You are on page 1of 56

SUBMITTED TO : DR.

JINAL PARIKH

Marketing Research
On OBESITY

Group 2 (Section B):


Kunjal Desai (B12)
Heer Erda (B17)
Jyoti Gurnani (B24)
Table of Contents
Rajit Joshi (B29)
Mohit Parihar (B45)
Rutu Patel (B48)
Executive Summary________________________________________________________
(2)
Problem Definition________________________________________________________ (3)
Approach to the problem____________________________________________________ (4)
Research Design__________________________________________________________ (5)
Data Analysis_____________________________________________________________ (6)
Results_________________________________________________________________ (56)
Limitations______________________________________________________________ (57)
Conclusions& Recommendations____________________________________________ (58)

Bibliography & References_________________________________________________ (59)


Annexure_______________________________________________________________ (60)

Executive Summary
Obesity is the major health problem in developing and developed countries. There are many
books presenting the analysis of trends in obesity on individual level and population data. As
a part of our marketing research project, we have selected this topic for the better
understanding of increasing rate of obesity in the todays generation.
The main purpose of this research is to find obesity in the current generation in India, and to
analyse the food habits and physical activities done by them. The research took place in a
span of 1 month. Firstly we collected secondary data and after that a questionnaire was
prepared considering all the questions which we want to analyse to reach the primary
objective.
Sample size is 323. After preparing the questionnaire a pilot survey was carried out and after
altering the questionnaire it was floated to more than 500 people all over India to meet the
sample size of 323.
1

The questionnaire was drafted keeping in mind the theoretical framework of a research
design.
After collecting the responses the analysis was done in SPSS. Firstly the data was classified
and coded in Excel as per the requirement of SPPS software and then we came out with the
inferences for our objective with the help of demographic attributes.

Problem Definition
We all are aware that India battles malnutrition. The country has developed another
nutritional problemobesity. In past 10 years, the number of obese people has doubled in the
country - according to the National Family Health Survey (NFHS-4).
As per the survey conducted by Ministry of Health and Family Welfare (MoHFW),
people having Body Mass Index (BMI) more than 25 kilogram per metre square have been
considered as obese. There were 20 million obese women in India in 2014 compared with 9.8
million obese men, according to a study published in the British medical journal, the Lancet.
India is the third most obese country worldwide. India is just behind US and China in the
global hazard list of top 10 countries with highest number of obese people.
Obesity doesnt rest just by increasing weight. But it invites many other diseases
along with itself. There are more than 30 medical conditions that are associated with obesity.
Persons who are obese are at risk of developing one or more of these serious medical
2

conditions, causing poor health or, in severe cases, early death. Diabetes, high blood pressure,
high cholesterol, heart disease is few of the long lists of diseases.
To fight this problem, people should be aware regarding cause of obesity. Obesity is
generally caused by eating too much and moving too little. There are many reasons that cause
obesity. Poor diet, lack of physical activity, consuming too much calories, genetics etc. are
some of them. People should adopt or change their lifestyle keeping these reasons in mind.

Approach to the Problem


Lifestyle is essential in fighting obesity. How people eat, when they eat, what they eat etc. are
some important questions for obesity. Here we focused more on lifestyle of people.
Initially we analysed some secondary data. Certain studies done for obesity done are National
Family Health Survey, Ministry of Health and Family Welfare (MoHFW), British medical
journal The Lancet studied the status of obesity in India. Also to understand the reasons of
obesity we used studies of medical organizations.
We designed a questionnaire keeping in mind the demographic questions that are Gender,
Age Group and Occupation. With Lifestyle we also wanted to specifically analyse the data
Age Group, Gender and Occupation wise. We drafted the questions in an open ended way
keeping in mind Nominal Scale, Ordinal Scale and Likert Scale. Questions were focused to
know the eating habits of people, to know their daily routine chart and their awareness about
Obesity.

After the questionnaire was formed we went for a pilot testing. Pilot testing resulted in some
changes and after altering the questionnaire we floated it to more than 500 Individuals. The
responses we got were 331 from which we deleted the incomplete questionnaires and
finalized 323 Responses as required.
Issues like eating pattern, fast food and soft drink consumption, physical activity, exercise
etc. are covered in our questionnaire.
After collecting the responses, we analysed the collected data using software SPSS by Chi
Square, Factor Analysis and Determinant Analysis

Research Design
After collecting secondary data from:
o
o
o
o

All India Association for Advancing Research in Obesity


Obesity Foundation India
CSE India
ICMR

We thought of following Descriptive Research (quantitative method) for emphasizing on our


Primary Objective i.e. to study increasing level of Obesity among Youth in India. The main
idea behind using this research was to define an opinion, attitude and behavior of youth for
obesity among them in India.
This research was designed keeping in mind the obesity affecting factors that are Physical
activity, Eating habits, Motivation affects, Genetic, Environment and behavior. The
questionnaire mostly included Nominal Scale questions and was open ended. After the
4

questions were designed a pilot survey was carried out and gaps in the questionnaire were
found.
After knowing the gaps the questionnaire was altered and circulated to more than 500 people
to meet the sample size of 323 responses.
The demographic factors that are Gender, Age Group and Occupation were considered to
perform the analysis by various functions in SPSS.
The Analysis is done by:
o Chi Square
o Factor Analysis
o Discriminant Analysis

Data Analysis
Hypothesis:
1. There is no relationship between Gender and people carrying lunchbox to the
college/workplace.
There is a relationship between Gender and people carrying lunchbox to the
college/workplace.

Carry_Lunch_Box * Gender

Carry_Lunch_Box

Case Processing Summary


Cases
Valid
Missing
N
Percent
N
Percent
323
100.0%
0
0.0%

Total
Percent
323
100.0%

Carry_Lunch_Box * Gender Crosstabulation


Gender
Male
Female
Yes
Count
75
99

Total
174

No

Sometimes

Total

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear
Association
N of Valid Cases

Expected Count
% within Carry_Lunch_Box
% within Gender
% of Total
Count
Expected Count
% within Carry_Lunch_Box
% within Gender
% of Total
Count
Expected Count
% within Carry_Lunch_Box
% within Gender
% of Total
Count
Expected Count
% within Carry_Lunch_Box
% within Gender
% of Total

Value
20.878a
21.188

Chi-Square Tests
df
2
2

16.094

95.3
43.1%
42.4%
23.2%
65
51.5
69.1%
36.7%
20.1%
37
30.1
67.3%
20.9%
11.5%
177
177.0
54.8%
100.0%
54.8%

78.7
56.9%
67.8%
30.7%
29
42.5
30.9%
19.9%
9.0%
18
24.9
32.7%
12.3%
5.6%
146
146.0
45.2%
100.0%
45.2%

174.0
100.0%
53.9%
53.9%
94
94.0
100.0%
29.1%
29.1%
55
55.0
100.0%
17.0%
17.0%
323
323.0
100.0%
100.0%
100.0%

Asymp. Sig. (2-sided)


.000
.000

.000

323

a. 0 cells (0.0%) have expected count less than 5. The minimum expected count is 24.86.

Symmetric Measures
Value
Asymp. Std.
Error
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

-.224
-.239
323

Approx. Tb

Approx. Sig.

-4.110
-4.418

.000c
.000c

.053
.054

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors gender and people carrying lunchbox.


As per the crosstab maximum number of male and female carries their lunchbox to
the collage/workplace which is 42.4% and 67.8% of total respectively. Hence on an
average 53.9% people carry their lunchbox to the collage/workplace.
6

Analysis:
Chi-Square Test

Significance P = 0.00 > 0.05


o Reject Ho.
o Hence, there is anassociation between Gender and people carrying lunchbox to
the college/workplace.

Symmetric Measures

Value of P = 0.224 < 0.5


o Hence, there is low correlation between Gender and people carrying lunchbox
to the college/workplace.

Significance P = 0.00 < 0.05


o Reject Ho.
o Hence, there is a relationship between Gender and people carrying lunchbox to
the college/workplace.

2. There is no relationship between Gender and number of times people eat out in a
week.
There is a relationship between Gender and number of times people eat out in a
week.

Case Processing Summary


Cases
Valid
Missing
N
Percent
N
Percent
Times_you_eat_out *

323

Gender

100.0%

0.0%

Total
Percent
323

100.0%

Times_you_eat_out * Gender Crosstabulation

Times_you_eat_out

0-3

Count
Expected Count

Gender
Male
Female
73
115
103.0
85.0

Total
188
188.0

% within
Times_you_eat_out
% within Gender
% of Total
Count
Expected Count
% within

4-6

More than 6

Never

Total

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear

Times_you_eat_out
% within Gender
% of Total
Count
Expected Count
% within
Times_you_eat_out
% within Gender
% of Total
Count
Expected Count
% within
Times_you_eat_out
% within Gender
% of Total
Count
Expected Count
% within
Times_you_eat_out
% within Gender
% of Total

Chi-Square Tests
Df
3
3

Value
59.441a
65.363

38.8%

61.2%

100.0%

41.2%
22.6%
62
38.4

78.8%
35.6%
8
31.6

58.2%
58.2%
70
70.0

88.6%

11.4%

100.0%

35.0%
19.2%
24
16.4

5.5%
2.5%
6
13.6

21.7%
21.7%
30
30.0

80.0%

20.0%

100.0%

13.6%
7.4%
18
19.2

4.1%
1.9%
17
15.8

9.3%
9.3%
35
35.0

51.4%

48.6%

100.0%

10.2%
5.6%
177
177.0

11.6%
5.3%
146
146.0

10.8%
10.8%
323
323.0

54.8%

45.2%

100.0%

100.0%
54.8%

100.0%
45.2%

100.0%
100.0%

Asymp. Sig. (2-sided)


.000
.000

14.949
1
Association
N of Valid Cases
323
a. 0 cells (0.0%) have expected count less than 5. The minimum expected count is 13.56.

Symmetric Measures
Value
Asymp. Std.
Error
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

-.215
-.312
323

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

.000

Approx. Tb

Approx. Sig.

-3.953
-5.876

.000c
.000c

.056
.054

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors gender and Number of times people eat out.
As per the crosstab maximum numbers of male and female eat 0-3 times out in a week
which is 41.2% and 78.8% of total respectively. Hence on an average 58.2% people
eat 0-3 times out in a week.

Analysis:
Chi-Square Test

Significance P = 0.00 < 0.05


o Reject Ho.
o Hence, there is anassociation between Gender and number of times people eat
out in a week.

Symmetric Measures

Value of P = 0.215< 0.5


o Hence, there is low correlation between Gender and number of times people
eat out in a week.

Significance P = 0.00 < 0.05


o Reject Ho.
o Hence, there is a relationship between Gender and number of times people eat
out in a week.

3. There is no relationship between Gender and Type of food they eat.


There is a relationship between Gender and Type of food they eat.

Case Processing Summary


Cases
Valid
Missing
Percent
N
Percent

Total
Percent

Type_of_food * Gender

Type_of_food

Total

323

100.0%

0.0%

323

Type_of_food * Gender Crosstabulation


Gender
Male
Female
Count
138
107
Expected Count
134.3
110.7
Junk Food
% within Type_of_food
56.3%
43.7%
% within Gender
78.0%
73.3%
% of Total
42.7%
33.1%
Count
35
39
Expected Count
40.6
33.4
Natural food % within Type_of_food
47.3%
52.7%
% within Gender
19.8%
26.7%
% of Total
10.8%
12.1%
Count
4
0
Expected Count
2.2
1.8
Diet food
% within Type_of_food
100.0%
0.0%
% within Gender
2.3%
0.0%
% of Total
1.2%
0.0%
Count
177
146
Expected Count
177.0
146.0
% within Type_of_food
54.8%
45.2%
% within Gender
100.0%
100.0%
% of Total
54.8%
45.2%

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear

Chi-Square Tests
Df
2
2

Value
5.211a
6.715

100.0%

Total
245
245.0
100.0%
75.9%
75.9%
74
74.0
100.0%
22.9%
22.9%
4
4.0
100.0%
1.2%
1.2%
323
323.0
100.0%
100.0%
100.0%

Asymp. Sig. (2-sided)


.074
.035

.218
1
Association
N of Valid Cases
323
a. 2 cells (33.3%) have expected count less than 5. The minimum expected count is 1.81.
Symmetric Measures
Value
Asymp. Std.

.641

Approx. Tb

Approx. Sig.

.466
.848

.641c
.397c

Errora
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

.026
.047
323

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

10

.056
.056

According to case processing summary table we can say that we got 100% valid

response for the factors gender and type of food you eat.
As per the crosstab maximum number of male and female eats Junk food when they
go out which is 78.0% and 73.3% of total respectively. Hence on an average 75.9%
people eat Junk food when they go out.

Analysis:
Chi-Square Test

Significance P = 0.074 > 0.05


o Accept Ho.
o Hence, there is noassociation between Gender and Type of food they eat.

Symmetric Measures

Value of P = 0.026< 0.5


o Hence, there is low correlation between Gender and Type of food they eat.

Significance P = 0.641 > 0.05


o Accept Ho.
o Hence, there is no relationship between Gender and Type of food they eat.

4. There is no relationship between Gender and number of hours they sleep in a


day.
There is a relationship between Gender and number of hours they sleep in a day.

Hours_you_sleep * Gender

Case Processing Summary


Cases
Valid
Missing
N
Percent
N
Percent
323
100.0%
0
0.0%

Total
Percent
323
100.0%

Hours_you_sleep * Gender Crosstabulation


Gender

11

Total

Male
Count
Expected Count
% within Hours_you_sleep
% within Gender
% of Total
Count
Expected Count
% within Hours_you_sleep
% within Gender
% of Total
Count
Expected Count
% within Hours_you_sleep
% within Gender
% of Total
Count
Expected Count
% within Hours_you_sleep
% within Gender
% of Total

Less than 5 hours

Hours_you_sleep

5-8 Hours

9-11 hours

Total

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear

Chi-Square Tests
df
2
2

Value
4.978a
5.186

Female

11
8.2
73.3%
6.2%
3.4%
151
157.3
52.6%
85.3%
46.7%
15
11.5
71.4%
8.5%
4.6%
177
177.0
54.8%
100.0%
54.8%

4
6.8
26.7%
2.7%
1.2%
136
129.7
47.4%
93.2%
42.1%
6
9.5
28.6%
4.1%
1.9%
146
146.0
45.2%
100.0%
45.2%

Asymp. Sig. (2-sided)


.083
.075

.057
1
Association
N of Valid Cases
323
a. 0 cells (0.0%) have expected count less than 5. The minimum expected count is 6.78.

Symmetric Measures
Value
Asymp. Std.
Error
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

-.013
-.014
323

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

12

15
15.0
100.0%
4.6%
4.6%
287
287.0
100.0%
88.9%
88.9%
21
21.0
100.0%
6.5%
6.5%
323
323.0
100.0%
100.0%
100.0%

.812

Approx. Tb

Approx. Sig.

-.238
-.258

.812c
.796c

.054
.054

According to case processing summary table we can say that we got 100% valid

response for the factors gender and Hours of Sleep.


As per the crosstab maximum number of male and female sleep 5-8 hours in a day
which is 85.3% and 93.2% of total respectively. Hence on an average 88.9% people
sleep 5-8 hours.

Analysis:
Chi-Square Test

Significance P = 0.083 > 0.05


o Accept Ho.
o Hence, there is no association between Gender and Number of hours they
sleep in a day.

Symmetric Measures

Value of P = 0.013< 0.5


o Hence, there is low correlation between Gender and Number of hours they
sleep in a day.

Significance P = 0.812 > 0.05


o Accept Ho.
o Hence, there is no relationship between Gender and Number of hours they
sleep in a day.

13

5. There is no relationship between Gender and Engagement in exercise.


There is a relationship between Gender and Engagement in exercise.
Case Processing Summary
Cases
Valid
Missing
N
Percent
N
Percent
323
100.0%
0
0.0%

Exercise * Gender

Yes
Exercise
No

Total

Exercise * Gender Crosstabulation


Gender
Male
Female
Count
113
73
Expected Count
101.9
84.1
% within Exercise
60.8%
39.2%
% within Gender
63.8%
50.0%
% of Total
35.0%
22.6%
Count
64
73
Expected Count
75.1
61.9
% within Exercise
46.7%
53.3%
% within Gender
36.2%
50.0%
% of Total
19.8%
22.6%
Count
177
146
Expected Count
177.0
146.0
% within Exercise
54.8%
45.2%
% within Gender
100.0%
100.0%
% of Total
54.8%
45.2%

Total
186
186.0
100.0%
57.6%
57.6%
137
137.0
100.0%
42.4%
42.4%
323
323.0
100.0%
100.0%
100.0%

Chi-Square Tests
Df
Asymp. Sig. (2-

Value

Exact Sig. (2-

Exact Sig. (1-

sided)

sided)

sided)
Pearson Chi-Square
Continuity Correctionb
Likelihood Ratio
Fisher's Exact Test
Linear-by-Linear

6.276a
5.722
6.282

1
1
1

Total
Percent
323
100.0%

.012
.017
.012
.013

.008

6.257
1
.012
Association
N of Valid Cases
323
a. 0 cells (0.0%) have expected count less than 5. The minimum expected count is 61.93.
b. Computed only for a 2x2 table

Symmetric Measures
Value
Asymp. Std.

Approx. Tb

Approx. Sig.

2.522
2.522

.012c
.012c

Errora
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

.139
.139
323

14

.055
.055

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors gender and Engagement in exercise.


As per the crosstab maximum 63.8% male are engaged with any kind of exercise
where as 50% female are engaged and 50% are not engaged with any kind of exercise.
Hence on an average 57.6% are engaged with an exercise.

Analysis:
Chi-Square Test

Significance P = 0.012 < 0.05


o Reject Ho.
o Hence, there is no association between Gender and Engagement in exercise.

Symmetric Measures

Value of P = 0.139< 0.5


o Hence, there is low correlation between Gender and Engagement in exercise.

Significance P = 0.012 < 0.05


o Reject Ho.
o Hence, there is no relationship between Gender and Engagement in exercise.

6. There is no relationship between Age Group and people carrying lunchbox to the
college/workplace.
There is a relationship between Age Group and people carrying lunchbox to the
college/workplace.

15

N
Carry_Lunch_Box *

Case Processing Summary


Cases
Valid
Missing
Percent
N
Percent
323

Age_Group

100.0%

Total
N

0.0%

Percent
323

100.0%

Carry_Lunch_Box * Age_GroupCrosstabulation
Age_Group
15-20
Count
Yes

Carry_Lunch_Box

No

Sometimes

Total

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear Association
N of Valid Cases

21-25

Total

26-30

Above 30

10

140

17

174

Expected Count
% within Carry_Lunch_Box
% within Age_Group
% of Total
Count
Expected Count
% within Carry_Lunch_Box
% within Age_Group
% of Total
Count
Expected Count
% within Carry_Lunch_Box
% within Age_Group
% of Total
Count

8.6
5.7%
62.5%
3.1%
3
4.7
3.2%
18.8%
0.9%
3
2.7
5.5%
18.8%
0.9%
16

133.6
80.5%
56.5%
43.3%
64
72.2
68.1%
25.8%
19.8%
44
42.2
80.0%
17.7%
13.6%
248

21.0
4.0%
17.9%
2.2%
24
11.3
25.5%
61.5%
7.4%
8
6.6
14.5%
20.5%
2.5%
39

10.8
9.8%
85.0%
5.3%
3
5.8
3.2%
15.0%
0.9%
0
3.4
0.0%
0.0%
0.0%
20

174.0
100.0%
53.9%
53.9%
94
94.0
100.0%
29.1%
29.1%
55
55.0
100.0%
17.0%
17.0%
323

Expected Count
% within Carry_Lunch_Box
% within Age_Group
% of Total

16.0
5.0%
100.0%
5.0%

248.0
76.8%
100.0%
76.8%

39.0
12.1%
100.0%
12.1%

20.0
6.2%
100.0%
6.2%

323.0
100.0%
100.0%
100.0%

Value
34.234a
37.317
.110
323

Chi-Square Tests
Df
6
6
1

Asymp. Sig. (2-sided)


.000
.000
.740

a. 3 cells (25.0%) have expected count less than 5. The minimum expected count is 2.72.

Symmetric Measures
Value
Asymp. Std.
Error
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

-.019
.063
323

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

16

Approx. Tb

Approx. Sig.

.050
.054

-.332
1.127

.740c
.261c

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors age group and people carrying lunchbox.
As per the crosstab 62.5%, 56.5% and 85% people from age group of 15-20, 21-25
and above 30 respectively carries their lunchbox to the collage/workplace.Where as
61.5% people from age group of 26-30 did no carry their lunchbox. Hence on an
average 53.9% people carry their lunchbox to the collage/workplace.

Analysis:
Chi-Square Test

Significance P = 0.00 > 0.05


o Reject Ho.
o Hence, there is an association between Age group and people carrying
lunchbox to the college/workplace.

Symmetric Measures

Value of P = 0.019< 0.5


o Hence, there is low correlation between Age group and people carrying
lunchbox to the college/workplace.

Significance P = 0.740 > 0.05


o Accept Ho.
o Hence, there is no relationship between Age group and people carrying
lunchbox to the college/workplace.

7. There is no relationship between Age Group and number of times they eat out in
a week.
17

There is a relationship between Age Group and number of times they eat out in a
week.
Case Processing Summary
Cases
Valid
Missing
N
Percent
N
Percent
Times_you_eat_out *

323

Age_Group

100.0%

0.0%

Total
Percent
323

100.0%

Times_you_eat_out * Age_GroupCrosstabulation
15-20

0-3

4-6

Times_you_eat_out

More than 6

Never

Total

Count
Expected Count
% within

3
9.3

Age_Group
21-25
26-30 Above 30
158
19
8
144.3
22.7
11.6

Total
188
188.0

Times_you_eat_out
% within Age_Group
% of Total
Count
Expected Count
% within

1.6%

84.0%

10.1%

4.3%

100.0%

18.8%
0.9%
6
3.5

63.7%
48.9%
45
53.7

48.7%
5.9%
16
8.5

40.0%
2.5%
3
4.3

58.2%
58.2%
70
70.0

Times_you_eat_out
% within Age_Group
% of Total
Count
Expected Count
% within

8.6%

64.3%

22.9%

4.3%

100.0%

37.5%
1.9%
3
1.5

18.1%
13.9%
20
23.0

41.0%
5.0%
4
3.6

15.0%
0.9%
3
1.9

21.7%
21.7%
30
30.0

Times_you_eat_out
% within Age_Group
% of Total
Count
Expected Count
% within

10.0%

66.7%

13.3%

10.0%

100.0%

18.8%
0.9%
4
1.7

8.1%
6.2%
25
26.9

10.3%
1.2%
0
4.2

15.0%
0.9%
6
2.2

9.3%
9.3%
35
35.0

11.4%

71.4%

0.0%

17.1%

100.0%

25.0%
1.2%
16
16.0

10.1%
7.7%
248
248.0

0.0%
0.0%
39
39.0

30.0%
1.9%
20
20.0

10.8%
10.8%
323
323.0

5.0%

76.8%

12.1%

6.2%

100.0%

100.0%
5.0%

100.0%
76.8%

100.0%
12.1%

100.0%
6.2%

100.0%
100.0%

Times_you_eat_out
% within Age_Group
% of Total
Count
Expected Count
% within
Times_you_eat_out
% within Age_Group
% of Total

18

Chi-Square Tests
Df
9
9

Value
34.518a
35.340

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear

Asymp. Sig. (2-sided)


.000
.000

.524
1
Association
N of Valid Cases
323
a. 8 cells (50.0%) have expected count less than 5. The minimum expected count is 1.49.
Symmetric Measures
Value
Asymp. Std.
Error
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

.040
.013
323

.469

Approx. Tb

Approx. Sig.

.723
.241

.470c
.809c

.068
.061

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors Age group and Number of times people eat out.
As per the crosstab 37.5% people from age group of 15-20 eat 4-6 times out in a week
where as 63.7% from age group of 21-25, 48.7% from age group of 26-30 and 40.0%
from above 30 will eat 0-3 times in a week. Hence on an average 58.2% people eat 03 times out in a week.

Analysis:
Chi-Square Test

Significance P = 0.00 < 0.05


o Reject Ho.
o Hence, there is anassociation between Age group and number of times people
eat out in a week.

Symmetric Measures

Value of P = 0.040< 0.5

19

o Hence, there is low correlation between Gender and number of times people
eat out in a week.

Significance P = 0.470 > 0.05


o Accept Ho.
o Hence, there is no relationship between Age group and number of times
people eat out in a week.

8. There is no relationship between Age Group and type of food they eat.
There is a relationship between Age Group and type of food they eat.

Type_of_food * Age_Group

Case Processing Summary


Cases
Valid
Missing
N
Percent
N
Percent
323
100.0%
0
0.0%

Total
N
Percent
323
100.0%

Type_of_food * Age_GroupCrosstabulation
Age_Group
15-20
Count
Junk Food

Type_of_food

Natural food

Diet food

Total

Expected Count
% within Type_of_food
% within Age_Group
% of Total
Count
Expected Count
% within Type_of_food
% within Age_Group
% of Total
Count
Expected Count
% within Type_of_food
% within Age_Group
% of Total
Count
Expected Count
% within Type_of_food
% within Age_Group

20

21-25

Total

26-30

Above 30

13

184

31

17

245

12.1
5.3%
81.2%
4.0%
3
3.7
4.1%
18.8%
0.9%
0
.2
0.0%
0.0%
0.0%

188.1
75.1%
74.2%
57.0%
60
56.8
81.1%
24.2%
18.6%
4
3.1
100.0%
1.6%
1.2%

29.6
12.7%
79.5%
9.6%
8
8.9
10.8%
20.5%
2.5%
0
.5
0.0%
0.0%
0.0%

15.2
6.9%
85.0%
5.3%
3
4.6
4.1%
15.0%
0.9%
0
.2
0.0%
0.0%
0.0%

245.0
100.0%
75.9%
75.9%
74
74.0
100.0%
22.9%
22.9%
4
4.0
100.0%
1.2%
1.2%

16

248

39

20

323

16.0
5.0%
100.0%

248.0
76.8%
100.0%

39.0
12.1%
100.0%

20.0
6.2%
100.0%

323.0
100.0%
100.0%

% of Total

76.8%

Chi-Square Tests
Df
6
6

Value
2.593a
3.572

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear

5.0%

12.1%

6.2%

Asymp. Sig. (2-sided)


.858
.734

.946
1
Association
N of Valid Cases
323
a. 6 cells (50.0%) have expected count less than 5. The minimum expected count is .20.
Symmetric Measures
Value
Asymp. Std.
Error
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

-.054
-.044
323

100.0%

.331

Approx. Tb

Approx. Sig.

-.972
-.793

.332c
.428c

.046
.051

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors Age group and type of food you eat.
As per the crosstab 81.2% people from age group of 15-20, 74.2% people from age
group of 21-25, 79.5% people from age group of 26-30,75.9% people from above 30
eats Junk food when they go out. Hence on an average 75.9% people eat Junk food
when they go out.

Analysis:
Chi-Square Test

Significance P = 0.858 > 0.05


o Accept Ho.
o Hence, there is noassociation between Age group and Type of food they eat.

Symmetric Measures

Value of P = 0.054< 0.5


21

o Hence, there is low correlation between Age groupand Type of food they eat.

Significance P = 0.332 > 0.05


o Accept Ho.
o Hence, there is no relationship between Age groupand Type of food they eat.

9. There is no relationship between Age Group and hours of sleep in a day.


There is a relationship between Age Group and hours of sleep in a day.

Hours_you_sleep * Age_Group

Case Processing Summary


Cases
Valid
Missing
N
Percent
N
Percent
323
100.0%
0
0.0%

Total
N

Percent
100.0%

323

Hours_you_sleep * Age_GroupCrosstabulation
Age_Group
15-20
Count
Less than 5 hours

Hours_you_sleep

5-8 Hours

9-11 hours

Total

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear Association

21-25

Total

26-30

Above 30

15

Expected Count
% within Hours_you_sleep
% within Age_Group
% of Total
Count
Expected Count
% within Hours_you_sleep
% within Age_Group
% of Total
Count
Expected Count
% within Hours_you_sleep
% within Age_Group
% of Total
Count

.7
0.0%
0.0%
0.0%
16
14.2
5.6%
100.0%
5.0%
0
1.0
0.0%
0.0%
0.0%
16

11.5
26.7%
1.6%
1.2%
237
220.4
82.6%
95.6%
73.4%
7
16.1
33.3%
2.8%
2.2%
248

1.8
53.3%
20.5%
2.5%
23
34.7
8.0%
59.0%
7.1%
8
2.5
38.1%
20.5%
2.5%
39

.9
20.0%
15.0%
0.9%
11
17.8
3.8%
55.0%
3.4%
6
1.3
28.6%
30.0%
1.9%
20

15.0
100.0%
4.6%
4.6%
287
287.0
100.0%
88.9%
88.9%
21
21.0
100.0%
6.5%
6.5%
323

Expected Count
% within Hours_you_sleep
% within Age_Group
% of Total

16.0
5.0%
100.0%
5.0%

248.0
76.8%
100.0%
76.8%

39.0
12.1%
100.0%
12.1%

20.0
6.2%
100.0%
6.2%

323.0
100.0%
100.0%
100.0%

Value
74.360a
56.276
1.706

Chi-Square Tests
df
6
6
1

22

Asymp. Sig. (2-sided)


.000
.000
.192

N of Valid Cases

323

a. 6 cells (50.0%) have expected count less than 5. The minimum expected count is .74.

Symmetric Measures
Value
Asymp. Std.
Error
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

.073
.057
323

Approx. Tb

Approx. Sig.

.094
.093

1.307
1.016

.192c
.310c

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors Age group and Hours of Sleep.


As per the crosstab 100% people from age group of 15-20, 95.6% people from age
group of 21-25, 59.0% people from age group of 26-30 and 55.0% people from above
30 sleeps 5-8 hours in a day. Hence on an average 88.9% people sleep 5-8 hours.

Analysis:
Chi-Square Test

Significance P = 0.000 < 0.05


o Reject Ho.
o Hence, there is an association between Age group and Number of hours they
sleep in a day.

Symmetric Measures

Value of P = 0.073< 0.5


o Hence, there is low correlation between Age group and Number of hours they
sleep in a day.

Significance P = 0.192 > 0.05


o Accept Ho.

23

o Hence, there is no relationship between Age group and Number of hours they
sleep in a day.

10. There is no relationship between Age Group and awareness about the effects of
obesity.
There is a relationship between Age Group and awareness about the effects of
obesity.
Case Processing Summary
Cases
Valid
Missing
N
Percent
N
Percent
Aware_about_effects_of_ob
esity * Age_Group

323

100.0%

0.0%

Total
Percent
323

100.0%

Aware_about_effects_of_obesity * Age_GroupCrosstabulation
Age_Group
15-20
10
12.8

21-25
208
198.9

3.9%

80.3%

10.8%

5.0%

100.0%

62.5%
3.1%
6
3.2

83.9%
64.4%
40
49.1

71.8%
8.7%
11
7.7

65.0%
4.0%
7
4.0

80.2%
80.2%
64
64.0

9.4%

62.5%

17.2%

10.9%

100.0%

37.5%
1.9%
16

16.1%
12.4%
248

28.2%
3.4%
39

35.0%
2.2%
20

19.8%
19.8%
323

16.0

248.0

39.0

20.0

323.0

5.0%

76.8%

12.1%

6.2%

100.0%

obesity
% within Age_Group
100.0%
% of Total
5.0%
Chi-Square Tests

100.0%
76.8%

100.0%
12.1%

100.0%
6.2%

100.0%
100.0%

Count
Expected Count
% within
Yes

Aware_about_effects_of_
obesity
% within Age_Group
% of Total
Count
Expected Count
% within

Aware_about_effects_of_
obesity

No

Aware_about_effects_of_
obesity
% within Age_Group
% of Total
Count
Expected Count
% within

Total

Total

Aware_about_effects_of_

24

26-30
Above 30
28
13
31.3
16.0

259
259.0

Value
9.901a
8.986

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear

df

Asymp. Sig. (2-sided)


3
3

.019
.029

2.172
1
Association
N of Valid Cases
323
a. 2 cells (25.0%) have expected count less than 5. The minimum expected count is 3.17.

Symmetric Measures
Value
Asymp. Std.
Error
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

.082
.070
323

.141

Approx. Tb

Approx. Sig.

1.476
1.259

.141c
.209c

.067
.067

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors Age group and Awareness about the effect of obesity.
As per the crosstab 62.5% people from age group of 15-20, 83.9% people from age
group of 21-25, 71.8% people from age group of 26-30 and 65.0% people from above
30 are aware about the effect of obesity. Hence on an average 80.2% people are aware
about the effect of obesity.

Analysis:
Chi-Square Test

Significance P = 0.019< 0.05


o Reject Ho.
o Hence, there is an association between Age group and Awareness about the
effect of obesity.

Symmentric Measures

Value of P = 0.082< 0.5

25

o Hence, there is low correlation between Age group and Awareness about the
effect of obesity.

Significance P = 0.141> 0.05


o Accept Ho.
o Hence, there is no relationship between Age group and Awareness about the
effect of obesity.

11. There is no relationship between Occupation and number of times a person eats
out in a week
There is a relationship between Occupation and number of times a person eats
out in a week

N
Times_you_eat_out *

Case Processing Summary


Cases
Valid
Missing
Percent
N
Percent
323

Occupation

100.0%

Total
N

0.0%

Percent
323

100.0%

Times_you_eat_out * Occupation Crosstabulation


Occupation
Student

Total

Housewif Working Businessman


e

/Businesswo

Self
Employed

man
Times_you_eat_o

Count

ut

Expected Count
% within

0-3

4-6

Times_you_eat_out
% within Occupation
% of Total
Count
Expected Count
% within
Times_you_eat_out
% within Occupation
% of Total
Count
Expected Count

83

71

14

11

188

94.3

7.0

66.4

11.6

8.7

188.0

44.1%

4.8%

37.8%

7.4%

5.9%

100.0%

51.2%
25.7%
42
35.1

75.0%
2.8%
0
2.6

62.3%
22.0%
21
24.7

70.0%
4.3%
3
4.3

73.3%
3.4%
4
3.3

58.2%
58.2%
70
70.0

60.0%

0.0%

30.0%

4.3%

5.7%

100.0%

25.9%
13.0%
19
15.0

0.0%
0.0%
0
1.1

18.4%
6.5%
8
10.6

15.0%
0.9%
3
1.9

26.7%
1.2%
0
1.4

21.7%
21.7%
30
30.0

26

% within
More than
6

Never

Times_you_eat_out
% within Occupation
% of Total
Count
Expected Count
% within
Times_you_eat_out
% within Occupation
% of Total
Count
Expected Count
% within

Total

Times_you_eat_out
% within Occupation
% of Total

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear Association
N of Valid Cases

Value
19.547a
27.614
5.339
323

63.3%

0.0%

26.7%

10.0%

0.0%

100.0%

11.7%
5.9%
18
17.6

0.0%
0.0%
3
1.3

7.0%
2.5%
14
12.4

15.0%
0.9%
0
2.2

0.0%
0.0%
0
1.6

9.3%
9.3%
35
35.0

51.4%

8.6%

40.0%

0.0%

0.0%

100.0%

11.1%
5.6%
162

25.0%
0.9%
12

12.3%
4.3%
114

0.0%
0.0%
20

0.0%
0.0%
15

10.8%
10.8%
323

162.0

12.0

114.0

20.0

15.0

323.0

50.2%

3.7%

35.3%

6.2%

4.6%

100.0%

100.0%
50.2%

100.0%
3.7%

100.0%
35.3%

100.0%
6.2%

100.0%
4.6%

100.0%
100.0%

Chi-Square Tests
Df
12
12
1

Asymp. Sig. (2-sided)


.076
.006
.021

a. 9 cells (45.0%) have expected count less than 5. The minimum expected count is 1.11.

Symmetric Measures
Value
Asymp. Std.
Error
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

-.129
-.138
323

Approx. Tb

Approx. Sig.

.048
.053

-2.326
-2.490

.021c
.013c

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors Occupation and Number of time a person eat out.
As per the crosstab 51.2% students, 75.0% housewives, 62.3% working people,70.0%
businessman/ businesswomen and 73.3% self-employed people eats 0-3 times out in a
week. Hence on an average 58.2% people eat 0-3 time in a week.

Analysis:
27

Chi-Square Test

Significance P = 0.076 > 0.05


o Accept Ho.
o Hence, there is no association between Occupation and Number of time a
person eat out.

Symmetric Measures

Value of P = 0.129< 0.5


o Hence, there is low correlation between Occupation and Number of time a
person eat out.

Significance P = 0.021 < 0.05


o Reject Ho.
o Hence, there is a relationship between Occupation and Number of time a
person eat out.

12. There is no relationship between Occupation and motivation behind eating out
There is a relationship between Occupation and motivation behind eating out

Motivation * Occupation

Case Processing Summary


Cases
Valid
Missing
N
Percent
N
Percent
323
100.0%
0
0.0%

Total
Percent
323
100.0%

Motivation * Occupation Crosstabulation


Occupation
Student

Total

Housewif Working Businessman


e

/Businesswo

Self
Employed

man
Price

Count
Expected Count

4
4.0

28

0
.3

0
2.8

0
.5

4
.4

8
8.0

% within
Motivation
% within
Occupation
% of Total
Count
Expected Count
% within
Taste

Motivati
on

Away from
home

Motivation
% within
Occupation
% of Total
Count
Expected Count
% within
Motivation
% within
Occupation
% of Total
Count
Expected Count
% within

Other

Motivation
% within
Occupation
% of Total
Count
Expected Count
% within

Total

Motivation
% within
Occupation
% of Total

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear

Value
60.711a
46.491

50.0%

0.0%

0.0%

0.0%

50.0%

100.0%

2.5%

0.0%

0.0%

0.0%

26.7%

2.5%

1.2%
75
78.7

0.0%
4
5.8

0.0%
60
55.4

0.0%
7
9.7

1.2%
11
7.3

2.5%
157
157.0

47.8%

2.5%

38.2%

4.5%

7.0%

100.0%

46.3%

33.3%

52.6%

35.0%

73.3%

48.6%

23.2%
44
43.6

1.2%
3
3.2

18.6%
36
30.7

2.2%
4
5.4

3.4%
0
4.0

48.6%
87
87.0

50.6%

3.4%

41.4%

4.6%

0.0%

100.0%

27.2%

25.0%

31.6%

20.0%

0.0%

26.9%

13.6%
39
35.6

0.9%
5
2.6

11.1%
18
25.1

1.2%
9
4.4

0.0%
0
3.3

26.9%
71
71.0

54.9%

7.0%

25.4%

12.7%

0.0%

100.0%

24.1%

41.7%

15.8%

45.0%

0.0%

22.0%

12.1%
162

1.5%
12

5.6%
114

2.8%
20

0.0%
15

22.0%
323

162.0

12.0

114.0

20.0

15.0

323.0

50.2%

3.7%

35.3%

6.2%

4.6%

100.0%

100.0%

100.0%

100.0%

100.0%

100.0%

100.0%

50.2%

3.7%

35.3%

6.2%

4.6%

100.0%

Chi-Square Tests
Df
12
12

Asymp. Sig. (2-sided)

4.489
1
Association
N of Valid Cases
323
a. 10 cells (50.0%) have expected count less than 5. The minimum expected count is .30.

Symmetric Measures

29

.000
.000
.034

Value

Asymp. Std.

Approx. Tb

Approx. Sig.

-2.130
-1.584

.034c
.114c

Errora
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

-.118
-.088
323

.058
.058

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors Occupation and Motivation behind eating out.
As per the crosstab 46.3% students, 52.6% working people and 73.3% self-employed
people eat out for taste where as 41.7% housewives,45.0% businessman/
businesswomen eats out because of other reasons. Hence on an average 48.6% people
eat out for taste.

Analysis:
Chi-Square Test

Significance P = 0.00 < 0.05


o Reject Ho.
o Hence, there is an association between Occupation and Motivation behind
eating out.

Symmentric Measures

Value of P = 0.118< 0.5


o Hence, there is low correlation between Occupation and Motivation behind
eating out.

Significance P = 0.034 < 0.05


o Reject Ho.
o Hence, there is a relationship between Occupation and Motivation behind
eating out.
30

13. There is no relationship between Occupation and number of hours you sleep
There is a relationship between Occupation and number of hours you sleep

Case Processing Summary


Cases
Valid
Missing
N
Percent
N
Percent
Hours_you_sleep *
Occupation

323

100.0%

0.0%

Total
Percent
323

100.0%

Hours_you_sleep * Occupation Crosstabulation


Occupation

Total

Student Housewi Workin Businessma


fe

n/Business

Self
Employed

woman

Less than 5
hours

Hours_you_sl
eep

Count
Expected Count
% within
Hours_you_sleep
% within
Occupation
% of Total
Count
Expected Count
% within

5-8 Hours

Hours_you_sleep
% within
Occupation
% of Total
Count
Expected Count
% within

9-11 hours

Total

Hours_you_sleep
% within
Occupation
% of Total
Count
Expected Count

31

12
7.5

0
.6

3
5.3

0
.9

0
.7

15
15.0

80.0%

0.0%

20.0%

0.0%

0.0% 100.0%

7.4%

0.0%

2.6%

0.0%

0.0%

4.6%

3.7%
146
143.9

0.0%
12
10.7

0.9%
104
101.3

0.0%
14
17.8

0.0%
11
13.3

4.6%
287
287.0

50.9%

4.2%

36.2%

4.9%

3.8% 100.0%

90.1%

100.0%

91.2%

70.0%

73.3%

88.9%

45.2%
4
10.5

3.7%
0
.8

32.2%
7
7.4

4.3%
6
1.3

3.4%
4
1.0

88.9%
21
21.0

19.0%

0.0%

33.3%

28.6%

19.0% 100.0%

2.5%

0.0%

6.1%

30.0%

26.7%

6.5%

1.2%
162

0.0%
12

2.2%
114

1.9%
20

1.2%
15

6.5%
323

162.0

12.0

114.0

20.0

15.0

323.0

% within
Hours_you_sleep
% within
Occupation
% of Total

3.7%

100.0%
50.2%

35.3%

6.2%

4.6% 100.0%

100.0% 100.0%

100.0%

100.0% 100.0%

6.2%

4.6% 100.0%

3.7%

Chi-Square Tests
df
8
8

Value
38.539a
30.452

Pearson Chi-Square
Likelihood Ratio
Linear-by-Linear

50.2%

35.3%

Asymp. Sig. (2-sided)


.000
.000

22.985
1
Association
N of Valid Cases
323
a. 6 cells (40.0%) have expected count less than 5. The minimum expected count is .56.
Symmetric Measures
Value
Asymp. Std.
Error
Interval by Interval
Ordinal by Ordinal
N of Valid Cases

Pearson's R
Spearman Correlation

.267
.258
323

.000

Approx. Tb

Approx. Sig.

4.967
4.791

.000c
.000c

.053
.052

a. Not assuming the null hypothesis.


b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.

Inferences

According to case processing summary table we can say that we got 100% valid

response for the factors Occupation and Number of hours you sleep.
As per the crosstab 90.1% students, 100.0% housewives, 91.2% working people,
70.0% businessman/ businesswomen and 73.3% self-employed people sleep 5-8 hours
in a day. Hence on an average 88.9% people sleep 5-8 hours in a day.

Analysis:
Chi-Square Test

Significance P = 0.00 < 0.05


o Reject Ho.
o Hence, there is an association between Occupation and Number of hours you
sleep.

Symmentric Measures
32

Value of P = 0.267< 0.5


o Hence, there is low correlation between Occupation and Number of hours you
sleep.

Significance P = 0.00< 0.05


o Reject Ho.
o Hence, there is a relationship between Occupation and Number of hours you
sleep.

Discriminant Analysis
Taking Gender as a Grouping Variable and others as Independent

Analysis Case Processing Summary


Unweighted Cases
N
Valid
323
Excluded
Missing or out-of-range group
0
codes
At least one missing
0
discriminating variable

33

Percent
100.0
.0
.0

Both missing or out-of-range


group codes and at least one
missing discriminating variable
Total
Total

.0

0
323

.0
100.0

Group Statistics
Gender

Mean

Std. Deviation

Valid N (listwise)
Unweighted

Male

Female

Total

Weighted

Carry_Lunch_Box

1.7853

.76812

177

177.000

Times_you_eat_out

1.9266

.97714

177

177.000

Type_of_food

1.2429

.48002

177

177.000

Motivation

2.6497

.81283

177

177.000

Snack_before_bed

1.7232

.44870

177

177.000

Hours_you_sleep

2.0226

.38368

177

177.000

Aware_about_effects_of_obesity

1.2938

.45679

177

177.000

Obesity_run_in_your_family

1.8475

.36057

177

177.000

Exercise

1.3616

.48182

177

177.000

Carry_Lunch_Box

1.4452

.70497

146

146.000

Times_you_eat_out

1.4863

1.01870

146

146.000

Type_of_food

1.2671

.44398

146

146.000

Motivation

2.7260

.87510

146

146.000

Snack_before_bed

1.7603

.42839

146

146.000

Hours_you_sleep

2.0137

.26225

146

146.000

Aware_about_effects_of_obesity

1.0822

.27560

146

146.000

Obesity_run_in_your_family

1.8493

.35897

146

146.000

Exercise

1.5000

.50172

146

146.000

Carry_Lunch_Box

1.6316

.75830

323

323.000

Times_you_eat_out

1.7276

1.01850

323

323.000

Type_of_food

1.2539

.46352

323

323.000

Motivation

2.6842

.84108

323

323.000

Snack_before_bed

1.7399

.43935

323

323.000

Hours_you_sleep

2.0186

.33385

323

323.000

Aware_about_effects_of_obesity

1.1981

.39922

323

323.000

Obesity_run_in_your_family

1.8483

.35929

323

323.000

Exercise

1.4241

.49498

323

323.000

34

Carry_Lunch_Box
Times_you_eat_out
Type_of_food
Motivation
Snack_before_bed
Hours_you_sleep
Aware_about_effects_of_obesit

Tests of Equality of Group Means


Wilks' Lambda
F
df1
.950
16.888
.954
15.628
.999
.217
.998
.658
.998
.570
1.000
.057

y
Obesity_run_in_your_family
Exercise

Sig.
.000
.000
.641
.418
.451
.812

321

.000

1.000
.981

.002
6.361

1
1

321
321

.963
.012

Log Determinants
Gender
Rank
Log Determinant
Male
9
-12.070
Female
9
-14.286
Pooled within-groups
9
-12.262
The ranks and natural logarithms of determinants printed are
those of the group covariance matrices.

Test Results

321
321
321
321
321
321

24.087

Box's Test of Equality of Covariance Matrices

Approx.
df1
df2
Sig.

df2

.930

Analysis 1

Box's M

1
1
1
1
1
1

259.691
5.599
45
314290.009
.000

35

Tests null hypothesis of equal


population covariance matrices.

Summary of Canonical Discriminant Functions

Function

Eigenvalue

Eigenvalues
% of Variance
Cumulative %

1
.262a
100.0
100.0
a. First 1 canonical discriminant functions were used in the analysis.

Canonical
Correlation
.455

Wilks' Lambda
Test of Function(s)
Wilks' Lambda
Chi-square
Df
1
.793
73.537
9
Standardized Canonical Discriminant Function Coefficients
Function
1
Carry_Lunch_Box
Times_you_eat_out
Type_of_food
Motivation
Snack_before_bed
Hours_you_sleep
Aware_about_effects_of_obesit
y
Obesity_run_in_your_family
Exercise

Sig.
.000

.645
.564
-.132
-.258
.017
-.207
.599
-.240
-.444

Structure Matrix
Function
1
Aware_about_effects_of_obesit

.536
y
Carry_Lunch_Box
.448
Times_you_eat_out
.431
Exercise
-.275
Motivation
-.089
Snack_before_bed
-.082
Type_of_food
-.051
Hours_you_sleep
.026
Obesity_run_in_your_family
-.005
Pooled within-groups correlations between
discriminating variables and standardized
canonical discriminant functions
Variables ordered by absolute size of
correlation within function.

36

Canonical Discriminant Function


Coefficients

Carry_Lunch_Box
Times_you_eat_out
Type_of_food
Motivation
Snack_before_bed
Hours_you_sleep
Aware_about_effects_of_obesit

Function
1
.872
.566
-.285
-.306
.039
-.618

y
Obesity_run_in_your_family
Exercise
(Constant)
Unstandardized coefficients

1.554
-.666
-.905
.619

Functions at Group
Centroids
Gender
Function
1
Male
.463
Female
-.561
Unstandardized
canonical discriminant
functions evaluated at
group means

Classification Statistics
Classification Processing Summary
Processed

323
Missing or out-of-range group

Excluded

codes
At least one missing

discriminating variable
Used in Output

0
323

Classification Function Coefficients


Gender
Male
Female
Carry_Lunch_Box
1.093
.200
Times_you_eat_out
.399
-.181
Type_of_food
2.837
3.129
Motivation
5.037
5.351
Snack_before_bed
8.247
8.207
Hours_you_sleep
20.347
20.981
Aware_about_effects_of_obesit
3.874
2.282
y

37

Obesity_run_in_your_family
15.938
Exercise
6.642
(Constant)
-59.922
Fisher's linear discriminant functions

16.621
7.569
-60.606

Classification Resultsa
Gender
Predicted Group Membership
Male
Female
Male
115
62
Count
Female
40
106
Original
Male
65.0
35.0
%
Female
27.4
72.6
a. 68.4% of original grouped cases correctly classified.

Total
177
146
100.0
100.0

Analysis Case Processing Summary:

N = 323 it means that we have 100% data. No data is missing

Group Statistics:
Male:

Mean of Snack before bed = 1.7232 is negative on a scale of 1-2(Yes - No)


Mean of Aware about effects of obesity = 1.2938 is positive on a scale of 1-2(Yes -

No)
Mean of Engaged in any kind of exercise = 1.3616 is positive on a scale of 1-2(Yes -

No)
Mean of Obesity run in your family = 1.8475 is negative on a scale of 1-2(Yes - No)

Female:

Mean of Snack before bed = 1.7603 is negative on a scale of 1-2(Yes - No)


Mean of Aware about effects of obesity = 1.0822 is positive on a scale of 1-2(Yes -

No)
Mean of Engaged in any kind of exercise = 1.5000 is neutral on a scale of 1-2(Yes -

No)
Mean of Obesity run in your family = 1.8493 is negative on a scale of 1-2(Yes - No)

38

Test of Equality of Group Means:

In case of Group Means nearer the significant are to zero the variable is more
significant and farther the significant are to zero the variable is less significant.
More significant Variables are:
o Carry lunchbox 0.000
o Times you eat out 0.000
o Aware about effect of obesity 0.000
o Exercise 0.012

Pooled Within Group Matrix:

This Matrix shows correlation between two variables.


o Correlation between Carry Lunch Box and Times you eat is 0.065 < 0.5.
Hence we can say that there is low correlation between them which is good
because we are able to distinguish between them.
o Correlation between Carry Lunch Box and Type of food is 0.044 < 0.5. Hence
we can say that there is low correlation between them.
o Correlation between Carry Lunch Box and Motivation is 0.093 < 0.5. Hence
we can say that there is low correlation between them.
o Correlation between Carry Lunch Box and Snack before bed is 0.105 < 0.5.
Hence we can say that there is low correlation between them.
o Correlation between Carry Lunch Box and Hours you sleepis 0.088< 0.5.
Hence we can say that there is low correlation between them.
o Correlation between Carry Lunch Box and Aware about effect of obesity is
0.046< 0.5. Hence we can say that there is low correlation between them.
o Correlation between Carry Lunch Box and Obesity run in your family is 0.105
< 0.5. Hence we can say that there is low correlation between them.
o Correlation between Carry Lunch Box and Exerciseis 0.131< 0.5. Hence we

can say that there is low correlation between them.


Similar to carry lunch box, all other variables have low correlation with other
variables and hence we can say that Discriminant Analysis is appropriate technique
for our data.

Box's Test of Equality of Covariance Matrices


Test Results:
39

Sig = 0.000 More Significant


Reject Result.

Summary of Canonical Discriminant Functions


Eigenvalues:

Canonical Correlation = 0.455


Variance due to independent variable into dependent variable r2 = (0.455)2
= 0.207
= 20.7%
o It means that Power of an independent variable in making two groups is 20.7%
and it was is explained itself by variables.

Wilks Lambda:

This table shows that how powerful your analysis is in discriminating each other.
Here we have sig = 0.000 More significant
o It means that two groups are significantly different from each other.

Standardized Canonical Discriminant Function Coefficients:

This will give the variables that are important over the others.
Three variable that are considered to be important for analysis are:
o Carry Lunch Box: 0.645
o Aware about effect of obesity: 0.599
o Times you eat out: 0.564

Canonical Discriminant Function Coefficients:

D = a + b1x1 + b2x2 + b3x3 + b4x4 + b5x5 + b6x6 + b7x7 + b8x8 + b9x9


D = 0.619 + 0.872 CLB + 0.566 TYEO 0.285 TOF - 0.306 M + 0.039SBB 0.618
HYS + 1.554 AEO - 0.666 ORYF 0.905 E

Functions at Group Centroids:

Obesity in gender varies from 0.561 to 0.436 where group 1: o.436 is of Male and

group 2: - 0.561 is of female.


Here, the value of D helps in prediction.

40

o If value of D is Positive then male are more obese and if value of D is


negative then female are more obese.

Classification Statistics
Case Wise Statistics

This table gives details statistics of each respondent with the discriminant scores.

These scores are compared with the predicted Group.


For Case Number 1: The Predicted Group is 2 i.e. the respondent is a Female and the

discriminant score are negative i.e. -0.962, that means this respondent is not obese.
For Case Number 4: The Predicted Group is 1 i.e. the respondent is male and the

discriminant score are positive i.e. 0.721, that means this respondent is obese.
From the complete statistics out of 323 there are around 83 cases which have positive
discriminant scores and others have negative scores.

Classification Results

According to Analysis:
o Group 1: Male 65.0% cases are correctly classified and 35.0% cases are not
correctly classified.
o Group 2: Female 72.6% cases are correctly classified and 27.4% cases are

not correctly classified.


In total 68.4% cases are correctly classified and 31.6% cases are not correctly
classified.

41

Factor Analysis

Carry_Lunch_Box
Times_you_eat_out
Type_of_food
Motivation
Snack_before_bed
Hours_you_sleep
Aware_about_effects_of_obesity
Obesity_run_in_your_family
Exercise

Descriptive Statistics
Mean
Std. Deviation
1.6316
.75830
1.7276
1.01850
1.2539
.46352
2.6842
.84108
1.7399
.43935
2.0186
.33385
1.1981
.39922
1.8483
.35929
1.4241
.49498

KMO and Bartlett's Test


Kaiser-Meyer-Olkin Measure of Sampling Adequacy.
Approx. Chi-Square
Bartlett's Test of Sphericity
Df
Sig.

42

Analysis N
323
323
323
323
323
323
323
323
323

.537
167.849
36
.000

Communalities
Initial
Extraction
Carry_Lunch_Box
1.000
.726
Times_you_eat_out
1.000
.678
Type_of_food
1.000
.489
Motivation
1.000
.493
Snack_before_bed
1.000
.475
Hours_you_sleep
1.000
.633
Aware_about_effects_of_obesit
1.000
.557
y
Obesity_run_in_your_family
1.000
.684
Exercise
1.000
.539
Extraction Method: Principal Component Analysis.

Total Variance Explained


Component

Initial Eigenvalues
Total

Extraction Sums of Squared Loadings

% of

Cumulative

Variance

Total

% of

Cumulative

Variance

Rotation Sums of Squared Loadings


Total

% of

Cumulative

Variance

1.722

19.128

19.128

1.722

19.128

19.128

1.454

16.157

16.157

1.305

14.500

33.628

1.305

14.500

33.628

1.360

15.110

31.267

1.198

13.307

46.935

1.198

13.307

46.935

1.289

14.318

45.585

1.050

11.670

58.605

1.050

11.670

58.605

1.172

13.020

58.605

.994

11.045

69.649

.813

9.029

78.678

.719

7.987

86.665

.622

6.908

93.572

.578

6.428

100.000

Extraction Method: Principal Component Analysis.

43

Component Matrixa
Component
1
Carry_Lunch_Box
Times_you_eat_out
Type_of_food
Motivation
Snack_before_bed
Hours_you_sleep
Aware_about_effects_of_obesit

2
.070
.474
.553
.655
-.146
-.542

-.205
y
Obesity_run_in_your_family
.521
Exercise
-.359
Extraction Method: Principal Component Analysis.
a. 4 components extracted.

Carry_Lunch_Box
Times_you_eat_out
Type_of_food

.431
.528
.250
.101
-.255
.512

-.268
.099
.132
-.230
.609
.274

.681
-.404
-.321
-.042
-.133
-.057

.532

.464

.130

.013
.397

.412
-.464

.493
-.192

Rotated Component Matrixa


Component
1
2
3
-.086
.166
.139
.806
.156
-.056
.684
-.043
.118

44

4
.820
.012
-.072

Motivation
Snack_before_bed
Hours_you_sleep
Aware_about_effects_of_obesit

.521
-.127
-.084

-.372
.228
.748

.135
.295
-.256

.256
-.565
-.031

.728

.127

.059

.041
.157

.784
-.671

.202
.252

.087
y
Obesity_run_in_your_family
.163
Exercise
.007
Extraction Method: Principal Component Analysis.
Rotation Method: Varimax with Kaiser Normalization.
a. Rotation converged in 5 iterations.

Component Transformation Matrix


Component
1
2
3
1
.711
-.467
.497
2
.501
.675
-.246
3
.065
.564
.622
4
-.489
.086
.553
Extraction Method: Principal Component Analysis.

4
.170
.483
-.539
.669

Rotation Method: Varimax with Kaiser Normalization.

Component Score Coefficient Matrix


Component
1
2
3
Carry_Lunch_Box
-.138
.134
.158
Times_you_eat_out
.593
.158
-.124
Type_of_food
.481
.015
.012
Motivation
.316
-.238
.029
Snack_before_bed
-.063
.184
.252
Hours_you_sleep
.014
.536
-.141
Aware_about_effects_of_obesit
.084
.560
.149
y
Obesity_run_in_your_family
.013
.100
.621
Exercise
.068
.068
-.521
Extraction Method: Principal Component Analysis.
Rotation Method: Varimax with Kaiser Normalization.
Component Scores.

Component Score Covariance Matrix


Component
1
2
3
1
1.000
.000
.000
2
.000
1.000
.000
3
.000
.000
1.000
4
.000
.000
.000
Extraction Method: Principal Component Analysis.

4
.000
.000
.000
1.000

Rotation Method: Varimax with Kaiser Normalization.


Component Scores.

Analysis
Descriptive Statistics:

45

4
.721
-.060
-.117
.179
-.468
-.024
.051
.185
.198

Mean of Times you eat out = 1.7276


o Between 0-3 times to 4-6 times from never to more than 6 times
Mean of Snack before bed = 1.7399
o No from yes and no
Mean of Hours you sleep = 2.0186
o 5-8 hours from 0 to more than 11 hours
Mean of Aware about effects of obesity = 1.1981
o Yes from yes and no
Mean of Obesity run in your family = 1.8483
o No from yes and no
Mean of Exercise = 1.4241
o Neutral between yes and no

Here Analysis N shows number of responses on individual variables.

Correlation Matrix:

This matrix is used to club similar type of variables together.


From the table we can say that there are four factors required to show the variables
that are highly correlated to each other and that are,
o Factor 1 contains: Type of food, Motivation, Hours of Sleep and Obesity run
in you family
o Factor2 contains: Times you eat and Aware about effect of obesity
o Factor3 contains: Snack before bed and Exercise
o Factor4 contains: Carry Lunch box

KMO and Bartletts Test:

KMO Test:
o KMO Measure = o.537 > 0.5
o Here, KMO Measure is greater than 0.5 so we can go for the Factor Analysis.
Bartletts Test:
o Significance = o.oo
o Here the vale of significance indicates that we can apply Factor Analysis on
our data.

46

Communalities:
Initial: When the variable individually explained.

When each variable is explained individually, they are 100% similar.


Example: Carry Lunch Box = 1.00 = 100% alone.

Extraction: When the variable is explained with the other variables.

Carry Lunch Box = 0.726 = 72.6%


o Carry lunch box is 72.6% similar with Obesity and number of times you eat

out
Times you eat = 0.678 = 67.8%
o Number of times you eat out is 67.8% similar to Awareness about effect of

obesity
Type of food = 0.489 = 48.9%
o Type of food is 48.9% similar to the motivation, hours of sleep and obesity run

in your family
Motivation = 0.493 = 49.3%
o Motivation is 49.3% similar to the type of food, hours of sleep and obesity run

in your family
Snack before bed = 0.475 = 47.5%
o Snack before bed is 47.5% similar to Exercise and Awareness about the effect

of obesity
Hours of Sleep = 0.633 = 63.3%
o Hours of Sleep is 63.3% similar to Motivation, Type of food and obesity run in

your family
Aware about effect of obesity = 0.557 = 55.7%
o Aware about effect of obesity is 55.7% similar to times you eat out
Obesity run in your family = 0.684 = 68.4%
o Obesity run in your family is 68.4% similar to Type of food, Motivation and
hours of sleep
Exercise = 0.539 = 53.9%
o Exercise is 53.9% similar to Snack before bed

Total Variance Explained:

Here, Total 4 Factors have value > 1 which is 1.722, 1.305, 1.198 and 1.050 because
we grouped our variables in four factors.
o 1stFactorexplain 19.128% variance
o 2ndFactorexplain 14.500% variance
47

o 3rdFactorexplain 13.307% variance


o 4thFactorexplain 11.670% variance
The whole model explains 58.605% of data which is cumulative percentage of first

four factors.
Here in the table, Rotation Sums of Squared Loading gives the vale of only 4
Factorthat are 16.157%, 15.110%, 14.318% and 13.020% (Clubbing all 9 variable in 4
Factors )

Component Matrix:

This matrix will also give an idea that which variable can be clubbed.
Values > 0.5 under Component 1 are clubbed together.
o That are: Type of food, Motivation, Hours you sleep and Obesity run in
your family
Values > 0.5 under Component 2 are clubbed together.
o That are: Times you eat out, Hours you sleep and Aware about effect of
obesity
Values > 0.5 under Component 3 are clubbed together.
o That are: Snack before bad and exercise
Values > 0.5 under Component 4 are clubbed together.
o That are: Carry Lunchbox and Obesity run in your family

Rotated Component Matrix:

This matrix will give final idea of factor 1, factor 2,factor 3 and factor 4.
Factor 1: Value > 0.5 in component 1
o That are: Times you eat out, type of food and motivation
Factor 2: Value > 0.5 in component 2
o That are: Hours you sleep and Aware about effect of obesity
Factor 3: Value > 0.5 in component 3
o That are: Obesity run in your family and Exercise
Factor 4: Value > 0.5 in component 4
o That are: Carry Lunch box and Aware about effect of obesity

Results
48

The analysis is done by proving 13 Hypothesis, 1 Factor Analysis and Discriminant

Analysis with SPPS Output and Inferences.


Through Hypothesis Testing Comparing Gender with the other attributes as : people
carrying lunchbox to work place/college, times people out in a week, type of food
they eat, number of hours they sleep, there engagement in exercise it proves that only
2 out of 5variables have relationship or association with the demographic attribute
Gender. Where as in case of age group we found that there is no relationship between
age group and other variables. But in case of Hypothesis Testing of Occupation we
found that there is a relationship between Occupation and number of hours people

sleep, the motivation for eating out and number of times they eat out.
KMO and Barletts test value of significance proved that we can apply factor analysis
on our data. So considering Gender as a grouping variable and other as independent
we went forward with factor analysis. The analysis helps us to group all similar
variables into four groups. The result is as follows for the factors:
o 1st Factorexplain 19.128% variance
o 2nd Factorexplain 14.500% variance
o 3rd Factorexplain 13.307% variance
o 4th Factorexplain 11.670% variance

With the help of Discriminant Analysis that is done with considering Gender as an
independent variable and all other variables as a dependent variables we are able to
find out that in total 68.4% cases are correctly classified and 31.6% cases are not
correctly classified.

49

Limitations
The most important limitation for this research was lack of time. If we would have got more
time we would have been able to perform more functions of statistical tools and may have
come out with the same authentic answer by supporting more inferences.
Getting genuine answer from the respondent was another limitation. As some of the questions
were personal to the people who have obesity issues they might have just gave the answer for
the sake of filling the questionnaire. So deleting that kind of responses which we found that
were not answered genuinely was a task.
Lack of command on IBM SPSS.

50

Conclusions and Recommendations


Conclusion:
The conclusions made from the research are that all the factors dont prove the level of
obesity among an individual.
The following factors prove the level of obesity among the youth in India:

Engagement in any kind of exercise


Snacks before bed
Hours of sleep
Obesity in the family and
Occupation

Recommendations:
The respondents should concentrate on the physical activity and should not allow the
occupation affect their healthy living style to be away from obesity.

51

Bibliography and References


1. http://www.nhs.uk/Conditions/Obesity/Pages/Causes.aspx
2. http://www.nhlbi.nih.gov/health/health-topics/topics/obe/causes
3. http://obesityfoundationindia.com/about.htm
4. http://www.cseindia.org/userfiles/presentation_cse

52

Annexure
Primary Objective: To study increasing level of Obesity of Youth in India
Secondary Objective: To learn eating habits of Youth
1. Do you carry Lunch box to your college/workplace?
o Yes
o No
o Sometimes
2. How many times do you eat out in a week?
o
o
o
o

0-3
4-6
More than 6
Never

3. Which type of Food do you eat while you are out?


o Junk food (Pizza, Burger, Soft drinks etc.)
o Natural food (Salad, Juice etc.)
o Diet food (Low fat, High calorie)
4. Motivation behind eating out
o
o
o
o

Price
Taste
Away from Home
Other

5. Do you eat any snack before going to bed?


o Yes
o No
6. How many hours do you sleep in a day?
o
o
o
o

Less than 5 hours


5-8 hours
9-11 hours
More than 11 hours

7. Are you aware about adverse effects of obesity?


53

o Yes
o No
8. Does Obesity run in your family?
o Yes
o No
9. Are you engaged in any kind of exercise?
o Yes
o No
10. Gender
o Male
o Female
11. Age group
o
o
o
o

15-20
21-25
26-30
Above 30

12. Name: __________


13. Occupation
o
o
o
o
o

Student
Housewife
Working Professional
Businessman/Businesswoman
Self Employed

Sample Size Calculation


Primary Objective: To study increasing level of Obesity of Youth in India

Confidence Level 95% :

54

o Confidence level defines that we are 95% confident that population proportion
will fall under this confidence interval.

Estimated true proportion P: 0.7


o The value of P denotes that 70% people of sample are prompt to obesity.

Desired Precision e : 0.05


o A 5% error denotes that we are expecting 5% of difference in our sample
proportion.

Calculation:

Z^2 = (1.96) ^2 = 3.8416


P=0.7
Q= 0.3
e^2 = (0.05) ^2 = 0.0025
n= 322.69 = 323

55

You might also like