MISRIMAL NAVAJEE MUNOTH JAIN ENGINEERING COLLEGE

Owned and Managed by

y Tamilnadu Educational And Medical Foundation
Approved by AICTE and Accredited by NBA
Affiliated to Anna University, Chennai
Jyothi Nagar, Thoraipakkam, Chennai – 600097

Department of Management Studies

Subject Code : BA4212

Subject Name : Data Analysis and
d Business Modeling (Laboratory)
(Laboratory
Class & Branch : MBA (1st Year)
Academic Year : 2023 – 2024
Semester : II Semester
Student Name :
 BONAFIDE CERTIFICATE

This is to certify that this is a bonafide record of practical work done by

Mr/Ms ______________________________________________________ of II-Semester MBA – Master
of Business Administration in the BA4212 - Data Analysis and Business Modeling (Laboratory) during the
Academic year 2023 – 2024.

Staff In-Charge Head of the Department

Submitted for the University Practical Examination held on ----------------------.

Internal Examiner External Examiner

 INDEX

PAGE FACULTY
S.NO DATE TITLE
NO. SIGN
1 Descriptive Statistics using SPSS
2 One Way ANOVA
3 Two Way ANOVA
4 T-Test with One Sample
5 T-Test with Independent Groups
6 Paired T-Test
7 Correlation
8 Regression
9 Chi-Square Test for Goodness of Fit: Based on
Individual Scores
10 Chi-Square Test for Goodness of Fit: Based on
Weigh Cases
11 Chi-Square Test for Goodness of Fit: Based on
Weigh Cases
12 Spearman’s Rank Correlation
13 Mann-Whitney U Test
14 Wilcoxon Signed-Rank Test
15 Kruskal-Wallis Test
16 Friedman Test
17 Transportation
18 Network Model: Minimum Spanning Tree Program
19 Network Model: Shortest Route
20 Queing Model
21 Linear Programming
22 Project Planning: Critical Path Method
23 Project Planning: Program Evaluation Review
Technique
24 Forecasting
25 Risk Analysis
 1. DESCRIPTIVE STATISTICS USING SPSS

PROBLEM:
The marks of 12 students in mathematics are as follows:
Students 1 2 3 4 5 6 7 8 9 10 11 12
Marks 45 67 78 98 100 72 91 34 94 61 82 92

Calculate the following:

1. Central Tendency
a) Mean
b) Median
c) Mode
d) Sum
2. Dispersion
a) Standard Deviation
b) Variance
c) Range
d) Minimum
e) Maximum
f) S.E mean
3. Distribution
a) Skewness
b) Kurtosis

AIM:
To analyse the descriptive measures of students marks using SPSS.

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows
Name Type Width Decimal Label Value Measure
Studentnumber Numeric 8 0 Student number None Ordinal
Studentmarks Numeric 8 0 Student marks None Scale

Step 4 – Go to ‘Data View’ tab and enter the given data under corresponding columns
Step 5 – Click on Analyze Descriptive StatisticsFrequencies
Step 6 – Select ‘Student marks’ and drag it to the variables box
Step 7 – Click the ‘Statistics button’ select the required options and press ‘continue’
Step 8 – Press ‘Ok’ button in the ‘Frequencies’ dialog box
Step 9 – The SPSS output viewer will appear with results
Step 10 – Save both the data and output
INFERENCE:
Skewness – Since Mean<Median, Skewness is negative skewed
Kurtosis – Since Kurtosis<0, it implies a platykurtic distribution

RESULT:
Thus, a Descriptive measure of students using SPSS has done successfully.
 2. ONE WAY ANOVA
PROBLEM:
The following table gives the yields of 15 samples of plot under 3 varieties of seed.
Variety I 20 21 23 16 20
Variety II 18 20 17 15 25
Variety III 25 28 22 28 32

Test whether there is a significant difference in the average yield between 3 varieties of seeds.

AIM:
To find the average yield between three variety of seeds through one way anova using SPSS.

HYPOTHESIS
Null Hypothesis H0: There is no significant differences between the groups (seed variety) mean scores.
Alternative Hypothesis H1: There is a significant differences between the groups (seed variety) mean scores.

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows
Name Type Width Decimal Label Value Measure
Seed Numeric 8 0 Seed Variety 1VAR 1 Nominal
2VAR 2
3VAR 3
Yield Numeric 8 0 Yield None Scale

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Go to AnalyzeCompare MeansOne Way Anova
Step 6 – Select and drag ‘Yield’ to the dependent list box and ‘Seed Variety’ to the ‘Factor’ and press ‘Ok’
Step 7 – The SPSS output viewer will appear with results
Step 8 – Save both the data and output.

INFERENCE:
F value – 8.143
P value – 0.006
Since the P value <0.05, then reject H0 at at 5% level of significance. There is a significant differences
between the groups (seed variety) mean scores.

RESULT:
Thus, an average yield between three variety of seeds through one way anova using SPSS has done
successfully.
 3. TWO WAY ANOVA
PROBLEM:
Find out whether the sales of the respondents depend on their place and education. The following table
gives you the details of sales in accordance with respective place and education of 15 respondents.
Place
(1-Delhi,
1 1 1 1 1 2 2 2 2 2 3 3 3 3 3
2-Kolkata,
3-Chennai)
Education
(1-Under Graduate,
1 2 3 3 2 3 3 1 1 2 1 2 3 2 1
2- Graduate,
3-Post Graduate)
Sales 35 30 55 65 40 50 45 20 15 30 10 15 30 11 15

AIM:
To find whether the sales in general is affected by place and education of a buyer through two way
anova using SPSS.

HYPOTHESIS
Null Hypothesis H0: The sales are not dependent on the place and education of a respondent.
Alternative Hypothesis H1: The sales are dependent on the place and education of a respondent.

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create three variables as follows
Name Type Width Decimal Label Value Measure
Place Numeric 8 0 Place 1Delhi Nominal
2Kolkata
3Chennai
Education Numeric 8 0 Education 1Under Graduate Nominal
2Graduate
3Post Graduate
Sales Numeric 8 0 Sales None Scale

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Go to AnalyzeGeneral Linear ModelUnivariate
Step 6 – Choose ‘Sales’ and drag it to dependent variable box. ‘Place and Education’ to the fixed factor list box
Step 7 – Click Descriptive Statistics, Estimates of effect size, Observed power and Homogeneity tests check
boxes in the Display box and click continue.
Step 8 – In Univariate dialog box, click ‘Ok’ to generate output.

INFERENCE:
F-value – 1.145
P value – 0.419
Since the p-value is greater than 0.05, the sales is not dependent on the place and education of a respondent.

RESULT:
Thus, Two way anova using SPSS has been done successfully.
 4. T-TEST WITH ONE SAMPLE
PROBLEM:
Test if the average test score of students taught by a new method is significantly different from a known
average test score of 80.
Students 1 2 3 4 5 6 7 8 9 10
Test Score 85 90 88 92 86 78 82 80 79 81

AIM:
To do one sample t-test using SPSS for identifying effectiveness of the new teaching method.

HYPOTHESIS
Null Hypothesis H0: There is no significant difference between average test score after the introduction of new
teaching method.
Alternative Hypothesis H1: There is a significant difference between average test score after the introduction
of new teaching method.

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create variables as follows
Name Type Width Decimal Label Value Measure
Student Numeric 8 0 Student None Nominal
Number
Test Score Numeric 8 0 Test Score None Scale

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Go to AnalyzeCompare meansOne Sample T-Test
Step 6 - Move the Test Score variable to the Test Variable box.
Step 7 - Enter the known mean or hypothesized mean you want to test against. In this case, enter 80.
Step 8 - Click OK to run the one-sample t-test.

INFERENCE:
T-value (2.08) indicates the difference between the sample mean and the test value (80) relative to the
variability of the scores. Degree of Freedom (9) is used to determine the critical t-value. The p-value (0.067) is
greater than 0.05, so we fail to reject the null hypothesis. Hence, there is no statistically significant difference
between the average test score of students taught by the new method.

RESULT:
Thus, one sample t-test using SPSS has been executed successfully.
 5. T-TEST WITH INDEPENDENT GROUPS
PROBLEM:
The marks obtained by a group of a 9 regular students and another group of 11 part time course students
in a test are given below:
Regular 78 78 75 71 73 59 78 69 72
Part Time 62 70 71 62 60 56 69 64 72 68 66

Examine whether the marks obtained by regular and part time students differs significantly at 5% level
of significance.

AIM:
To create an analysis of T-test for the regular and part time students.

HYPOTHESIS
Null Hypothesis H0: There is no significant difference between average marks obtained by regular and part
time students
Alternative Hypothesis H1: There is a significant difference between average marks obtained by regular and
part time students

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows
Name Type Width Decimal Label Value Measure
Students Numeric 8 0 Students 1Regular Nominal
2Part time
Marks Numeric 8 0 Marks None Scale
Obtained

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Go to AnalyzeCompare MeansIndependent Sample Test
Step 6 – Move ‘Marks’ to the test variable and ‘Students’ to the grouping variables
Step 7 – Click continueOk.
Step 8 – Output will be generated

INFERENCE:
Pearson correlation value for the level of knowledge and satisfaction score is -0.404 which is negatively
correlated. There is a significant difference between average marks obtained by regular and part time students.

RESULT:
Thus, t-test with independent groups using SPSS has been executed successfully.
 6. PAIRED T-TEST
PROBLEM:
Find out whether efficiency of engine with and without ethanol differs between manual and automatic
cars. 10 cars were test driven with and without ethanol and the number of kilometers per litre were recorded.
The cars used were having either automatic or manual transmission.
Car
(1-Automatic 1 1 2 2 1 2 1 2 1 2
2-Manual)
With Ethanol 15 16 20 22 18 20 10 19 9 15
Without Ethanol 15 15 19 18 15 18 11 20 8.50 14

AIM:
To run a paired t-test using SPSS to analyze the effectiveness of engine performance with and without
ethanol.

HYPOTHESIS
Null Hypothesis H0: There is no significant difference in engine efficiency between with and without ethanol
Alternative Hypothesis H1: There is no significant difference in engine efficiency between with and without
ethanol

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create three variables as follows
Name Type Width Decimal Label Value Measure
Car Numeric 8 0 Car type 1Automatic Scale
2Manual
WithEthanol Numeric 8 2 With Ethanol None Scale
WithoutEthanol Numeric 8 2 Without Ethanol None Scale
Step 4 – Go to ‘Data View’ tab and enter the given data
Step 5 – Go to AnalyzeCompare MeansPaired Sample T Test
Step 6 – Move both ‘with and without ethanol’ to the Paired Variables list box.
Step 7 – Click ‘OK’ to see the output viewer

INFERENCE:
T value – 2.067
P value – 0.069
Since the p-value is greater than 0.05 significance level, there is no significance difference in engine efficiency
between with and without ethanol.

RESULT:
Thus, the paired t-test using SPSS has been executed successfully.
 7. CORRELATION
PROBLEM:
Find the correlation co-efficient between the income and expenditure of the family to the following data.
Also test whether the correlation co-efficient is single.
Income 60 58 45 65 56 38 70
(in hundreds)
Expenditure 55 50 40 60 62 45 63

AIM:
To find the correlation between income and expenditure using SPSS.

HYPOTHESIS
Null Hypothesis H0: There is no significant correlation between income and expenditure
Alternative Hypothesis H1: There is a significant correlation between income and expenditure

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows
Name Type Width Decimal Label Value Measure
Income Numeric 8 0 Income None Scale
Expenditure Numeric 8 0 Expenditure None Scale

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Go to AnalyzeCorrelateBivariate correlations dialog will open
Step 6 – Select ‘Income’ ‘Expenditure’ to the Variable box
Step 7 – Select the Pearson option
Step 8 – Click the Statistics buttonselect required options and press ‘Continue’
Step 9 – Press ‘OK’ button and the output viewers will open with results.

INFERENCE:
Correlation Coefficient : 0.83
P value: 0.021
Since P value < 0.05, correlation co-efficient is significance at level of 5%. Hence, there is a highly
positive correlation between income and expenditure.

RESULT:
Thus, correlation using SPSS has been executed successfully.
 8. REGRESSION
PROBLEM:
Solve the given traditional regression problem. The following table gives the food expenditure and
annual income of co-familiar fit a multiple regression equation of food expenditure on annual family income.
Family Annual Food Expenditure Annual Income
1 5.2 25
2 5.1 26
3 5.6 32
4 4.6 24
5 11.3 54
6 8.1 59
7 7.8 44
8 5.8 30
9 5.1 40
10 18.0 82

AIM:
To find the relationship between one’s family annual income and food expenditure using regression
analysis in SPSS software.

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows
Name Type Width Decimal Label Value Measure
Family Numeric 8 0 Family None Nominal
FoodExp Numeric 8 0 Annual Food None Nominal
Expenditure
Income Numeric 8 0 Annual Income None Nominal

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Go to AnalyzeRegressionLinear
Step 6 – Drag ‘Annual Food Expenditure” to the dependent variable box and ‘Annual Income’ to the
independent variable box
Step 7 – Press ‘OK’ and the output viewer will with the results.

INFERENCE:
The p-value for Annual income coefficient is .000, indicating that it is statistically significant at the 0.05
significance level.

RESULT:
Thus, regression using SPSS has been executed successfully.
 9. CHI-SQUARE TEST FOR GOODNESS OF FIT
(Based on Individual Scores)
PROBLEM:
Find whether internet has influence on cost/price comparison of products. He also wants to know the
influence of internet in case of online ordering. The level of significance will be 5%. Categorize the responses
based on 5 point scale of Never(1), Occasionally(2), Considerably(3), Almost Always(4) and Always(5). Run a
Chi Square test for results.
Cost/Price Online Order
Almost Always Always
Always Always
Almost Always Almost Always
Considerably Almost Always
Considerably Almost Always
Considerably Almost Always
Almost Always Almost Always
Almost Always Occasionally
Never Always
Always Considerably
Considerably Always
Almost Always Considerably
Almost Always Occasionally
Almost Always Almost Always
Almost Always Almost Always

AIM:
To identify the influence of internet in case of cost/price comparison and online ordering through
running Chi-square in SPSS.

HYPOTHESIS
Null Hypothesis 1: There is not much influence of internet in case of cost/price comparison
Alternative Hypothesis 1: There is much influence of internet in case of cost/price comparison
Null Hypothesis 2: There is not much influence of internet in case of online ordering
Alternative Hypothesis 2: There is much influence of internet in case of online ordering

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows:
 Name Type Width Decimal Label Value Measure
CostPrice Numeric 8 0 Cost/Price 1Never Ordinal
Comparison 2Occasionally
3Considerably
4Almost Always
5Always
OnlineOrder Numeric 8 0 Online Ordering 1Never Ordinal
2Occasionally
3Considerably
4Almost Always
5Always

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Go to AnalyzeNonparametric TestChi-Square
Step 6 – Select and drag the variables ‘Online Ordering’ and ‘Cost/Price comparison’ to the Test Variable List
Step 7 – Click OptionsSelect Descriptive check boxClick continue
Step 8 – In Chi Square dialog box click ‘OK’ to see the output

INFERENCE:
The result shows Chi-square value of 4.467 & 7.667 (df=3, N=15), p>0.05 is not significant at 3 degrees
of freedom, showing that there is no significant difference in expected and observed frequencies.

RESULT:
Thus, chi-square test using SPSS has been executed successfully.
 10. CHI-SQUARE TEST FOR GOODNESS OF FIT
(Based on Weigh Cases)
PROBLEM:
Find whether internet has influence on cost/price comparison of products. He also wants to know the
influence of internet in case of online ordering. The level of significance will be 5%. Categorize the 29
responses based on 5 point scale of Never(1), Occasionally(2), Considerably(3), Almost Always(4) and
Always(5). Run a Chi Square test for results.
Internet Influence Frequency
Never (1) 1
Occasionally (2) 1
Considerably (3) 7
Almost Always (4) 19
Always (5) 1

AIM:
To identify the influence of internet in case of cost/price comparison based on weigh cases using Chi-
square in SPSS.

HYPOTHESIS
Null Hypothesis H0: There is not much influence of internet in case of cost/price comparison
Alternative Hypothesis H1: There is much influence of internet in case of cost/price comparison

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows
Name Type Width Decimal Label Value Measure
InternetInfluence Numeric 8 0 Internet Influence None Ordinal
CostPriceFreq Numeric 8 0 Cost/Price Comparison None Ordinal

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Select Data menuWeigh CasesDialog box will open
Step 6 – Click on Weigh cases by radio button
Step 7 – Select the variable ‘Cost/Price Comparison’ and move to Frequency Variable
Step 8 – Press ‘OK’ to close the dialog box
Step 9 – The message ‘Weigh On’ should appear on the status bar at the bottom right of the window
Step 10 – Go to AnalyzeNonparametric TestChi-Square
Step 11 – Select and drag the variable ‘Internet Influence to the Test Variable List
Step 12 – Click OptionsSelect required options availablePress continue
Step 13 – In Chi Square dialog box click ‘OK’ to see the output
INFERENCE:
The result shows that Chi-square value of 42.207 (df=4, N=29), p<0.05 is significant at 4 degree of
freedom. So, we have to reject null hypothesis and accept the alternative hypothesis, that is, there is much
influence of internet in case of cost/price comparison.

RESULT:
Thus, chi-square test using SPSS has been executed successfully.
 11. CHI-SQUARE TEST FOR INDEPENDENCE
(Based on Weigh Cases)
PROBLEM:
Find whether the movie preference was dependent on location of the respondent. The responses
indicate, 75 respondents each have seen movie 3 Idiots and Dabang. Responses indicate 71 respondents from
Delhi and 79 respondents from Mumbai.
Enter the frequencies and other variables in data view as shown in the table below.
Movie Place Frequency
3 Idiots (1) Delhi (1) 42
3 Idiots (1) Mumbai (2) 33
Dabang (2) Delhi (1) 29
Dabang (2) Mumbai (2) 46

AIM:
To identify whether the movie preference was dependent on location based on weigh cases using Chi-
square for independence in SPSS.

HYPOTHESIS
Null Hypothesis H0: There is not much influence of location on the movie preference
Alternative Hypothesis H1: There is much influence of location on the movie preference

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create three variables as follows
Name Type Width Decimal Label Value Measure
Movie Numeric 8 0 3 Idiots / Dabang 13 Idiots Nominal
2 Dabang
Place Numeric 8 0 Delhi / Mumbai 1 Delhi Nominal
2 Mumbai
Frequency Numeric 8 0 Frequency None Scale

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Select Data menuWeigh CasesDialog box will open
Step 6 – Click on Weigh cases by radio button
Step 7 – Select the variable ‘Frequency’ and move to Frequency Variable
Step 8 – Press ‘OK’ to close the dialog box
Step 9 – The message ‘Weigh On’ should appear on the status bar at the bottom right of the window
Step 10 – Go to AnalyzeDescriptive StatisticsCrosstabs
Step 11 – Move ‘3 Idiots/Dabang’ to the row variable and ‘Delhi/Mumbai’ to the column variable
Step 12 – Click Statistics buttonChi-square check boxcontinue (For additional results, you can select any
of the option under nominal head to measure the strength of association between two variables)
Step13 – Go to CellsSelect Observed and Expected check boxes in counts box and row, column, total check
boxes in percentageClick continue
Step 13 – Press ‘OK’ in the main dialog box to generate the results

INFERENCE:
The Pearson Chi-square value of 4.520 (df=1, N=150) is significant at 1 degree of freedom and p<0.05.
Based on the results, it is concluded that there is much influence of location on the movie preference

RESULT:
Thus, chi-square test using SPSS has been executed successfully.
 12. SPEARMAN’S RANK CORRELATION
PROBLEM:
Find the relationship between monthly household income and retail purchase by 20 respondents through
spearman’s rank correlation.
Enter the variables in the data view as mentioned in the below table.
Household Retail
Income Purchase
1.00 10.00
5.00 25.00
0.50 10.00
10.00 100.00
3.00 35.00
3.00 30.00
7.00 100.00
8.00 100.00
10.00 150.00
0.40 8.00
0.30 6.00
0.20 3.00
0.10 2.00
0.15 2.00
0.80 10.00
5.00 30.00
6.00 30.00
7.00 20.00
8.00 60.00
1.00 10.00

AIM:
To find the relationship between monthly household income and retail purchase through spearman’s
rank correlation using SPSS.

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows
Name Type Width Decimal Label Value Measure
Hincome Numeric 8 2 Monthly Household None Ordinal
Income (Rs.Lacs)
Purchase Numeric 8 2 Retail Purchase None Ordinal
(Rs.thousand)

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Select AnalyzeDescriptive StatisticsCrosstabs
Step 6 – In the Crosstabs dialog box, enter household and retail purchase in the row and column list
respectively
Step 7 – Click Statistics buttonSelect CorrelationsClick continue
Step 8 – Press ‘OK’ to see the output viewer
INFERENCE:
The output shows that Spearman’s rank correlation is significant, r (20) = 0.942, p<0.05. As such, we
can say that, higher monthly household income leads to more retail purchases.

RESULT:
Thus, spearman’s rank correlation using SPSS has been executed successfully.
 13. MANN-WHITNEY U TEST
PROBLEM:
The sales of two retail stores of Delhi (Store 1) and Mumbai (Store 2) are compared. The sales are in Rs.
Lacs. There are 20 responses, 10 from each store. The data violates the assumptions of an independent groups t-
test. As such Mann-Whitney U test is performed.
Delhi 40 60 45 80 20 80 85 120 85 55
Mumbai 30 55 25 60 100 10 90 60 55 25

AIM:
To do Mann-Whiney U Test using SPSS for the sales comparison of two retail stores.

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows
Name Type Width Decimal Label Value Measure
RetailStore Numeric 8 0 Retail Store 1Delhi Ordinal
2Mumbai
Sale Numeric 8 0 Sale (in Rs. Lacs) None Ordinal

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Click Analyze menuNonparametric Tests2 Independent Samplesthe dialogue box will be
opened
Step 6 – Select dependent variable (Sales) in Test Variable List and Retail Store in Grouping Variable list.
Select Mann-Whitney U check box in Test Type box.
Step 7 – Click Define Groups button. A sub dialogue box will open. Enter the values (Group1= 1 & Group2= 2)
Step 8 – The Grouping Variable updates from Retailstore (??) to RetailStore (1 2)
Step 9 – Click OK to see the output.

INFERENCE:
We have to consider Z-score and two tailed P-value. The result was not significant, Z=-.987, p>.05 and no
significant differences exist in the sales of two retail stores.

RESULT:
Thus, Mann Whitney U test using SPSS has been executed successfully.
 14. WILCOXON SIGNED-RANK TEST
PROBLEM:
A Showroom manager compares the laptop sales for the year in two parts. He wants to compare the
sales of first half and second half of the year. He recorded the sales from 20 showrooms and saved their sales in
Rs. Lacs. The data violates the assumptions of a paired t-test, so Wilcoxon signed-rank test is used.
Sale 1 10 20 25 50 45 30 50 60 100 20 50 90 60 40 20 45 65 56 38 28
Sale 2 20 50 60 35 65 90 110 25 20 35 64 69 95 85 76 68 59 120 50 30

AIM:
To do Wilcoxon Signed-Rank Test using SPSS for the laptop sales comparison between first and second
half of the year

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows
Name Type Width Decimal Label Value Measure
Sale1 Numeric 8 2 Laptop Sale (Jan-Jun) None Ordinal
Sale2 Numeric 8 2 Laptop Sale (July-Dec) None Ordinal

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Click Analyze menuNonparametric Tests 2 Related Samplesthe dialogue box will be opened.
Step 5 – Select Laptop Sale (Jan-June) in variable 1 and Laptop Sale (July-Dec) in variable 2 on the left side
box. Select Wilcoxon check box.
Step 7 – Click Options  Descriptive  Continue.
Step 8 – Click Ok in 2 Related Samples dialogue box to see the output.

INFERENCE:
The output shows that, there is a significant difference in showroom sales for the first & second half of the year,
z=2.036, p<.05. The result also shows that sales are higher in second half of the year.

RESULT:
Thus, Wilcoxon Signed-Rank test using SPSS has been executed successfully.
 15. KRUSKAL-WALLIS TEST
PROGRAM:
The SPSS Vice President-Sales has developed three new training programs for increasing sales
effectiveness. There are 50 new hires in the organization. He has randomly chosen 15 people for each training
program. After 1 year, he decides to see the results. Kruskal-Wallis test is performed.
Program 1 10 12 30 50 20
Program 2 9 90 80 110 150
Program 3 10 20 30 10 20

AIM:
To identify the effectiveness of three new training programs in sales through Kruskal-Wallis test in
SPSS.

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create two variables as follows
Name Type Width Decimal Label Value Measure
Program Numeric 8 0 Sales Training 1Program 1 Ordinal
Program 2Program 2
3Program 3
Sale Numeric 8 1 Sales (Rs.Crores) None Ordinal

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Click Analyze menuNonparametric Tests K Independent Samplesthe dialogue box will be
opened.
Step 6 – Enter dependent variable (Sales) in Test Variable List. Enter independent variable (Sales Training
Program) in Grouping variable box.
Select Kruskal-Wallis H check box in Test Type box.
Step 7 – Click on Define RangeEnter the values (since we have 3 training programs starting from 1, we have
selected minimum as 1 and maximum as 3)  Click Continue.
Step 8 – Click ‘OK’ in K Independent Samples dialogue box to see the output.

INFERENCE:
The chi-square value is 3.613, p>0.05 indicates that sales is not differs significantly across three training
programs. The second training delivers maximum good results, followed by first training program. Third
training program delivers least favourable results.

RESULT:
Thus, Kruskal-Wallis test using SPSS has been executed successfully.
 16. FRIEDMAN TEST
PROGRAM:
The consumption times in minutes (for 50 beverages bottles per individual) of 20 individuals were
measured under normal weather conditions, in cold weather and in hot weather.
Normal 20 25 30 35 20 26 30 39 40 50 60 50 40 80 90 20 10 50 5 75
Hot 15 20 25 30 15 18 28 30 35 44 55 15 35 70 52 5 4 50 10 60
Cold 20 30 35 40 50 40 30 12 50 60 40 60 56 90 95 60 1 3 50 80

AIM:
To run a Friedman test using SPPS to find out the consumption times of respondents during three
different weathers.

ALGORITHM:
Step 1 – Click StartAll ProgramsSPSS for WindowsSPSS
Step 2 – Select the Variable view tab
Step 3 – Create three variables as follows
Name Type Width Decimal Label Value Measure
Normal Numeric 8 2 Normal Weather None Ordinal
Hot Numeric 8 2 Hot Weather None Ordinal
Cold Numeric 8 2 Cold Weather None Ordinal

Step 4 – Go to ‘Data View’ tab and enter the given data

Step 5 – Click Analyze menuNonparametric Tests K Related Samplesthe dialogue box will be opened.
Step 6 – Enter all three variables in Test Variables list. You may click Statistics button for extra analysis.
Step 7 – Select Friedman check box in Test Type box.
Step 8 – Click Ok in K Related Samples dialogue box to see the output.

INFERENCE:
The Chi square, X2 (df=2, N=20) = 17.844, p<.05 shows that significant differences exist in consumption times
across all the three weather conditions. The result also shows that in cold weather, consumption of beverage
slowed and in hot weather beverages were consumed minimum time as compared to other weather conditions.

RESULT:
Thus, Friedman test using SPSS has been executed successfully.
 17. TRANSPORTATION
PROBLEM:
Solve the given transportation problem using TORA.
Demand D1 D2 D3 Supply
Source
S1 5 6 7 70
S2 3 4 5 60
S3 1 3 5 40
Supply 50 80 40

AIM: To solve the given transportation problem using TORA.

ALGORITHM:
Step 1: Select the menu transportation in TORA.
Step 2: Enter the problem name, no.of source and distribution.
Step 3: Solve the problem and click the “solve problem” menu.
Step 4: Select the custom & tabulate the result.

RESULT:
Transportation using TORA is done successfully.
 18. NETWORK MODEL
(A) MINIMUM SPANNING TREE PROBLEM
PROBLEM:
To determine the minimum spanning tree using TORA.
NODES 1-2 1-3 1-4 1-5 2-3 2-4 2-5 3-6 4-5 4-6
DURATION 1 5 7 9 6 4 3 10 8 3

AIM: To solve the given network problem using TORA.

ALGORITHM:
Step 1: Click StartAll programsTORA
Step 2: Select the minimal spanning tree from networking models option
Step 3: Enter the problem title and no.of nodes
Step 4: Feed the relevant data in the input grid
Step 5: Click the solve menu and then click solve problem
Step 6: Exit TORA.

RESULT:
Thus the given network problem using TORA is executed successfully.
 19. NETWORK MODEL
(B) SHORTEST ROUTE
PROBLEM:
To determine the shortest route using TORA.
NODES 1-2 1-3 1-4 2-3 2-4 2-5 3-4 3-5 4-5
COST 4000 5400 980 4300 6200 8700 4800 7100 4900

AIM: To solve the given network problem using TORA.

ALGORITHM:
Step 1: Click StartAll programsTORA
Step 2: Select the shortest route from networking models option
Step 3: Enter the problem title and no.of nodes
Step 4: Feed the relevant data in the input grid
Step 5: Click the solve menu and then click solve problem
Step 6: Select shortest route from solve problem
Step 7: Find the shortest route from the range
Step 8: Exit TORA.

RESULT:
Thus the given network problem using TORA is executed successfully.
 20. QUEING MODEL
PROBLEM:
A harbor has a single dock to unload he containers from the incoming ships. The arrival rate and service rate of
ships at the harbor follows poison distribution. The unloading time follows exponential (negative) distribution.
The arrival and service rate are 8 ships per week respectively. Find the following.
(a) Utilization of the dock, (b) Average no.of waiting ships in queue, (c) Average no.of waiting ships in the
system, (d) Average waiting time per ship in queue, and (e) Average waiting time per ship in system.

AIM: To solve the given problem using TORA.

ALGORITHM:
Step 1: Click StartAll programsTORA
Step 2: Select queuing analysis from main menu and go to the input screen.
Step 3: Enter the problem title and no.of scenarios
Step 4: Feed the values of Lambda, Mu, No.of service, Systems limit and source limit.
Step 5: Click solve menu and save the data.
Step 6: Obtain the output by clicking ‘solve problem’
Step 7: In the output screen select ‘comparative analysis’ from the drop.

RESULT:
Thus the given queuing problem using TORA is executed successfully.
 21. LINEAR PROGRAMMING
PROBLEM:
Solve by Graphical method.
Max z = 6x1 + 8x2
Subject to 5x1 + 10x2 ≤ 60
4x1 + 4x2 ≤ 40
x1, x2 ≥ 0

AIM: To solve the given linear programming by graphical method using TORA.

ALGORITHM:
Step 1: Click StartAll programsTORA
Step 2: Select linear programming from menu.
Step 3: Enter the problem title, no.of variables and no.of constraints.
Step 4: Select the objective function whether to maximize or minimize.
Step 5: Click solve menu and save the data.
Step 6: Tabulate the result constraints.
Step 7: Results will be displayed.

RESULT:
Thus the given linear programming using TORA is executed successfully.
 22. PROJECT PLANNING
(A) CRITICAL PATH METHOD
PROBLEM:
To determine the critical path using TORA.
ACTIVITY 1-2 1-3 1-5 2-3 2-4 3-4 3-5 3-6 4-6 5-6
DURATION 8 7 12 4 10 3 5 10 7 4

AIM: To solve the critical path using TORA.

ALGORITHM:
Step 1: Click StartAll programsTORA
Step 2: Select project planningcritical path method from main menu.
Step 3: Enter the problem title and press ‘enter key’.
Step 4: Enter the node and duration in the input grid.
Step 5: Click solve menu and save the data.
Step 6: Obtain the output by clicking ‘solve problem’.
Step 7: Select CPM Bar chart.

RESULT:
Thus the critical method using TORA is executed successfully.
 23. PROJECT PLANNING
(B) PROGRAM EVALUATION REVIEW TECHNIQUE
PROBLEM:
To determine the PERT for the project using TORA.
ROW FROM TO ACTIVITY a m b
NODE NODE
1 1 2 A 3:00 6:00 15:00
2 1 6 B 2:00 5:00 14:00
3 2 3 C 6:00 12:00 30:00
4 2 4 D 2:00 5:00 8:00
5 3 5 E 5:00 11:00 17:00
6 4 5 F 8:00 6:00 15:00
7 5 8 G 1:00 4:00 7:00
8 6 7 H 8:00 4:00 27:00
9 7 8 I 4:00 19:00 28:00

AIM: To solve PERT using TORA.

ALGORITHM:
Step 1: Click StartAll programsTORA
Step 2: Select project planningPERT method from main menu.
Step 3: Enter the problem title and press ‘enter key’.
Step 4: Enter mode and time estimator in the input grid.
Step 5: Click solve menu and save the data.
Step 6: Obtain the output by clicking ‘solve problem’.
Step 7: Go to the output screen and choose activity mean, variance and also PERT calculations.
Step 8: Results will be displayed.

RESULT:
Thus the PERT calculation using TORA is executed successfully.
 24. FORECASTING
PROBLEM:
Monthly sales detail of a company are given and based on the given details forecast the sales for the next year.
PERIOD MONTH ACTUAL SALES
1 Jan-12 12,00,000
2 Feb-12 15,00,000
3 Mar-12 12,80,000
4 Apr-12 13,50,000
5 May-12 10,20,000
6 Jun-12 14,00,000
7 Jul-12 15,40,000
8 Aug-12 11,00,000
9 Sep-12 14,50,000
10 Oct-12 14,00,000
11 Nov-12 13,20,000
12 Dec-12 12,80,000

AIM: To forecast the sales of company using MS Excel.

ALGORITHM:
Step 1: Click StartAll programsMs OfficeMicrosoft Office Excel
Step 2: Enter the given problem in the excel sheet.
Step 3: Add a column forecast next to the actual sale column.
Step 4: Select the cell from which forecast have to start and enter the formula,
FORECAST(x,known_y's,known_x's)
Step 5: Drag the full handle to forecast for the rest of the data.
Step 6: Put all the time value cost of the first set of problem at zero.
Step 7: Select the all columns and go to insert tabinsert chartline chart.
Step 8: Chart will be displayed showing the comparison of both.

RESULT:
Hence the sales forecasting is done using MS excel.
 25. RISK ANALYSIS
PROBLEM:
Given below is the annual return of 2 companies which company is better for investment.
RATE OF RETURN -
YEAR SHARES
Company 1 Company 2
1 2.2 1.1
2 -3.5 1.1
3 11.6 4.2
4 -2.1 7.1
5 -3.1 -3.8
6 -8.8 -2.9
7 1.4 -9.1
8 1.4 31.1
9 -5.8 33.9
10 5.5 13.6
11 10.1 30.4
12 -4.4 -4.3
13 -5.3 -12.9
14 21.7 22.1
15 -5.5 8.4
16 -2.5 -5.4
17 -3.61 28.7
18 -1.6 15.6
19 2.3 -9.6
20 13.5

AIM: To do risk analysis of given data using MS Excel.

ALGORITHM:
Step 1: Click StartAll programsMs OfficeMicrosoft Office Excel
Step 2: Enter the data into the excel sheet.
Step 3: Go to data tabData analysisDescriptive statisitics.
 Input range – select the values of both companies with heading.
 Select labels in first row.
 Select any empty cell for ‘output range’.
 Select summary statisticsClick ‘OK’
Step 4: It displays the descriptive statistics of both the companies.
Step 5: Save the worksheet.

INFERENCE:
We can see the standard deviation, sample variance and range are all greater for company 2 compared to the
company 1. Hence, it is better for investment.

RESULT:
Hence the risk analysis is done using MS excel.