COMPARISON OF

EXPENDITURE ON
CIGARETTES AND
ALCOHOL
DECISION ANALYSIS
PROJECT

PROF. KRISHNA NIKUMBH

Group MembersParag Parmar 183
Anish Bhatnagar 142
Shrish Somani 159
Govan Mehta 176

Contents

INTRODUCTION
EXPENDITURE BY AGE GROUP 18-21
EXPENNDITURE BY AGE GROUP 21-25
RELATIONAL MEAN AND STANDARD
DEVIATION CALCULATION
Z-TEST AND CONCLUSION.

INTRODUCTION
This project is basically done to make a comparative
analysis between the weekly spending on alcohol and
cigarettes by the youth and how people in the age
bracket of 18-25 years are spending a major portion of
their pocket money or salaries on cigarettes and
alcohol. Also smoking is slowly becoming a lifestyle
habit of the youth all over India and everyday more and
more young people are taking to smoking and drinking.
For this study we have considered only the people
residing in the area Juhu and Andheri west for our
convenience.
Also, the age bracket of 18-25 because this is the age
group that we will have to target to reduce the
consumption of such carcinogenic products. Further we
have considered the expenditure into two segments:
18-21 years
21-25 years
This is done so as to compare whether there is more
instance of underage consumption of alcohol with
cigarettes or vice versa.
Research Problem: Rising consumption of cigarettes
and alcohol in the youth and ascertaining whether more
of underage youth is consuming the same or not.

(Comparison based on total monthly expenditure on

smoking and consuming alcohol)
Research Hypothesis: Weekly expenditure on alcohol
and cigarettes is more among the age group of 18-21.
For the purpose of testing our hypothesis we used the
Z-Test for difference in mean with 5% margin.

AGE GROUP 18 to 21
Weekly
Expenditure in Rs.
(X10)

Mid point
(x)

Frequency (f)

x2

fx

Fx2

0-400

200

40000

600

120000

400-800

600

360000

4200

2520000

800-1200

1000

11

1000000

11000

11000000

1200-1600

1400

1960000

5600

7840000

1600-2000

1800

3240000

3600

6480000

25000

27960000

Total

27

Mean (m1)= fx/f

m1 = 25000/27
m1 = 925.93
Standard Deviation (1) = [(fx2/n) (fx/n)2]
1 = [(27960000/27) (25000/27)2]
1 = [1035555.56 857338.82]
1 = 422.16
Coeficient of variation = 1/m1

CV = [422.16/925.93] * 100
CV = 45.59%

Expenditure by age group 18-21

AGE GROUP 21 to 25
Weekly
Expenditure in Rs.
(X10)

Mid point
(x)

Frequency (f)

x2

fx

Fx2

0-400

200

40000

200

40000

400-800

600

360000

3000

1800000

800-1200

1000

12

1000000

12000

12000000

1200-1600

1400

1960000

4200

5880000

1600-2000

1800

3240000

3600

6480000

23000

26200000

Total

23

Mean (m2)= fx/f

m2 = 23000/23
m2 = 1000

Standard Deviation (2) = [(fx2/n) (fx/n)2]

2 = [(26200000/23) (23000/23)2]
2 = [ 1139130.44 1000000]
2 = 373.001

Coeficient of variation = 2/m2

CV = [373.001/1000] * 100
CV = 37.3%

Expenditure Age Group 21-25

RELATIONAL MEAN AND STANDARD

DEVIATION
m = (nm + nm)/ (n+n)
m = (27*925.93 + 23*1000)/ (27+23)
m = (25000.11+23000)/ 50
m =48000.11/50
m = 960.002

d = (m-m)
d = (925.93-960.002)
d = - 34.072

d = (m-m)
d = (1000-960.002)
d = 39.998

= [n (2+d2) + n (22+d22)]/ (n+n)

= [27(178219.07+1160.90) + 23(139129.75+1599.84)]/ (27+23)
= [27(179379.97) + 23(140729.59)]/ (50)
= [4843259.19+3236780.57]/ 100
= 8080039.76/50
= 161600.7952
= 401.996

Z TEST (5% MARGIN)

z-test is based on the normal probability distribution

and is used for judging the significance of several
statistical measures, particularly the mean. The
relevant test statistic, z, is worked out and compared
with its probable value (to be read from table showing
area under normal curve) at a specified level of
significance for judging the significance of the measure
concerned.
This is a most frequently used test in research studies.
z-test is generally used for comparing the mean of a
sample to some hypothesized mean for the population
in case of large sample, or when population variance is
known.
z-test is also used for judging the significance of
difference between means of two independent
samples in case of large samples, or when
population variance is known.
z-test is also used for comparing the sample proportion
to a theoretical value of population proportion or for
judging the difference in proportions of two
independent samples when n happens to be large.

z= (m-m)/ [2 (1/n+1/n)]
z= (925.93-1000)/ [401.996(1/27+1/23)]
z= -74.07/ [401.996(0.081)]
z= -74.07/32.5617
z = -74.07/5.71
z = - 12.97
Reject: Z > 1.96
Hypothesis ACCEPTED as -12.97 is less than 1.96., which is tha acceptance limit.