s

ATMA RAM
SANATAN DHARMA
COLLEGE
PROBABLITY AND STATISTICS
LAB PRACTICAL FILE
Name: AMAN PANDEY
Course: B.Sc.(hons) Mathematics
Semester: Ist
Roll No: 23/37028
Section: B
Submitted to: Mr. Anant Tiwari and
Dr. Amit Mittal

1 Roll no. 23/37028

 INDEX
1. Presentation and analysis of data by
statists
a) Frequency table
b) Stem and leaf..
c) Dotplot
d) Histogram
e) Boxplot
f) Comparative Boxplot

2. Fitting of Binomial, Poisson and

Normal Distribution

3. Illustrating the central Limit Theorem

Through Excel

4. Fitting of Regression Line using the

principle of least squares

5. Computation of sample of Co-relation

2 Roll no. 23/37028

 PRACTICAL-1
PRESENTATION AND ANALYSIS OF DATA (UNIVARIATE AND
BIVARIATE) BY FREQUENCY TABLE, DESCRIPTIVE STATISTICS,
STEM AND LEAF PLOT, DOTPLOTS, HISTOGRAMS, BOXPLOTS,
COMPARITIVE BOXPLOTS, AND PROBABILITY PLOTS.

QUESTION-1: PRESENTATION of UNIVARIATE (CONTINUOUS) data and

ANALYSING by frequency table.
METHODS:

1) Take the random data by applying formula “=randbetween(bottom,top)”

in EXCEL.
2) SELECT the data, COPY it, go to PASTE SPECIAL, click to VALUE option, in
order to fix the data.

3 Roll no. 23/37028

3) Make the frequency table of observed data set in excel by counting the
data by in built function “=COUNTIFS(criteria_range1, criteria1,….)”.

4 Roll no. 23/37028

QUESTION-2: PRESENTATION of UNIVARIATE (DISCRETE) data and ANALYSING
by frequency table.
METHODS:

1) Take the random data by applying formula “=randbetween(bottom,top)”

in EXCEL.
2) SELECT the data, COPY it, go to PASTE SPECIAL, click to VALUE option, in
order to fix the data.

5 Roll no. 23/37028

 3) Make the frequency table of observed data set in excel by counting the
data by in built function “=COUNTIF( range, criteria)”.

QUESTION-3: Analyse the UNIVARIATE (DISCRETE) Data by DESCRIPTIVE

STATISTICS.
(a) METHODS for finding MEAN:

1) Find the value of {F*X}, which is frequency (F) multiplied by data(X);

Find the sum of {F*X)} by appling the formula “=sum(range)”; Find the
sum of {F} Frequency by appling the formula “=sum(range)”.

6 Roll no. 23/37028

 2) To obtain MEAN divide (F*X) by (F) and Verify it by in-built function
“=AVERAGE(number1, number2,…).

(b) METHODS for finding MEDIAN:

1) Apply the formula in a cell in which the MEDIAN is to be estimated

“=MEDIAN (number1, number2, …..)”.
2) Press ENTER, MEDIAN will be displayed in that cell.

7 Roll no. 23/37028

(c) METHODS for finding MODE:
1) Apply the formula in a cell in which the MODE is to be estimated
“=MODE(number1, number2, …..)”.
2) Press ENTER, MODE will be displayed in that cell.

(d) METHODS for finding MAXIMUM VALUE:

1) Apply the formula in a cell in which the MAXIMUM VALUE is to be

estimated “=MAX(number1, number2, …..)”.
2) Press ENTER, MAXIMUM VALUE will be displayed in that cell.

8 Roll no. 23/37028

 (e) METHODS for finding MINIMUM VALUE:

1) Apply the formula in a cell in which the MINIMUM VALUE is to

be estimated “=MIN(number1, number2, …..)”.
2) Press ENTER, MINIMUM VALUE will be displayed in that cell.

(f) METHODS for finding 1st QUARTILE:

1) Apply the formula in a cell in which the 1st QUARTILE is to be estimated

“=QUARTILE(array, quart)”.
2) Select the DATA in place of “array” and Take the value “1” in place of
“quart”.
3) Press ENTER, 1st QUARTILE of the data will be displayed in that cell.

9 Roll no. 23/37028

(g) METHODS for finding 3rd QUARTILE:

1) Apply the formula in a cell in which the 1st QUARTILE is to be estimated

“=QUARTILE(array, quart)”.
2) Select the DATA in place of “array” and Take the value “3” in place of
“quart”.
3) Press ENTER, 3st QUARTILE of the data will be displayed in that cell.

10 Roll no. 23/37028

QUESTION-4: Analyse the UNIVARIATE (CONTINUOUS) Data by DESCRIPTIVE
STATISTICS.
(a) METHODS for finding MEAN:

1) Calculate the CLASS INTERVAL(X) by taking the average of lower limit

and upper limit.
2) Multiply frequency(F) by Class interval(X) and Represent it by ‘F*X’.
3) Sum the ‘F*X’ column and Divide by Frequency(F), we get the MEAN of
the data.
4) Now, compare the result with ‘MEAN’ by inbuilt function.

(b) METHODS for finding MEDIAN:

1) Apply the formula in a cell in which the MEDIAN is to be estimated

“=MEDIAN (number1, number2, …..)”.
2) Press ENTER, MEDIAN will be displayed in that cell.

11 Roll no. 23/37028

(c) METHODS for finding MODE:

1) Apply the formula in a cell in which the MODE is to be estimated

“=MODE(number1, number2, …..)”.
2) Press ENTER, MODE will be displayed in that cell.

12 Roll no. 23/37028

(d) METHODS for finding MAXIMUM VALUE:

1) Apply the formula in a cell in which the MAXIMUM VALUE is to be

estimated “=MAX(number1, number2, …..)”.
2) Press ENTER, MAXIMUM VALUE will be displayed in that cell.

(e) METHODS for finding MINIMUM VALUE:

1) Apply the formula in a cell in which the MINIMUM VALUE is to be

estimated “=MIN(number1, number2, …..)”.
2) Press ENTER, MINIMUM VALUE will be displayed in that cell.

13 Roll no. 23/37028

 (f) METHODS for finding 1st QUARTILE:
1) Apply the formula in a cell in which the 1st QUARTILE is to be estimated
“=QUARTILE(array, quart)”.
2) Select the DATA in place of “array” and Take the value “1” in place of
“quart”.
3) Press ENTER, 1st QUARTILE of the data will be displayed in that cell.

(g) METHODS for finding 3rd QUARTILE:

1) Apply the formula in a cell in which the 1st QUARTILE is to be estimated
“=QUARTILE(array, quart)”.
2) Select the DATA in place of “array” and Take the value “3” in place of
“quart”.
3) Press ENTER, 3st QUARTILE of the data will be displayed in that cell.

14 Roll no. 23/37028

QUESTION-5: Display the STEM AND LEAF PLOT by using DISCRETE Variable.
METHODS:
1) Take the DICRETE RANDOM VARIABLE and use the formula
“=REPT(text,number_time)” in each column to which LEAF has to obtain.

15 Roll no. 23/37028

QUESTION-6: Display the STEM AND LEAF PLOT by using CONTNUOUS Variable.
METHODS:
1) Take the CONTINUOUS RANDOM VARIABLE and use the formula
“=REPT(text,number_time)” in each column to which LEAF has to obtain.

QUESTION-7: Display the DOTPLOT by using NUMERICAL DATA.

METHODS:
1) Take the Random Variable and Make the FREQUENCY TABLE.

16 Roll no. 23/37028

 2) GO to INSERT TAB and CLICK on the BAR CHAT OPTION, bar chat will
appear in excel.

3) Double click on BARS of the chart and GO to FORMAT DATA CHAT and
the design of bar to dot, thus result in DOT PLOTS.

QUESTION-8: Display the DOTPLOT by using CATEGORICAL DATA.

METHODS:
1) TAKING QUESTION: Survey report display that the number of people
are Married, Divorced, Separated, Never Married and Widowed.

17 Roll no. 23/37028

 2) GO to INSERT TAB and CLICK on the BAR CHAT OPTION, bar chat will
appear in excel.
3) Double click on BARS of the chart and GO to FORMAT DATA CHAT
and the design of bar to dot, thus result in DOT PLOTS.

QUESTION-9: Display the HISTOGRAM using CATEGORICAL DATA.

18 Roll no. 23/37028

METHODS:
1) TAKING QUESTION: Survey report display that the MARK of the student
having their ROLL NO..

2) Select the table, go to insert option and CLICK on the chart sub-
section, in order to make column chart.

19 Roll no. 23/37028

 3) Right click on the bar of chart and click on “Format Data
Series”.
4) Reduce the gap width to “0”, we observe HISTOGRAM.

QUESTION-10: Display the BOXPLOT using DISCRETE RANDOM VARIABLES.

METHODS:
1) Take the Random Variables and Find out their MINIMUM VALUE, 1st
QUARTILE, MEDIAN, 3rd QUARTILE, MAXIMUM VALUE.

20 Roll no. 23/37028

2) Make the DIFFERENCE Column by differencing the Adjacent column cell.

3) Make the Stacked Bar by going in INSERT-> RECOMMENDED CHART->

BAR CHAT-> STACKED BAR.

21 Roll no. 23/37028

 4) UNFILLED the color of range of 0-21, 21-25.5 and 42.25-45.
5) CLICK on the STACKED BAR, go to DESIGN option -> ADD CHART
ELEMENT-> ERROR BAR, will result in BOX PLOTS.

QUESTION-11: Display the BOXPLOT using CONTINOUS RANDOM VARIABLES.

METHODS:
1) TAKING QUESTION: Survey report display that the SALARY of employees
at different post in a company.
2) Find out their MINIMUM VALUE, 1st QUARTILE, MEDIAN, 3rd QUARTILE,
MAXIMUM VALUE.
3) Make the DIFFERENCE Column by differencing the Adjacent column cell.

22 Roll no. 23/37028

4) Make the Stacked Bar by going in INSERT-> RECOMMENDED CHART->
BAR CHAT-> STACKED BAR.

23 Roll no. 23/37028

 5) UNFILLED the color of range of 0-17500, 17500-22750 and 38250-49000.
6) CLICK on the STACKED BAR, go to DESIGN option -> ADD CHART
ELEMENT-> ERROR BAR, will result in BOX PLOTS.

QUESTION-12: Display the COMPARATIVE BOXPLOT using CONTINOUS

RANDOM VARIABLES.
METHODS:
1) TAKING QUESTION: High levels of sodium in food products represent a
growing health concern. The accompanying data consists of values of
sodium content in one serving of cereal for one sample of cereals
manufactured by General Mills, another sample manufactured by
Kellogg, and a third sample produced by Quaker.

24 Roll no. 23/37028

2) Find out their MINIMUM VALUE, 1st QUARTILE, MEDIAN, 3rd QUARTILE,
MAXIMUM VALUE of each of the column.

25 Roll no. 23/37028

3) Make the DIFFERENCE Column by differencing the Adjacent column cell
in each SECTION.

4) Make the Stacked Bar of each SECTION by going in INSERT->

RECOMMENDED CHART-> BAR CHAT-> STACKED BAR.

26 Roll no. 23/37028

 5) CLICK on the STACKED BAR, go to DESIGN option -> ADD CHART
ELEMENT-> ERROR BAR, will result in COMPARATIVE BOX PLOTS.

QUESTION-13: Display the COMPARATIVE BOXPLOT using NUMERICAL

VARIABLES.
METHODS:
1) TAKING QUESTION: The following table shows the total marks obtained
in five subjects by 15 students of two sections. For each subjects, the
maximum marks are 100.

27 Roll no. 23/37028

2) Find out their MINIMUM VALUE, 1st QUARTILE, MEDIAN, 3rd QUARTILE,
MAXIMUM VALUE of each of the column.

3) Make the DIFFERENCE Column by differencing the Adjacent column cell

in each SECTION.
4) Make the Stacked Bar of each SECTION by going in INSERT->
RECOMMENDED CHART-> BAR CHAT-> STACKED BAR.
5) CLICK on the STACKED BAR, go to DESIGN option -> ADD CHART
ELEMENT-> ERROR BAR, will result in COMPARATIVE BOX PLOTS.

28 Roll no. 23/37028

 PRACTICAL-2
FITTING OF BINOMIAL, POISSON AND NORMAL
DISTRIBUTIONS.

Presentation of UNBAISED BINOMIAL DISTRIBUTIONS.

QUESTIONS-1: Each person has a diseased with probability 0.1 independently.
Out of 20 random persons tested for the diseased, DISPLAY the BINOMIAL
DISTRIBUTION of 20 person test positive.
METHODS:
1) Make the TABLE of No. of person (X) vs BINOMIAL DISTRIBUTIONS.
2) Write the Value of ‘N’ and ‘p’.
3) Apply the formula “=BINOM.DIST(C7,$J$8,$J$7,FALSE)”, in the First
cell and drag it down to display the BINOMIAL DISTRIBUTIONS of rest
of the random variables.

29 Roll no. 23/37028

 4) Now, make the GRAPH of the BINOMIAL DISTRIBUTIONS data.

COMPARITION OF BAISED and UNBAISED BINOMIAL DISTRIBUTIONS.

QUESTIONS-2:
(a) A BAISED COIN of coming the probability of HEAD is 0.3, is tossed 10 time.
Let the Random Variable(X) define no. of HEAD comes on the upper face.
(b) A UNBAISED COIN of coming the probability of HEAD is 0.5, is tossed 10
time. Let the Random Variable(X) define no. of HEAD comes on the upper face.
METHODS:
1) Make the TABLE of No. of HEAD (X) vs BINOMIAL DISTRIBUTIONS.
2) Write the Value of ‘N’ and ‘p’ of each section.
3) Apply the formula “=BINOM.DIST(C7,$J$8,$J$7,FALSE)”, in the First cell
and drag it down to display the BINOMIAL DISTRIBUTIONS of rest of the
random variables in sections.

30 Roll no. 23/37028

4) Now, make the GRAPH of the BINOMIAL DISTRIBUTIONS of each section
of data.

31 Roll no. 23/37028

QUESTION 3:
Suppose a biased coin has a probability of landing on heads (p)
equal to 0.7. If the coin is flipped 10 times, what is the probability of
getting exactly 7 heads? Additionally, create a binomial distribution
graph to visualize the probabilities of getting 0 through 10 heads.
Solution:
Here, p=0.7, n=10 Enter the probability of heads (p) in one cell. Enter
the number of trials (n) in another cell. In a new cell, calculate the
probability of getting exactly 7 heads using the BINOM.DIST function.
Type the following formula in a cell: =BINOM.DIST(B3,B2,B1,false) In
another column, list the possible number of heads (0 through 10) in
one column. In the adjacent column, use the BINOM.DIST function to
calculate the probabilities for each number of heads.
=BINOM.DIST(A6,$B$2,$B$1,FALSE) Drag this formula down to cover
the range of 0 through 10. Select the range of cells in the two
columns where you have calculated the probabilities. Go to the
"Insert" tab in the Excel ribbon and choose "Scatter Plot" or "Line
Chart" to create a binomial distribution graph

32 Roll no. 23/37028

 POISSON DISTRIBUTIONS
QUESTIONS-3: Make the Classical and Poisson distribution of the following
data:

METHODS:

1) Find the MEAN of the frequency table.

33 Roll no. 23/37028

2) Now, make the Classical and Poisson distribution, by using formula
“=f/sum(f)” and “=POISSON.DIST(x, mean, false)”.

3) Now, Make the chart of POISSON DISTRIBUTIONS.

34 Roll no. 23/37028

QUESTIONS-4: Compare the POISSON DISTRIBUTION having SAME RANDOM
VARIABLE and THREE DIFFERENT MEANS.
METHODS:
1) Apply the formula “=POISSON.DIST(x, mean, false)”, in the First cell
and drag it down to display the POISSON DISTRIBUTIONS of rest of
the random variables, in each column.

35 Roll no. 23/37028

 2) Making their GRAPH and compare the POISSON DISTRIBUTIONS.

CLASSICAL AND NORMAL DISTRIBUTIONS

QUESTIONS-5: Display the CLASSICAL and NORMAL DISTRIBUTIONS graph of
the Following data.

36 Roll no. 23/37028

METHODS:
1) Find the MEAN, VARIANCE, STANDARD DEVIATION, LOWER LIMIT,
UPPER LIMIT, CLASS MARK, f*x, fxx and CLASSICAL PROBABILITY.

2) Find the CDF for lower limit, CDF for upper limit and NORMAL
PROBABILITY.

37 Roll no. 23/37028

 3) Make the GRAPH of NORMAL PROBABILITY and CLASSICAL PROBABILITY.

QUESTIONS-6: Display the CLASSICAL and NORMAL DISTRIBUTIONS graph of

the Following data.

38 Roll no. 23/37028

METHODS:
1) Find the MEAN, VARIANCE, STANDARD DEVIATION, LOWER LIMIT,
UPPER LIMIT, CLASS MARK, f*x and fxx.

39 Roll no. 23/37028

 2) Find the CDF for lower limit, CDF for upper limit, NORMAL PROBABILITY
and CLASSICAL PROBABILITY.

3) Make the GRAPH of NORMAL PROBABILITY and CLASSICAL PROBABILITY.

QUESTIONS-7: Display the CLASSICAL and NORMAL DISTRIBUTIONS graph of

the Following data.

40 Roll no. 23/37028

METHODS:
1) Find the MEAN, VARIANCE, STANDARD DEVIATION, LOWER LIMIT,
UPPER LIMIT, CLASS MARK, f*x and fxx.

41 Roll no. 23/37028

2) Find the CDF for lower limit, CDF for upper limit, NORMAL PROBABILITY
and CLASSICAL PROBABILITY.

3) Make the GRAPH of NORMAL PROBABILITY and CLASSICAL PROBABILITY.

42 Roll no. 23/37028

 PRACTICAL-3
ILLUSTRATING THE CENTRAL LIMIT THEOREM THROUGH
EXCEL.

QUESTION-1: Illustrate the central limit theorem by taking 300 random values
ranging from 20-40 and hence depict the frequency table graph.
METHODS:
1) We will take 300 random data ranging from 20-40 by using formula
“RANDBETWEEN(20,40)”.
2) Putting n=300, we further in next column will take 15 samples and
further take 20 rows.

3) USE the formula in Sample-1 cell

“=INDEX($A$2:$A$301,RANDBETWEEN(1,$C$1))”

43 Roll no. 23/37028

4) Now stretch it up to column 20 and sample 15.
5) Now we will take out mean of the data. For instance we will first draw
out the mean of sample 1 by the formula. Then stretch it up to sample
15.

44 Roll no. 23/37028

6) We will make a frequency table consisting of frequency ranging from 20-
40 as shown in step 6.

7) Now we will find the value for the f of range 20-25 by formula
“=COUNTIFS($A$2:$A$301,">=20",$A$2:$A$301,"<25")”. Similarly we will
find value of f of rest of ranges.

8) Now we will find the value for f(m) for the given different ranges using
the formula. “=COUNTIFS($X$2:$X$16,">=20",$X$2:$X$16,"<25")”.

9) Now we will draw a graph for the frequency table by going into insert
section and plotting a graph as shown down.

45 Roll no. 23/37028

QUESTION-2: Take population sample size ranging from 200 to 1000. Find
central limit and plot the respective graph.
METHODS:
1) We will take 300 random data ranging from 20-40 by using formula
“RANDBETWEEN(200,1000)”.
2) Putting n=300, we further in next column will take 15 samples and
further take 20 rows.
3) Now, use the formula in Sample-1 cell
“=INDEX($A$1:$A$300,RANDBETWEEN(1,$D$2)). And drag it to entire
row and column.

46 Roll no. 23/37028

4) Now we will take out mean of the data. For instance we will first draw
out the mean of sample 1 by the formula. Then stretch it up to sample
15.

5) We will make a frequency table consisting of frequency ranging from 20-

40 as shown in step 6.

6) Now we will find the value for the f of range 20-25 by formula
“=COUNTIFS($A:$A,">=200",$A:$A,"<300")” Similarly we will find value of
f of rest of ranges.

47 Roll no. 23/37028

7) Now we will find the value for f(m) for the given different ranges using
the formula,“=COUNTIFS($Y$6:$Y$20,">=500",$Y$6:$Y$20,"<600")”.

8) Now we will draw a graph for the frequency table by going into insert
section and plotting a graph as shown down.

48 Roll no. 23/37028

 PRACTICAL-4
FITTING OF REGRESSION LINE USING THE PRINCIPLE OF
LEAST SQUARES.

QUESTION-1: Illustrate the FITTING OF REGRESSION LINE by BIVARIATE DATA.

METHODS:
1) TAKING QUESTION: An experiment to investigate how the behavior of
mozzarella cheese varied with temperature. Consider the accompanying
data on X= temperature and Y=elongation at failure of the cheese.

2) Draw the SCATTERPLOT by going to INSERT option-> RECOMMENDED

CHART-> SCATTER PLOT.

49 Roll no. 23/37028

3) CLICK on the CHART-> CHART ELEMENTS->TRENDLINE.

4) CILCK on the TRENDLINE -> FORMAT TRENDLINE -> DISPLAY EQUATION

ON CHART, and Hence the BEST FITTING LINE will be displayed with
formula.

50 Roll no. 23/37028

QUESTION-2: Illustrate the FITTING OF REGRESSION LINE by BIVARIATE
NUMERICAL DATA.
METHODS:
1) Taking the two numerical data and Computing their ASSOCIATION by
FITTING OF REGRESSION LINE.

2) Draw the SCATTERPLOT by going to INSERT option-> RECOMMENDED

CHART-> SCATTER PLOT.

51 Roll no. 23/37028

3) CLICK on the CHART-> CHART ELEMENTS->TRENDLINE.

4) CLICK on the TRENDLINE -> FORMAT TRENDLINE -> DISPLAY EQUATION

ON CHART, and Hence the BEST FITTING LINE will be displayed with
formula.

52 Roll no. 23/37028

QUESTION-3: Suppose an analyst is interested to know the association
between age of cars (years) and price of car (in lakhs). For this, he collected
data of 15 cars and tabulated as follows:-

METHODS:
1) Draw the SCATTERPLOT by going to INSERT option-> RECOMMENDED
CHART-> SCATTER PLOT.

53 Roll no. 23/37028

2) CLICK on the CHART-> CHART ELEMENTS->TRENDLINE.

3) CLICK on the TRENDLINE -> FORMAT TRENDLINE -> DISPLAY EQUATION

ON CHART, and Hence the BEST FITTING LINE will be displayed with
formula.

54 Roll no. 23/37028

 PRACTICAL-5
COMPUTATION OF SAMPLE CORRELATION COEFFICIENT.
Correlation = cov(x,y)/Sx*Sy

QUESTION-1: Suppose an analyst is interested to know the association

between age of cars (years) and price of car (in lakhs). For this, he collected
data of 15 cars and tabulated as follows and wanted to find the CORRELATION
COEFFICIENT.

55 Roll no. 23/37028

METHODS:
1) Find the MEAN of X and Y, Square Difference from their (X and Y) MEANS
and Multiply their Difference from their MEAN and Represent them in
column.

56 Roll no. 23/37028

2) Find the COV(X,Y) and STANDARD DEVIATION of X and Y, by applying
formula “=COVAR(number1, number2,….)” and “=STDEV(number1,
number2,……)” respectively.

3) Now, Apply the formula= “Correlation = cov(x,y)/Sx*Sy”.

Hence, we get CORRELATION COEFFICIENT OF DATA.
4) Now, we can check the CORRELATION by in-built function
“=CORREL(array1, array2,….)”.

57 Roll no. 23/37028

58 Roll no. 23/37028
QUESTION-2: Toughness and fibrous of asparagus are major determinants of
quality. The article reported the accompanying data on X= shear force (kg) and
Y= percent fiber dry weight.

METHODS:
1) Find the MEAN of X and Y, Square Difference from their (X and Y) MEANS
and Multiply their Difference from their MEAN and Represent them in
column.

2) Find the COV(X,Y) and STANDARD DEVIATION of X and Y , by applying

formula “=COVAR(number1,number2,….)” and “=STDEV(number1,
number2,……)” respectively.

59 Roll no. 23/37028

3) Now, Apply the formula= “Correlation = cov(x,y)/Sx*Sy”.
Hence, we get CORRELATION COEFFICIENT OF DATA.

4) Now, we can check the CORRELATION by in-built function

“=CORREL(array1, array2,….)”.

60 Roll no. 23/37028

61 Roll no. 23/37028