making more research on how these things are solved through excel is done. But once I
learned it, it made me realize, now a days solving statistics is made easier.

With my journey in Statistics II, I’ve realized, being a student is more fun. And studying at an
old age is more difficult and challenging, because your mind work slowly compared to the younger
ones, your classmates. But it made me enjoy, because, for me, learning Statistics before in a
traditional way is an advantage for me. Why? My classmates are very expert in solving the given
problems through excel, but compared to them, I am more familiar in solving it through the traditional
way. It is so much fun, learning this way. Giving them discussions on how the given numbers are
solved in a traditional way is more fun for it made me make sure that my answer is correct, as I
compare their answers in an excel way.

Although the first activity is very challenging for me, but now I realized, it is actually the easiest
one compared to the rest of the activities. And I really thank the opportunity of learning this way with
you and with my classmates.
 UNIVERSITY OF BOHOL
PROFESSIONAL STUDIES

Activity # 2: FOCUS QUESTIONS ON PARAMETRIC TEST – T-TEST

DATE SUBMITTED: October 19, 2021

A Research Activity submitted to

ENGR. BUENAVENTURADA D. LIBOT, PhD, EM, HRM, PA
As partial fulfillment of the requirements in
EM303 STATISTICS II
1st Semester: School Year 2021 – 2022

EUFE RHODA R. GALON

PhD. E M

UNIVERSITY OF BOHOL
 GRADUATE SCHOOL

STATISTICS II

FOCUS QUESTIONS FOR T - TEST

PARAMETRIC TEST

Directions: Solve the following using excell and data analysis. State your inferential

questions and null hypothesis, then test your null hypothesis using 0.05 level of

significance. Based on your findings, make a conclusion and give your

interpretation.

1. The data below represent the number of hours of pain relief provided by two brands of

headache tablets administered to 24 subjects. These subjects were randomly divided

into two groups and each group was treated with a different brand.

Brand X1 Brand X2

9 6

16 4

14 2

6 8

8 10

16 12

14 14

10 6

12 10

14 8

10 4

10 6

2. Ten subjects were given an attitude test on a controversial issue. Then they were shown

a film favorable to the ten subjects and the same attitude test was administered.

Pre - test Post - test

34 42

36 40
 32 48

48 56

40 40

50 60

44 46

36 48

30 38

30 15

ANSWERS & SOLUTIONS:

Number 1:
Excell Formula:
0.007343251 TTEST = (Array1,Array2,tailed,type)
Array 1
Array 2
Tails 2 2 tailed
Type 3 unequal variance (because the ratio is more than 1:4)
THE T - TEST FOR TWO INDEPENDENT SAMPLES/GROUPS
TRADITIONAL (manual)
t= X1 - X2
√ ( SS1 + SS2 ) (1 + 1 )
n1 n2 - 2 n1 n2
Where:
t = the t test
X1 = the mean of group 1
X2 = the mean of group 2
SS1 = the sum of squares of group 1
SS2 = the sum of squares of group 2
n1 = the number of observations in group 1 Type equation here.
n2 = the number of observations in group 2
Brand X1 Brand X2
X1 (X1) 2 X2 (X2) 2
9 81 6 36
16 256 4 16
14 196 2 4
6 36 8 64
8 64 10 100
16 256 12 144
14 196 14 196
10 100 6 36
12 144 10 100
14 196 8 64
10 100 4 16
10 100 6 36
139 1725 90 812
ROUND OFF TO TWO DIGITS:
∑X1 = 139 ∑(X1)² = 1725 ∑X2 = 90 ∑(X2)² = 812
n1 = 12 n2 = 12
 ͞ X1 = 11.58 ͞ X2 = 7.5

SS1 = ∑(X1)² - [∑(X1)]² SS2 = ∑(X2)² - [∑(X2)]²

n1 n2
SS1 = 1725 - (139)² SS2 = 812 - (90)²
12 12
SS1 = 1725 - 19,321 SS2 = 812 - 8,100
12 12
SS1 = 1725 - 1610.08 SS2 = 812 - 675
SS1 = 114.92 SS2 = 137
t= ͞ 1 - ͞X2
X
√ ( SS1 + SS2 ) (1 + 1 )
n1 n2 - 2 n1 n2
t= 11.52 - 7.5
√ ( 114.92 + 137 ) (1 + 1 )
12 12 - 2 12 12
t= 4.02
√ ( 251.92 ) ( .08 + .08 )
22
t= 4.02
√ ( 11.45 ) ( .16 )

t= 4.02
√ (1.832 )

t= 4.02
1.3535
t= 2.97
NOT ROUND OFF:
∑X1 = 139 ∑(X1)² = 1725 ∑X2 = 90 ∑(X2)² = 812
n1 = 12 n2 = 12
͞ X1 = 11.583 ͞ X2 = 7.5

SS1 = ∑(X1)² - [∑(X1)]² SS2 = ∑(X2)² - [∑(X2)]²

n1 n2
SS1 = 1725 - (139)² SS2 = 812 - (90)²
12 12
SS1 = 1725 - 19,321 SS2 = 812 - 8,100
12 12
SS1 = 1725 - 1610.083 SS2 = 812 - 675
SS1 = 114.917 SS2 = 137

t= ͞ 1 - ͞X2
X
√ ( SS1 + SS2 ) (1 + 1 )
n1 n2 - 2 n1 n2
t= 11.583 - 7.5
√ ( 114.917 + 137 ) (1 + 1 )
12 12 - 2 12 12
t= 4.083
√ ( 251.917 ) ( .08 + .08 )
22
t= 4.083
√ ( 11.45077272 ) ( .16 )
t= 4.083
√ (1.832123635 )
t= 4.083
 1.353559616
t= 3.016490704

SOLVING BY THE STEPWISE METHOD:

I. PROBLEM:

Is there a significant difference between the number of

hours of pain relief between Brand X1 and Brand X2 of

headache tablets.

II. HYPOTHESIS:

H0 There is no significant difference between the number of hours

of pain relief between Brand X1 and Brand X2 of headache tablets

H0 ͞X1 = ͞X2

H1 There is a significant difference between the number of hours

of pain relief between Brand X1 and Brand X2 of headache tablets

H1 ͞X1 ≠ ͞X2

III. LEVEL OF SIGNIFICANCE:

 = .05
df = n1 + n2 - 2
= 12 + 12 - 2
= 22
t .05 = 2.074 t-tabular value at .05
IV. STATISTICS:

t - test for two independent samples

V. DECISION RULE:

If the t- computed value is greater than or beyond the t-tabular/

critical value, reject H0.

VI. CONCLUSION:

Since the t-computed value of 2.97 is greater than t-tabular value

of 2.074 at .05 level of significance with 22 degrees of freedom, the null

hypothesis is rejected in favor of the research hypothesis.

This means that there is a significant difference between the number

of hours of pain reliefs between Brand X1 and Brand X2 of headache tablets.

It implies that Brand X1 is more effective as a pain relieving tablet

because it has a longer number of hours of pain reliefs than the Brand X2.

Considering that the average number of hours of pain reliefs of Brand X1 is

11.58, wherein it is greater compared to the number of hours of pain reliefs

of Brand X2 which is only 7.5.

Number 2:
Excell Formula:
0.040628234 TTEST = (Array1,Array2,tailed,type)
Array 1
Array 2
Tails 1 1 tailed
Type 1 Paired variance

THE T - TEST FOR CORRELATED SAMPLES

TRADITIONAL (manual)

t= D͞ ________

√ ∑D² - (∑D)²

n__________
n (n-1)

Where:
D͞ = the mean difference between the pretest and the posttest.

∑ D² = the sum of squares of the difference between the pretest

and the post test

∑ D = the summation of the difference between the pretest and the

posttest

n = the sample size

Pre - test Post - test

X1 X2 D D²
34 42 -8 64
36 40 -4 16
32 48 -16 256
48 56 -8 64
40 40 0 0
50 60 -10 100
44 46 -2 4
36 48 -12 144
30 38 -8 64
30 15 15 225
-53 937
∑ D = - 53 ∑ D² = 937
D͞ = - 53/10
D͞ = - 5.3
t= D͞ ________
 √ ∑D² - (∑D)²
________n________
n(n-1)
t= - 5.3_______
√ 937 - (-53)²
_______10________
10 (10-1)
t= - 5.3_______
√ 937 - 2809
_______10________
10 (9)
t= - 5.3_______
√ 937 - 2809
90
t= - 5.3_____
√ 656.1
90
t= - 5.3_____
√ 7.29
t= - 5.3_____
2.7
t = 1.96

I. PROBLEM:

Is there a significant difference between the pretest and the

posttest given of an attittude test after showing a controversial film issue?

II. HYPOTHESIS:

H0 There is no significant difference between the pretest and the

posttest given of an attittude test after showing a controversial film

issue. or the showing of a controversial film issue does not affect the

attitude of the ten subjects.

H1 The posttest result is higher than the pretest result.

III. LEVEL OF SIGNIFICANCE:

 = .05
df = n-1
= 10 - 1
= 9
t .05 = - 1.833 t-tabular value at .05
IV. STATISTICS:

t - test for correlated samples

 V. DECISION RULE:

If the t- computed value is greater than or beyond the critical value, reject Ho

VI. CONCLUSION:

The t-computed value of - 1.96 is beyond or greater than the t-critical

value of - 1.833 at .05 level of significance with 9 degrees of freedom, the

null hypothesis is therefore rejected in favor of the research hypothesis.

This means that the posttest result is higher than the pretest result.

It implies that the showing of a controversial film issue affects the

attitudes of the ten subjects.

ACTIVITY 2: LEARNINGS & REFLECTION

This second activity is a new learnings for me. It made me compute the t-value, compare it
with the t-tabular value. I can recall that while doing the research it takes me a whole night to
research the formula on how to get the t-tabular value given. It’s so funny because the moment I
realized it’s just a t-tabular value where you can just search in google. So this made me develop a
technique, that whatever my query on the problems given, I’ll just search for it in google, and google
will suggest the solutions and thus make my research and study simple and easy.

In computing the t-value, I’ve learned to analyze every single details of the given problem.
Thus it made me learn to determine whether the data of the two independent or correlated groups are
significant or insignificant.

Actually, what made me get the correct solutions I think is the notes and the guide you have
given to us. Although I really need to hear your feedback on the activities submitted, to make sure
and get your affirmation that what I did is right and the solutions I computed is correct. But still with
the research I made, it made me confirm, I’m doing the computations right.

With these, I can say that doing a simple research, I think I can already determine whether the
data or the results of the research survey could be significant or insignificant. But honestly, I do have
difficulty in identifying what kind of formula should I used when computing the data given. In the
activity, it’s a good thing that it has a clue as to what formula are we going to use. In the long run, and
through the help of google, it made me decide, that the formula I used is correct, because in google
and u-tube, there are problems that more or less are similar to the problems given to me. I think this
is an advantage if you are doing the research by yourself. You will discover more and learn effectively
things because you involve yourself in analyzing, solving, research and computing by yourself.

Doing the activity is very challenging for me, but it made me more satisfied that after doing
such, I’ve gain new knowledge in doing the activity by myself and made me enjoy to solve more.
Although, my greatest enemy is the time, because since I’m working, my time is very precious. Doing
my studies at night and waking up with less sleep and work in the day….is really very challenging.
But I’m glad, I’m doing the right decision to enroll Statistics this time of pandemic, because I realize, I
can still cope up to study by myself through reading and research.

My reflection? There’s nothing difficult or problem that one cannot overcome, if only the person
involve will do his best, make efforts, and commit himself to solve for it. This is the realization I’ve
meet after answering the activity.

Again, I enjoy answering the problems, but what makes me so stress is the deadlines that
mixed up with other deadlines in my work. But being a student is so much fun. Learning with my
classmates made my challenges in solving the activity fun and enjoyable.

UNIVERSITY OF BOHOL
PROFESSIONAL STUDIES

Activity # 3: FOCUS QUESTIONS ON PARAMETRIC TEST ….THE PEARSON PRODUCT

CORRELATION OF r & ANOVA
DATE SUBMITTED: November 17, 2021

A Research Activity submitted to

ENGR. BUENAVENTURADA D. LIBOT, PhD, EM, HRM, PA
As partial fulfillment of the requirements in
EM303 STATISTICS II
1st Semester: School Year 2021 – 2022

EUFE RHODA R. GALON

PhD. E M
 UNIVERSITY OF BOHOL
GRADUATE SCHOOL

STATISTICS II
FOCUS QUESTIONS
PARAMETRIC TEST
Nov. 15, 2021

Directions: Perform the following and show your solution using the formula and data
analysis. State the following:

a. Inferential question
b. Null Hypothesis (use 0.05 level of significance)
c. Conclusion

1. A study was made by a department store to determine the relationship between weekly
sales and advertising expenditures. The following data were recorded. Use 0.05 level of
significance.

Advertising Cost (in thousand pesos) Sales (in thousand pesos)

3.0 28.5
1.0 30.1
1.5 29.5
1.0 26.5
4.0 34.0
4.5 45.0
0.5 10.5
2.0 31.5
1.0 32.0
1.5 38

2. The data on rape cases committed from January to December in 3 cities in Metro Manila
 are as follows:

A City B City C City

January 2 1 6
February 3 6 5
March 5 7 5
April 4 8 8
May 6 3 9
June 7 5 8
July 8 2 9
August 4 9 10
September 5 8 9
October 2 7 8
November 5 3 5
December 4 6 5

ACTIVITY 3: ANSWERS & SOLUTIONS

1. A study was made by a department store to determine the relationship between weekly
sales and advertising expenditures. The following data were recorded. Use 0.05 level of
significance.
Advertising Cost (in thousand pesos) Sales (in thousand pesos)
3.0 28.5
1.0 30.1
1.5 29.5
1.0 26.5
4.0 34.0
4.5 45.0
0.5 10.5
2.0 31.5
1.0 32.0
1.5 38
a. Inferential Question:
Is there a significant difference on the relationship between the
weekly sales and the advertising expenditures of a certain department store?
b. Null Hypothesis: (Use 0.05 level of significance)
Ho There is no significant difference on the relationship between the weekly
sales and advertising expenditures of a certain department store.
Level of Significance:
a = 0.05
df = n-2
= 10-2
= 8
r .05 = 0.632
Formula: The Pearson Product Moment Coeffient of Correlation, r
X Y X² Y² XY
3.0 28.5 9 812.25 85.5
1.0 30.1 1 906.01 30.1
1.5 29.5 2.25 870.25 44.25
1.0 26.5 1 702.25 26.5
4.0 34.0 16 1156 136
 4.5 45.0 20.25 2025 202.5
0.5 10.5 0.25 110.25 5.25
2.0 31.5 4 992.25 63
1.0 32.0 1 1024 32
1.5 38 2.25 1444 57
20 305.6 57 10042.26 682.1
∑X= 20 ∑X=305.6 ∑X²=57 ∑Y²=10042.26 ∑XY= 682.10
r= n ∑XY - ∑X ∑Y  
  √ [ n ∑X² - (∑X)² ] [ n ∑Y² - (∑Y)² ]
= 10 (682.1) - (20)(305.6)  
  √ [10(57) - (20)²] [10(10042.26) - (305.6)²]
= 6821 - 6112    
  √ [ 570 - 400 ] [ 100422.6 - 93391.36 ]
= 709    
  √ [ 170 ] [ 7031.24 ]  
= 709    
  √ 1195310.8    
= 709    
  1093.3    
r= 0.648    
Decision Rule: If the computed value is greater than or beyond the critical value,
Reject Ho.
c. Conclusion:
The computed r value of 0.648 is greater than the critical value of .632 at .05 level of
significance with 8 degrees of freedom, so the null hypothesis is rejected.
This means that there is a significant relationship between the weekly sales and
advertising expenditures of a certain department store. Since the value of r is
positive, it implies that the higher the advertising cost, the higher os its weekly sales.
Likewise, the lower the advertising cost, the lower also are the weekly sales.
When checking the Coefficient of Determination to explain the extent of the influence of
the advertising cost to its weekly sales this is the result.
r= 0.648
CD= r² x 100%
= (.648)² x 100%
= .4199 x 100%
= 41.99% or .42
This 41.99% indicates that the weekly sales dependency has only below 50% of
chances that can be predicted through its advertising cost. Thus there is only a
medium level of fit between the advertisement cost and its weekly sales. This means
that the dependency of its weekly sales is not as strong as it is in its advertisement
cost. Therefore – the prediction of its sales has only a medium level of dependency
According to its advertisement cost. But this still proves that there is a significant relationship
Between the weekly sales and its
advertising cost.

Advertising Cost (in thousand pesos) Sales (in thousand pesos)

3.0 28.5

1.0 30.1

1.5 29.5

1.0 26.5

4.0 34.0
 4.5 45.0

0.5 10.5

2.0 31.5

1.0 32.0

1.5 38

Correlations on data analysis:

  Column 1 Column 2

Column 1 1

Column 2 0.648493778 1

Regression on Data Analysis:

SUMMARY OUTPUT

Regression Statistics

Multiple R 0.648493778

R Square 0.42054418

Adjusted R Square 0.348112202

Standard Error 1.109659235

Observations 10

X Variable 1 Line Fit Plot

6.0
4.0
Y
2.0 Predicted Y
Y

0.0
-2.0 5.0 10.0 15.0 20.0 25.0 30.0 35.0 40.0 45.0 50.0

X Variable 1

Normal Probability Plot

5
4
3
2
Y

1
0
0 10 20 30 40 50 60 70 80 90 100
Sample Percentile

ANOVA
  df SS MS F Significance F
Regression 1 7.149251057 7.149251057 5.806056858 0.042536327
Residual 8 9.850748943 1.231343618
Total 9 17      
  Coefficients Standard Error t Stat P-value Lower 95%
Intercept -1.08153896 1.326140082 -0.815554085 0.438360281 -4.139623472
X Variable 1 0.100835699 0.0418479 2.409576074 0.042536327 0.004334268

Upper 95% Lower 95.0% Upper 95.0%

1.976545552 -4.139623472 1.976545552
0.19733713 0.004334268 0.19733713
RESIDUAL OUTPUT

Standard
Observation Predicted Y Residuals Residuals
1 1.79227846 1.20772154 1.154392354
2 1.953615578 -0.953615578 -0.911506913
3 1.893114159 -0.393114159 -0.375755474
4 1.590607062 -0.590607062 -0.564527711
5 2.346874804 1.653125196 1.580128384
6 3.456067493 1.043932507 0.997835729
7 -0.022764121 0.522764121 0.499680501
8 2.094785557 -0.094785557 -0.090600125
9 2.145203407 -1.145203407 -1.094634824
10 2.7502176 -1.2502176 -1.195011922

PROBABILITY OUTPUT
Percentile Y
5 0.5
15 1
25 1
35 1
45 1.5
55 1.5
65 2
75 3
85 4
95 4.5

Directions: Perform the following and show your solution using the formula and data
analysis. State the following:
a. Inferential question
b. Null Hypothesis (use 0.05 level of significance)
c. Conclusion
2. The data on rape cases committed from January to December in 3 cities in Metro Manila
are as follows:
A City B City C City
January 2 1 6
February 3 6 5
March 5 7 5
April 4 8 8
May 6 3 9
June 7 5 8
July 8 2 9
August 4 9 10
September 5 8 9
 October 2 7 8
November 5 3 5
December 4 6 5

Formula: F-test one-way analysis of variance computation

X1 X1² X2 X2² X3 X3²
January 2 4 1 1 6 36
February 3 9 6 36 5 25
March 5 25 7 49 5 25
April 4 16 8 64 8 64
May 6 36 3 9 9 81
June 7 49 5 25 8 64
July 8 64 2 4 9 81
August 4 16 9 81 10 100
September 5 25 8 64 9 81
October 2 4 7 49 8 64
November 5 25 3 9 5 25
December 4 16 6 36 5 25
55 289 65 427 87 671
∑X1 = 55 ∑X1² = 289 ∑X2 = 65 ∑X2² = 427 ∑X3 = 87 ∑X3² = 671
N1 = 12 N1 = 12 N1 = 12
X͞1 = 4.58 X͞1 = 5.42 X͞1 = 7.25

CF = (∑X1 + ∑X2 + ∑X3)²

n1 + n2 +n3
= (55 + 65 + 87)²
12 + 12 + 12
= (207)²
36
= 42,849
36
CF = 1,190.25
TSS= ∑X1² + ∑X2² + ∑X3² - CF
= 289 + 427 + 671 - 1,190.25
= 1,387 - 1190.25
TSS= 196.75
BSS= (∑X1)² + (∑X2)² + (∑X3)² - CF
n1 n2 n3
= (55)² + (65)² +( 87)² - 1,190.25
12 12 12
= 3,025 + 4,225 + 7,569 - 1,190.25
12 12 12
= 252.083 + 352.083 + 630.75 - 1190.25
= 1,234.916 - 1190.25
BSS= 44.67
WSS= TSS - BSS
= 196.75 - 44.67
WSS= 152.08
F = (SSE1 – SSE2 / m) / SSE2 / n-k,
F= BSS / K-1
WSS /(N-1)(K-1)
= 44.67 / 2
152.08 / 33
= 22.335
 4.608
F= 4.84

Anova: Single Factor

SUMMARY

Groups Count Sum Average Variance

Column 1 12 55 4.583333 3.356061

Column 2 12 65 5.416667 6.810606

Column 3 12 87 7.25 3.659091

ANOVA
Source of
Variation SS df MS F P-value F crit

Between Groups 44.66667 2 22.33333 4.846027 0.014281 3.284918

Within Groups 152.0833 33 4.608586

Total 196.75 35        

Analysis of Variance Table

Sources of Variation Degrees of Sum of Mean F - Value

Freedom Squares Squares Computed Tabular

Between Groups 2 44.67 22.335 4.84 3.29

K-1

Within Group 33 152.08 4.608

(N-1) - (K-1)

Total N-1 35 196.75

a. Inferential Question:

Is there a significant difference on the number of rape cases committed

from January to December in the three cities of Metro Manila?

(Use 0.05 level of
b. Null Hypothesis: significance)

Ho There is no significant difference on the number of cases committed

from January to December in the three cities of Metro
Manila.

Level of Significance:

a = 0.05
2&
df = 33
 F Critical Value = 3.29

Decision Rule: If the F - computed value is greater than F-tabular value, Reject Ho.

c. Conclusion:

Since the F-computed value of 4.84 is greater than the F-tabular value of 3.29 at

0.05 level of significance with 2 and 33 degrees of freedom, the null hypothesis

is rejected in favor of the research hypothesis which means that there is a

significant difference in the number of rape cases committed from january to

December on the three cities of Metro Manila.

ACTIVITY 3: LEARNINGS & REFLECTION

This third activity is another new learnings for me. It made me compute the Pearson Product
Correlation of r and ANOVA. In this activity, I learned to determine whether there is a significant
relationship between its cost and its sales. It made me also predict on something based on the
relationship of the cost and its actual sales. It made me determine the influence of certain things over
other things.

I’ve done it through the traditional way of solving it, using the formula suggested in the given
notes. Then my answers can be validated through the result of the excel way in determining its
answer.

When answering this activity, although, I am already expose to the excel way of solving it, I still
have difficulty in making affirmation whether my solutions are right. So in doing this, I search and
read for a problem that somewhat similar with the given problem. So I would be at ease and with
confident that I am doing the right thing.

I do have a lot of reflections and realizations in this activity. This knowledge can help me in
managing the school I was assigned now.

How is this related to my work being a school head? It can really help me predict whether the
results of the pupils’ performance can be determined to the amount of expenses incurred in a certain
class activity. By making such prediction, it can make me save our school resources, if knowing that
some expenses on some curricular activities may have a positive effect to the pupils’ performance
and other facts.

It will also help me predict whether the strategies that teachers use is effective or not.

It is indeed very helpful to me, in managing teachers, pupils, parents, stakeholders and the
whole school.
 UNIVERSITY OF BOHOL
PROFESSIONAL STUDIES

Activity # 4: FOCUS QUESTIONS ON NON PARAMETRIC TEST …. CHI SQUARE, P-

VALUE, & KRUSKAL WALLIS TEST
DATE SUBMITTED: November 24, 2021

A Research Activity submitted to

ENGR. BUENAVENTURADA D. LIBOT, PhD, EM, HRM, PA
As partial fulfillment of the requirements in
EM303 STATISTICS II
1st Semester: School Year 2021 – 2022

EUFE RHODA R. GALON

PhD. E M

UNIVERSITY OF BOHOL
GRADUATE SCHOOL
 ACTIVITY 4: ANSWERS & SOLUTIONS

Solving Stepwise Method:

I. Problem:

Is there a significant relationship between the civil status and drinking habits?

II. Hypotheses:

Ho : There is no relationship between civil status and drinking habits.

or : Civil status is independent of drinking habits.

Ha : There is relationship between civil status and drinking habits.

or : Civil status is dependent of drinking habits.

III. Level of Significance:

a = 0.05

df = (c-1) (r-1)

= (3-1) (3-1)

= (2) (2)

= 4

X² .05 = 9.488 tabular value

IV. Statistics: Chi- Square Independence Test

X² - test of independence

V. Decision Rule:

If the X² computed value is greater than the X² tabular value, reject Ho.

VI. Conclusion:

The X² computed value of 21.99089 is greater than the X² tabular value of

9.488 at .05 level of significance with 4 degree of freedom. This leads to

the confirmation of the research hypothesis which means that there is a

significant relationship exists between civil status and drinking habits.

It implies that Married civil status has more numbers of non-drinkers,

moderate drinkers, and heavy drinkers than single and widowed.

Thus the civil status is dependent on its drinking habits. This means,

married drinks more, than single, and single drinks more than widowed.

Computation: through manual

Drinking Habits Single Married Widowed Total
 O E O E O E
Non-drinkers 29 35.09 74 63.525 18 22.385 121
Moderate
drinkers 32 42.34 75 76.65 39 27.01 146
Heavy drinkers 55 38.57 61 69.825 17 24.605 133
Total 116 210 74 400

For expected values: Multiply the column total to the row total and divide the product

by the grand total.

C1 E: (Single) =116 x 121 14,036 = 35.09

400 400

=116 x 146 16,936 = 42.34

400 400

=116 x 133 15,428 = 38.57

400 400

C2 E: (Married) =210 x 121 25,410 = 63.525

400 400

=210 x 146 30,660 = 76.65

400 400

=210 x 133 27,930 = 69.825

400 400

C3 E:(Widowed) 74 x 121 = 8,954 = 22.385

400 400

74 x 146 = 10,804 = 27.01

400 400

74 x 133 = 9,842 = 24.605

400 400

X² = ∑ (O-E)²

= (29-35.09)² + (32-42.34)² + (55-38.57)² + (74-63.525)² + (75-76.65)² + (61-69.825)²+ (18-22.385)²+ (39-27.01)²+ (17-24.605)²

35.09 42.34 38.57 63.525 76.65 69.825 22.385 27.01 24.605

(-
= (-6.09)²+ (-10.34)²+ (16.43)²+ (10.475)²+ (-1.65)²+ (-8.825)²+ (-4.385)²+ (11.99)²+ 7.605)²+

35.09 42.34 38.57 63.525 76.65 69.825 22.385 27.01 24.605

269.9449 143.7601
= 37.0881 + 106.9156 + + 109.7256 + 2.7225 + 77.8806 + 19.2282 + + 57.836
 35.09 42.34 38.57 63.525 76.65 69.825 22.385 27.01 24.605

= 1.0569 + 2.525 + 6.9988 + 1.72728 + 0.03551 + 1.1154 + 0.8589 + 5.3225 + 2.3506

X² = 21.991

Computation: through excell

Observe Data on Single Married Widowed Total

Drinking Habits

Non-drinkers 29 74 18 121

Moderate drinkers 32 75 39 146

Heavy drinkers 55 61 17 133

Total 116 210 74 400

Expected Data on Single Married Widowed Total

Drinking Habits

Non-drinkers 35.09 63.53 22.39 121

Moderate drinkers 42.34 76.65 27.01 146

Heavy drinkers 38.57 69.83 24.61 133

Total 116 116 116 400

Significance level
0.000201
P value 2 0.05

Degrees of Freedom 4

Chi-Square Value 21.991

Critical Value 9.488

I. Problem:
Is there a significant relationship between the civil status and drinking habits?
II. Hypotheses:
Ho : There is no relationship between civil status and drinking habits.
or : Civil status is independent of drinking habits.
Ha : There is relationship between civil status and drinking habits.
or : Civil status is dependent of drinking habits.
III. Level of Significance:
a = 0.05
df = (c-1) (r-1)
= (3-1) (3-1)
= (2) (2)
= 4
X² .05 = 9.488 tabular value
The decision rules for rejecting Ho in the p-value method are:
If the p-value is less than the alpha (significance) level then reject the null hypothesis.
If the p-value is greater than the alpha (significance) level then do not reject the null hypothesis.
Since our p-value here is lesser than the significance value, then our decision is reject the null hypothesis.

The decision rule is: If the X² computed value is greater than the X² critical value, reject Ho.
Since our X² computed value is greater than the X² critical value, reject Ho.      

From the above data, with the p-value of 0.0002012 which is lesser than its significance level of 0.05,
and the computed chi square value of 21.991 which is greater than the critical value of 9.488,
the null hypothesis is rejected and thereby accepting the alternate hypothesis. This implies that
there is a significant relationship between the civil status and their drinking habits.
It is therefore proven that the drinking habits is dependent on its civil status.

2. Two judges of a town fiesta parade ranked 10 floats in the following order.
Judge X Judge Y
5 7
8 5
9 10
10 9
4 4
3 2
6 8
2 1
7 6
1 3
Use rѕ at0.05 level of significance to test if there is a significant correlation in the
ranking of two judges.
Solving Using Stepwise Method:
I. Problem:
Is there a significant relationship between the opinion of two judges on the rank
of the 10 floats in a town fiesta parade?
or: Is there a significant correlation in the ranking of two judges?
II. Hypotheses:
Ho: The two judges differ most in their opinions on the rank of the 10 floats in
the fiesta parade.
or: There is no correlation in the ranking of two judges.
H1: The two judges do not differ most in their opinions on the rank of the 10
floats in the fiesta parade.
or: There is a correlation in the ranking of two judges.
III. Level of Significance:
a = .05
df= n-1
= 10-1
=9
rs = .600
IV. Statistics:
rs Spearman Rank Order Coefficient of Correlation
Computation:
Judge A Judge B D D²
5 7 -2 4
8 5 3 9
9 10 -1 1
10 9 1 1
4 4 0 0
3 2 1 1
 6 8 -2 4
2 1 1 1
7 6 1 1
1 3 -2 4
26
∑D² = 26
Where:
rs = 1 - 6 ∑ D² rs = Spearman Rank Order Coefficient Correlation
Sum of the squares of the difference between rank x
n-(n²-1) ∑ D² = and rank y
n = sample size
6 = constant

rs = 1 - 6 ∑ D²
n-(n²-1)
rs = 1- 6 (26)
10 (10²-1)
= 1 - 156
…..990
= 0.15758
rs = 0.842
V. Decision Rule:
If rs computed value is greater than rs tabular value, reject Ho.
VI. Conclusion:
Since the rs computed value of 0.842 is greater than rs tabular value of .600
at .05 level of significance, with a degree of freedom of 9, the null hypothesis
is rejected. This means that the alternate hypothesis is accepted. This implies
that there is a correlation in the ranking of two judges and that the two
judges do not differ in their opinions on the ranking of 10 floats in the fiesta
parade.

Excell Computation:
Judge A Judge B Rank Judge A Rank Judge B
5 7 5 7
8 5 8 5
9 10 9 10
10 9 10 9
4 4 4 4
3 2 3 2
6 8 6 8
2 1 2 1
7 6 7 6
1 3 1 3
I. Problem:
Is there a significant relationship between the opinion of two judges on the rank
of the 10 floats in a town fiesta parade?
or: Is there a significant correlation in the ranking of two judges?
II. Hypotheses:
Ho: The two judges differ most in their opinions on the rank of the 10 floats in
the fiesta parade.
or: There is no correlation in the ranking of two judges.
H1: The two judges do not differ most in their opinions on the rank of the 10
floats in the fiesta parade.
or: There is a correlation in the ranking of two judges.
 Coefficient
(rs): 0.842424242

N: 10

T statistics: t = rs x √ n-2

√1 - r s²

4.422179103

DF: 8

p value: 0.002220031

significance level= 0.05

rs @ .05 = 0.643

The above data shows:

significant positive correlation

Decision Rule: When p value is greater than .05 level of significance,
Reject the Null Hypothesis.
When the computed rs is greater than the rs critical value
Reject the null hypothesis and accept the alternate hypothesis
Conclusion: This means there is a significant positive correlation between the ranking of Judge A and
Judge B.

3. Random sample of 3 brands of cigarettes were tested for the tar content. The following

figures show the milligrams of tar found in the 15 cigarettes tested.

Brand A Brand B Brand C

16 17 11

15 18 12

17 19 9

14 20 10

13 21 11

Use the Kruskal-Wallis test.

Formula: H = 12 ∑ Ri² - 3 (n+1)

n (n+1)
ni

Where:

H = Kruskal Wallis test

n = the number of observation

12 = constant

3 = constant
 Brand A Rank of Brand A Brand B Rank of Brand B Brand C Rank of Brand C

16 9 17 10.5 11 3.5

15 8 18 12 12 5

17 10.5 19 13 9 1

14 7 20 14 10 2

13 6 21 15 11 3.5

40.5 64.5 15

n1 = 5 ∑R₁ = 40.5 n1 = 5 ∑R₂ = 64.5 n1 = 5 ∑R₃ = 15

Arrange the data jointly from the lowest to the highest then rank them.

Number Observation Rank

1 9 1

2 10 2

3 11 3.5

4 11 3.5

5 12 5

6 13 6

7 14 7

8 15 8

9 16 9

10 17 10.5

11 17 10.5

12 18 12

13 19 13

14 20 14

15 21 15

Solving the Stepwise Method:

I. Problem: Are there significant difference in the milligrams of tar content found in the three

brands of 15 cigarettes tested?

II. Hypotheses: Ho: There are no significant difference in the milligrams of tar content found in
 the three brands of 15 cigarettes tested.

H1: There are significant difference in the milligrams of tar content found in

the three brands of 15 cigarettes tested.

III. Level of Significance:

a= 0.05

df= h-1

= 3-1

= 2

X².05 = 5.991

IV. Statistics: H Test

Computation:

H= 12 ∑ Ri² - 3 (n+1)

n (n+1) ni

= 12 [(40.5)² + (64.5)² + (15)² ] - 3(15+1)

15 (15+1) 5 5 5

= 12 [(1,640.25) + (4,160.25) + (225)] - 3 (16)

240 5 5 5

= 12 [(328.05) + (832.05) + (45)] - 48

240

= 12 (1205.1) - 48

240

= 0.05 (1,205.1) - 48

= 60.255 - 48

H= 12.255

V. Decision Rule: If the H-computed value is greater than the X² tabular value, reject Ho.

VI. Conclusion: Since the H-computed value of 12.255 is greater than the X² tabular value of 5.991

at .05 level of significance with 2 degrees of freedom, the research hypothesis is

 accepted. This means that there is a significant difference in the number of

milligrams content of tar in the three brands of 15 cigarettes tested. It can also

be concluded that the three cigarette brands have different milligrams of tar content

in the 15 cigarettes tested.

COMPUTATION THROUGH EXCELL:

Brand A Brand B Brand C BRAND TAR CONTENT RANK

16 17 11 Brand A 16 9

15 18 12 Brand A 15 8

17 19 9 Brand A 17 10.5

14 20 10 Brand A 14 7

13 21 11 Brand A 13 6

Brand B 17 10.5

Brand B 18 12

Brand B 19 13

Brand B 20 14

Brand B 21 15

Brand C 11 3.5

Brand C 12 5

Brand C 9 1

Brand C 10 2

Brand C 11 3.5

Sum of
Row Labels RANK
Brand A 40.5
Brand B 64.5
Brand C 15
Grand Total 120

K= 3

N1 5
N2 5
N3 5

NT 15 k
H = [12 ∑ Ri² ]- 3 (nt+1)
 nt (nt+1) i=1
Part 1 0.050000 ni

Part 2
R-square(n1) 1640.25 k= number of populations
R-square(n2) 4160.25
R-square(n3) 225 ni= the number of populations in sample i
k
R-square(n1)/n1 328.05 nt= ∑ ni the total number of samples in all distribution
R-square(n2)/n2 832.05 i=1
R-square(n3)/n3 45
1205.1 Ri= the sum of the ranks of sample i
 
Part 3 48

H 12.255
chi-square 5.991464547
p-value 0.002182029

Reject Null? Reject Null

Inferential Question: Is there a significant difference on the tar contents of the three brands of cigarettes?
Null Hypothesis: There is no a significant difference on the tar contents of the three brands of cigarettes.
As shown in the above data, an H value of 12.255 and a probability of 0.00218, the null hypothesis was rejected
and found to be significant at 0.05 level. This implies that there is a significant difference on the tar contents
of the three brands of
cigarettes.

On this side here, is a result of another trial and error. From

other source of computation.
Although the result is different with the other, it is still have the
same decision
and that is to reject the null hypothesis.

Rank of Rank of
Brand A Brand A Brand B Brand B Brand C

16 9 17 10.5 11
15 8 18 12 12
17 10.5 19 13 9
14 7 20 14 10
13 6 21 15 11
40.5 64.5
n1 = 5 ∑R₁ = 40.5 n1 = 5 ∑R₂ = 64.5 n1 = 5

Computation through excell: Kruskall Wallis H Test

Determine the ranks (use average ranks in case of

Step 1: ties)
Step 2: Determine the overall average rank.
 ravg 8
Step 3: Determine the number of cases in each category
Determine the average rank per category and
Square the difference with the overall average rank,
then multiply by the number of cases in the category.

Category ni ravg ni (ravg-ravg)²

1 5 8.1 0.05
2 5 12.9 120.05
3 5 3 125
Total 15

Step 4: Sum up the last column.

245.1  

For each rank subtract the overall rank average and square the
Step5: result
see column R

Step 6: Sum up the result of step 5.

279
Step 7: Determine the H value statistics
  12.2989247

UDF 12.2989247
=kruskalwallis($Q$3:$Q$17;$R$3:$R$17;1)

Step 8: Determine the degrees of freedom

df = number of categories - 1
  2

UDF 2

=kruskalwallis($Q$3:$Q$17;$R$3:$R$17;2)
Use the chi square distribution to determine the p
Step 9: value

Sig.=p= 0.00213463 ChiDist

0.00213463 CHISQ.DIST.RT
0.00213463 CHISQ.DIST

UDF 0.00213463
=kruskalwallis($Q$3:$Q$17;$R$3:$R$17)

X Y ri (ri - ravg²)
1 16 9 1
1 15 8 0
1 17 10.5 6.25
1 14 7 1
1 13 6 4
2 17 10.5 6.25
2 18 12 16
 2 19 13 25
2 20 14 36
2 21 15 49
3 11 3.5 20.25
3 12 5 9
3 9 1 49
3 10 2 36
3 11 3.5 20.25

ACTIVITY 4: LEARNINGS & REFLECTION

This fourth activity is another new learnings for me. It made me compute the chi square, p-
value and kruskal wallis test.

This non-parametric test made me learned on how to interpret things based on their status and
drinking habits, the correlations of the judgment of the two judges and the tar content of each brands
of cigarettes.

Although in the problem, this uses other things, I can be use in the field of education.

Specifically, studying the relationship between the status and their drinking habit could also be
change into the analysis of the teachers performance based on their salary grade, or others. The
second one is about the significant and the correlations of things. Like the ratings of each teacher,
made by the school head or the master teacher. Is there a significant relationship between the two
raters? And so on….
 I would say, in the totality of these activities, it gave me a background knowledge and
confidence to analyze and interpret the simple survey implemented by deped in our school.

It also encourages me to apply, my learnings through interpreting the significance relationship

between the ratings made by our pupils, parents and stakeholders as to the services rendered by the
teachers, the administrator, and the whole school.

The analysis and the interpretation made me the basis on making interventions and plans for
improvement. It is indeed a great help for me, as a school head knowing these things. Analyzing and
interpreting the data I’ve got here in school and serve as my basis in the formulation of next stpes like
planning for interevention and improvement program of the whole school.