Professional Documents
Culture Documents
Bhagyashri Sawant 20-1013 Statistics
Bhagyashri Sawant 20-1013 Statistics
Calculate: -
i) Mean
ii) Median
iii) Mode
iv) Standard Deviation (σ)
v) Q1 and Q3
vi) D5 and D7
vii) P53 and P87
viii) Coefficient of Variance (C.V.)
ix) SKB and interpret the result
x) SKP and interpret the result
1} Mean Values
X Frequency Cumulative Mid-point F*X F * X2
F frequency
CF
0-10 3 3 5 15 75
10-20 5 8 15 75 1125
20-30 8 16 25 200 5000
30-40 10 26 35 350 12250
40-50 20 46 45 900 40500
50-60 12 58 55 660 36300
60-70 10 68 65 650 42250
70-80 6 74 75 450 33750
80-90 4 76 85 340 28900
90-100 2 80 95 190 18050
Total 80 3830 157550
Page | 1
1} Mean = sum of (F*X) / sum of F
Mean= 3830 /80
Mean=47.875
Median = L + [{(f/2) – CF} / F] * h Here,
median class selected = 40-50
Median = 40 + 7 = 47
Page | 2
σ = square root of (435.5569)
σ = 20.87
Q1 and Q3
Quartile Deviation Qr = L + [{(rn/4) – CF} / F] * h
Here, r = 1;
n = total frequency = 70
So, r*n / 4 = 80/4 = 20;
Finding the number in cumulative frequency if not found take the next higher value available
and the class belonging to that frequency is the lower quartile class
here, we get lower quartile class = 30-40
Now, CF = cumulative frequency of the class preceding the lower quartile class = 16;
Now, r = 3 So,
r * n / 4;
= 3*80 /4;
= 240/4 = 60
Finding the number in cumulative frequency if not found take the next higher value available
and the class belonging to that frequency is the upper quartile class
Here, class selected = 50-60
Now, CF = cumulative frequency of the class preceding the upper quartile class = 58;
Page | 3
Therefore, Q3 = 60 + {60 – 58) / 10} * 10
Q3 = 60 + 2
Q3= 62
D5 and D7
Decile Dr = L + [{(rn/10) – CF} / F] * h
Here, r = 5;
n = total frequency = 80;
So, r*n/10 = 5*8 = 40;
Finding the number in cumulative frequency if not found take the next higher value available
and the class belonging to that frequency is the 5th decile
We get 5th decile class = 40-50
Now, CF = cumulative frequency of the class preceding the decile class = 26;
Page | 4
L = lower limit of class selected = 50.
D7 = 50 + {(56 – 46) / 12} * 10
D7 = 50 + 8.33
D7 = 58.33
P53 and P87
Percentile Pr = L + [{(rn/100) – CF} / F] * h
Here, r = 53;
n = total frequency = 80;
So, r*n/100 = 53*0.8 = 42.4;
Finding the number in cumulative frequency if not found take the next higher value available
and the class belonging to that frequency is the 53rd percentile class
We get 53rd percentile class = 40-50
Now, CF = cumulative frequency of the class preceding the decile class = 26;
Here, r =87;
n = total frequency = 80;
So, r*n/100 = 87*0.8 = 69.6;
Finding the number in cumulative frequency if not found take the next higher value available
and the class belonging to that frequency is the 87th percentile class
We get 87th percentile class = 70-80
Now, CF = cumulative frequency of the class preceding the decile class = 68;
Page | 5
L = lower limit of class selected = 70.
P87 = 70 + {(69.6 – 68) / 6} * 10
P87 = 70 + 2.67
P87 = 72.67
Coefficient of Variance (C.V.) = (σ / mean) * 100
C.V. = (20.87 / 47.875) * 100 = 43.59
Question Number-2
The following data shows the number of items of similar type produced in a factory during
last 50 days. 21 22 17 23 27 15 16 22 15 23 24 25 36 19 14 21 24 25 14 18 20 31 22 19 18 20 21
20 36 18 21 20 31 22 19 18 20 20 24 35 25 26 19 32 22 26 25 26 27 22.
Obtain a frequency distribution fir the above data and with the help of histogram and
Ogive curves the mode and the median of the data (show graphically). Also, with the help if
histogram interpret the shape of the distribution (skewness)
Answer-
Page | 6
Class Tally mark Frequen
interval cy
10-15 || 2
15-20 || 12
20-25 | 21
|
25-30 9
30-35 ||| 3
35-40 ||| 3
Mean=23.3
Graph-
Here we can see mean > median > mode therefore it is positive skewed distribution.
Page | 9
Question Number- 3
1} For the first 4 weeks on job, a waiter averaged ₹40 /week as a tip. For the next 3 weeks,
he averaged ₹ 45 /week. If the overall average for the first 8 week was ₹ 43 /week, how
much tip did he receive in 8th week?
Answer-
For first four weeks averaged tip = 40 Rs.
For next 3 weeks averaged tip = 45 Rs For
total 8 weeks averaged tip = 43 Rs.
Let, the averaged tip for 8th week = x
Therefore, averaged tip for total 8 weeks = {(1st 4week * 4) + (next 3 weeks * 3) + (8th
week)} / 8
So, 43 = {(40*4) + (45*3) + x} / 8 43 * 8 = 295 + x
X = 344 -295
X = 49 Rs.
Page | 10
Profit for eighth year = 2,46,903.552 * (7/3) = 5,76,108.288
3} A Fruit vendor bought a certain number of oranges at 3 for ₹ 25 rupees and sold for 2
for ₹30. What is his gain or loss percent?
Answer-
Cost of 3 oranges = 25
Therefore, cost of 1 orange = 25/3 = 8.33
Sale price of 2oranges = 30
Sale of 1 orange = 15
Profit = {(sp - cp) / cp} * 100 Profit
= {(15 - 8.33) / 8.33} * 100
Profit = 80.07%
Therefore,
Page | 11
x + (x/2) + (x/3) = 38,016 Rs.
6x + 3x + 2x = 2,28,096
11x = 2,28,096
x = 2,28,096 / 11
x = 20,736 Rs.
Therefore, amount received by youngest kid = 20,736 / 3 = Rs. 6,912
5} A, B and C are the partners in a firm. A gets 20% of total profit, B gets 60% of
remaining profit, while C gets the rest. If C receives ₹ 5000 as his share of profit what is
the total profit?
Answer-
% received by A = 20%
% received by B = (total profit – A’s profit) * 60%
Assuming total profit as 100. We get
Profit of B = 80 * 60% = 48
Therefore, % received by B = 48%;
Therefore, % received by C = 32%
Received amount by C = 5000
Total amount of profit = x
Therefore, amount received by C = 32% of x
5000 = (32/100) * x
X = (5000*100) / 32
X = 15,625 Rs.
Therefore, total profit is 15,625.
Page | 12
Question Number-4
4} In the year 2016, the total strength of student in 3 colleges X, Y and Z in a city were in
a ratio 4:2:5. The strength of college Y was 1000. The proportion of girls and boys in all
the colleges was in the ratio 2:3. The faculty wise distribution of boys and girls in arts,
science and commerce was in the ratio 1:2:2 in all 3 colleges. Prepare a table to fit the
above data.
Answer- X college students = 4x
Y college students = 2x = 1000
Z college students = 5x
Taking y college
2x = 1000
X = 500
Therefore, students in x college = 4x = 4*500 = 2000
Page | 13
Boys in science in y college = (2/5) * 400 = 160
Boys in commerce in y college = (2/5) * 400 = 160
Boys in arts in y college = (1/5) * 400 = 80
Page | 14
Draw a Venn-diagram and find out: -
1} Number of students not playing any game
2} Number of students who play cricket only
3} Number of students who play only 1 game.
4} Number of students who play exactly 2 games
Answer-
Cricket Hockey
17 14
Football
12
Question Number- 5
Page | 15
5} Discuss the various sampling techniques with suitable examples (Probability sampling
techniques and non-probability sampling techniques).
Answer-
Sampling methods can be majorly classified in 2 types:
1} Probability sampling methods
2} Non- probability sampling methods.
Page | 16
B} Sampling without replacement: In this type once an element is selected, it is not replaced
back in the frame. It is kept aside so has no chance of getting selected again. In the first draw
each element has 1/N chances for getting selected, where in second selection it becomes 1/(N-
1), for third selection it becomes 1/(N-3) and so on.
1} There are two methods of selection in random sampling, and they are:
A} Through table of random digits
B} Lottery method
Page | 17
1} An Office has 400 male employees and 1200 female employees. The main aim is that the
sample reflects the gender balance of the office e, so we sort the population into two strata based
on gender. Then the use of random sampling is done on each group, by selecting 80 women and
20 men, which will give us a representative sample of 100 people.
2} Systematic sampling:
1} A systematic sample is obtained by selecting one unit at random and choosing rest units at
evenly spaced intervals till the desired value of elements are gathered.
2} From the population of N elements, we have to choose n samples then N/n is calculated
which is denoted by K.
3} From 1 to K element any number is chosen at random the followed by selection ok every kth
term from the chosen element till k terms are achieved.
Advantages of systematic sampling
1} More simple than random and stratified sampling.
2} Requires less time compared to others.
3} More efficient than simple random sampling given that the frame is complete and up to date
and units are arranged serially in random order like names in telephone dictionary.
4} More useful than simple random sampling.
Disadvantages of systematic sampling
1} It gives a biased result if there are periodic features in the frame and sampling period is
equal to multiple of period.
2} It works when the elements are randomly arranged and the frame available is up to date and
complete.
Example:
All the employees (100 employees) of a MNC are listed in alphabetical order. We need a
sample of 10 employees. So, N is 100 and n is 10 so the K = 100/10 = 10. Now, from the first
10 numbers, you randomly select a starting point suppose, number 6. From number 6 onwards
every 10th person on the list is being selected (6, 16, 26, 36, 46, 56, 66, 76, 86 and 96) gives us
the sample of 10 employees.
Cluster sampling:
Page | 18
1} Clusters are formed and selected randomly in this type.
2} It is used when the population is very high or geographically dispersed.
3} If practically possible, supervisor might include every individual from each sampled cluster.
If the cluster is too large random sampling can be done from clusters.
Advantages of cluster sampling:
1} Fixed cost is reduced in cluster sampling.
2} Applicable in non-complete list of units.
3} It is flexible as it allows division to be used a unit at various stages.
4} Useful where sampling frame is not available.
Multi-stage sampling:
1} It is done in more than one stage.
2} In the first stage population is known as primary sampling unit.
3} Samples are selected from primary sampling units then samples are taken from them till the
selection of final units.
4} It is similar to cluster sampling.
Advantages in multi-stage sampling
1} It results in concentration of field work.
2} Time saving.
3} Saves labour and money.
Example
Page | 19
1000 urban house have to be selected from the country. The first stage is where districts are
selected from the country suppose 20 districts from 400. Now in second stage cities are selected
from the selected districts suppose 5 cities from each district. In the last stage households from
the cities are selected and sampling is done.
Non-probability sampling
Each unit doesn’t have equal probability to be selected.
Judgment sampling
1} It is also known as purposive sampling.
2} In this type of sampling the researcher uses their judgement to select a sample that is most
useful to the purposes of the research.
3} It is often used in qualitative research, where the researcher wants to get a detailed
knowledge about a specific phenomenon rather than make statistical inferences.
Advantages of judgment sampling
1} Simple and easy.
2} Used to solve daily problems by businessman.
3} Useful when the number of sampling is less.
4} Useful to know the impact of specific phenomenon.
Page | 20
2} Cannot determine the size of sampling error
Example
Suppose, we want to know more about the opinions and experiences of hostel students at a
university, so you purposely select a number of students with different support needs so that
gathering a varied range of data on their experiences with student services.
Convenience sampling
1} It is used in exploratory research where surveyor is interested in getting inexpensive
approximation of truth.
2} Invigilator has freedom to choose whomsoever is convenient to them.
Quota sampling
1} It means to take a very tailored sample that is in proportion to some characteristic of a
population.
2} It is done initially as stratified sampling and the judgment sampling is used to select the
members from each stratum.
3} In this the invigilator deliberately sets the proportion of the strata within sample.
4} Quota is set independent to the characteristics of population.
Page | 21
2} More cost saving.
3} More detailed information is gained.
4} Results are reliable than census type.
Disadvantages of quota sampling
1} Estimation of accuracy is difficult.
2} Bias results can be obtained more.
3} Basis of quota division are crucial and need to be refined.
4} Proper planning is required.
Example:
A researcher wants to survey individuals about what car brand they prefer. He/she considers a
sample size of 100 respondents. Also, he/she is only interested in surveying 10 states. Following
is how the researcher can divide the population by quotas: Gender: 50 males and 50 females.
Age: 10 respondents each between the ages of 16-20, 21-30, 31-40, 41-50, and 51+. Employment
status: 50 employed and 50 unemployed people. Location: 5 responses per state.
Page | 22