Page 1 of 66

EX.NO:
TESTING THE RELATIONSHIP
BETWEEN THE VARIABLES USING
DATE : CROSSTABS IN SPSS 14.0

Testing the relationship between level of education & level of marriage

adjustment among married women’s at 95% of confidence interval using
cross tabs.

MARRIAGE ADJUSTMENT Total

VERY LOW HIGH VERY
LOW HIGH
LEVEL OF COLLEGE 24 97 62 88 271
EDUCATION HIGH 22 28 30 41 121
SCHOOL
MIDDLE 32 10 11 20 73
SCHOOL
Total 78 135 103 149 465

AIM:

To test the relationship between the variable using cross tabs.

ALGORITHM:

STEP 1: Start All programsSPSS for windows-SPSS 14.0

STEP 2: In variable view enter name as education, range, frequency.

STEP 3: Go to data view Enter the given data as for the frequency (as
in the form of matrix view).
 Page 2 of 66

STEP 4: Go to data weight casesselect weight cases by- frequency

variable put the frequency value Click ok

STEP 5: Go to analyze Descriptive statistics-Cross tabs- select row as

education and columns range.

STEP6: Select statisticsselect chi-squarecontinue and in

crosstabsClick ok.

INPUT

OUTPUT
 Page 3 of 66

RESULT:

The Calculated Pearson Chi Square Value is 0.000 which is lesser than
the expected value of 0.05 at 95 % of confidence interval. Hence there is
enough evidence to conclude that level of education is associated with
Marriage Adjustment among married women’s.

EX.NO : TESTING THE RELATIONSHIP BETWEEN THE

DATE : VARIABLES USING CROSSTABS IN SPSS 14.0

Testing the relationship between educational background & Type of

people (i.e. Smokers or Non Smokers) at 95% of confidence interval
using cross tabs.

EDUCATIONAL TYPES OF PEOPLE

BACKCROUND SMOKERS NON TOTAL
SMOKERS
LITERATE 83 57 140
ILLITERATE 45 68 113
TOTAL 128 125 253
 Page 4 of 66

AIM:

To test the relationship between the variable using cross tabs.

ALGORITHM:

STEP1: <Start> <All Programs> <SPSS for windows-SPSS 14.0>

STEP2: In Variable views – Enter the variables as Educational

background, Type of People & Frequency.

STEP 3: Go to Data view- enter the given data in the frequency column
(as in the form of matrix view).

STEP 4: Go to <Data> <Weight cases> <Weight cases by> and drop

the frequency variable in the column. Click ok

STEP 5: Go to <Analyze> <Descriptive Statistics> <Cross tabs> select

row as Educational Background and columns as Type of People.

STEP 6: Select Statistics and tick Chi-square and click Continue and
click ok.
 Page 5 of 66

INPUT
 Page 6 of 66

OUTPUT
 Page 7 of 66

RESULT:

The calculated person chi squared value is 0.002 which is lesser then
expected value of 0.05. So there is a relationship among education
background and type of people.

TESTING THE DIFFERENCE BETWEEN THREE

EX.NO: INDEPENDENTSAMPLESUSING KRUSKAL- WALLIS
TEST
DATE :

AIM:

To test the difference between 3 methods of teaching (Independent

sample) using Kruskal Wallis test.

ALGORITHM:

STEP 1: Start-All programs-spss for windows – SPSS 14.0.

STEP 2: Select variable view and enter name as score and method.

STEP 3: Go to data view – enter the frequency in the score and enter the
method.
 Page 8 of 66

STEP4: Go to <Analyze> <Nonparametric test><K Independent

samples>

STEP 5: Select test variable as Score and Group variable as method .

Click the test type as Kruskal Wallis-H. Click Ok.

INPUT
 Page 9 of 66

OUTPUT
Page 10 of 66
 Page 11 of 66

RESULT:

The calculated value is 0.023 which is lesser then the expected value
of 0.05 hence we conclude that is difference in teaching methodology
among professors.

EX.NO: TESTING THE DIFFERENCE BETWEEN TWO

DATE : INDEPENDENT SAMPLING USING MANN-
 Page 12 of 66

WHITNEY U-TEST

AIM:

To Test the Difference between the scores produced by two

different professors using two Independent Sample Using Mann-Whitney
U –test.

PROCEDURE:

STEP 1: Start-All program-SPSS for window-SPSS 14.0 for windows

evaluation version –select.

STEP 2: Select variable views – In Name Column enter two variable

named scores and professors.

STEP 3: Set decimal value 0

STEP 4: In data view – enter dada in score and in professor enter the
group value.

STEP5 : In <Analyze> <Nonparametric test> <Two independent

samples>

STEP 6: Select test variables as “Score”.

 Page 13 of 66

STEP 7: Select “Professor” as grouping variable. Define the group as 1

& 2.

STEP 8: Select test types as Mann-Whitney U

STEP 9: In Options click statistics and tick descriptives. Click continue

STEP 10: Click Ok.

INPUT
 Page 14 of 66

OUTPUT
 Page 15 of 66

RESULT:

The calculated value is 0.035 which is lesser then the expected value of
0.05 there is a difference among professors.
 Page 16 of 66

EX.NO: TESTING THE GOODNESS OF FIT

DATE : USING
CHI-SQUARE (NON PARAMETIC
TEST)

A Machine has a record of producing 80 % Excellent, 17% good, and 3 %

unacceptable parts. After extensive repairs, a sample of 200 produced 157
excellent, 42 good, and 1 unacceptable part. Have the repairs changed the
nature of the output of the machine? Find with 95 % confidence interval.

AIM:

To Test the goodness of fit in machines after extensive overhauling

using chi-square (non-parametric test).

ALGORITHM:

STEP 1: <Start> <All programs> < SPSS for windows SPSS 14.0>

STEP 2: In Variable view enters two variables named as quality and

count.

STEP 3: In data view enter the given data. Go to <Data> <Weight

cases> and click count and drop in the box. Click Ok

STEP 4: Go to <Analyze> <Nonparametric> <Chi Square>.

STEP 5: Select Quality as test variable, and enter the values as 0.80,
0.17and 0.03 –Ok
 Page 17 of 66

INPUT
 Page 18 of 66

OUTPUT
 Page 19 of 66

RESULT:

The calculated value is 0.047 (ASYMP.SIG), which is lesser then the

expected value of 0.05. So there is a difference among the performance of
machines after overhauling

TESTING THE LINEAR ASSOCIATION BETWEEN

EX.NO: VARIABLES USING PEARSON CORRELATION IN
DATE : SPSS 14.0
 Page 20 of 66

HOURS 2 24 2 1 34 2 19 1 20 1 26 1 28 2 23
STUDIE 4 0 8 4 9 9 8 7
D
EXAM 6 73 6 4 107 7 52 5 55 6 63 7 79 8 78
SCORES 8 5 8 3 5 1 2 0
AIM:

To Test the Linear Association between variables using Pearson

Correlation using SPSS 14.0.

ALGORITHM:

STEP 1: Start> <All Programs> <SPSS for Windows Evaluation Version

14.0>

STEP 2: In variable view enter the variable named as “Hours spent,

“Scores”.

STEP 3: In data view enter the given data for hours spent and marks
obtained.

STEP 4: Go to <Analyze> <Correlate> <Bi variate Correlation> Select

and drop the variables and select the check box “Pearson correlation
coefficient”. Click ok. The output will be displayed.

STEP 5: Go to <Regression>< Linear >.In Dependent Column drop the

variable named “Marks obtained” and in independent variable column
drop the variable named “Hours spent”.
 Page 21 of 66

STEP6: In Plots, Set Y as dependent and X as ADJPRD (ADJ

PREDICTED) and histogram and normality probability plot select both.
In linear regression -> Click ok .

INPUT
 Page 22 of 66

OUTPUT
 Page 23 of 66

RESULT:

The calculated value is 0.000 and Pearson Chi-square value is 0.840.

This shows there is a Positive higher relationship among hours studied
and marks obtained.
 Page 24 of 66

EX.NO: TEST THE NORMALITY OF THE GIVEN

DATE : DATA SET USING KOLMOGOROV ONE
SAMPLE TEST

The Total Leisure hour per week of 30 employees working in Barclays

bank has been observed by researcher to analyze the work life
balance. Using Kolmogorov one sample test find whether the given
data is normally distributed.

14 16 12 18 11 11 17 10 22 13
16 24 17 13 18 25 10 20 18 15
19 23 19 22 21 15 19 22 13 16

AIM:

To prepare the test normality of the given data set using

Kolmogorov one sample test.

ALGORITHM:

STEP 1: Start->all programs SPSS for windows->SPSS14.0

STEP 2: Select the variable view->enter name as hours set the decimal
value as 0

STEP 3: Go to Data view->enter the frequency for hours.

STEP 4: Go to <Analyze> <Descriptive statistics> <Explore>

STEP 5: Select the variable named “Hours” in independent list.

STEP 6: Click Plots Check Histogram and Normality plots with tests.
Click Continue
 Page 25 of 66

INPUT

HYPOTHESIS:

HO: There is no difference among received data (normally distributed).

H1: There is difference among the data (not normally distributed).

OUPUT
Page 26 of 66
 Page 27 of 66

RESULT:

The Skeweness and kurtosis value obtained is -0.190 and -0.5 which is
nearer to zero.

Hence the data is normally distributed and we unable to reject the null
hypothesis.
 Page 28 of 66

EX.NO: LINEAR PROGRAMMING USING TORA-

DATE: OPERATIONS RESEARCH SOFTWARE.

AIM:

To Solve the Linear programming using TORA.

ALGORITHM:

STEP 1: Start all programs TORA.

STEP 2: Choose the Type of problem to be solved
(Linear programming)
STEP 3: Enter the given data.
STEP 4: Click the button “Solve Menu”
STEP 5: By Clicking “Yes” save the data.
STEP 6: Click<SolveProblem><Algebraic><Final Solution>.

The output will be displayed. Exit Tora.

 Page 29 of 66

RESULT:

Thus the linear programming solved using graphical method of TORA.

EX.NO: FINDING LINEAR RELATIONSHIP

DATE: BETWEEN THE VARIABLES IN
 Page 30 of 66

REGRESSION USING SPSS 14.0

SALES 167.9 168 155 158.5 159.9 162 165 174.5

PRICE
ASSESE 152.7 163.8 167.6 127.3 155.7 169 187.1 153.6
D
VALUV
E

AIM:

Finding the Linear Relationship between the variables in regression

using SPSS 14 .0.

ALGORITHM:

STEP 1: <Start> <All programs> < SPSS For windows Evaluation

Version>

STEP 2: In variable view, type two variables named “Sales” and

“Assessed value”

STEP 3: Go to Data view enter sales price frequency assessed value

frequency.

STEP 4: Go to analyze regression linear (select it).

 Page 31 of 66

STEP 5: Select dependent as sales price and independent as assessed

value.

STEP 6: Go to plots select y axis as dependent x axis as adjusted

prediction.

STEP 7: Select Histogram and Normal probability plot continue.

STEP 8: Click OK.

 Page 32 of 66

INPUT
 Page 33 of 66

OUTPUT
 Page 34 of 66

OUTPUT
 Page 35 of 66

OUTPUT
 Page 36 of 66

RESULT:

The R square value obtained is 0.831 which says that 83.1 % the model is
said to be fit. The co efficient table shows that the significance is 0.000.
This shows the 100% there is a relationship among assessed value and
sales price.

EX.NO: FINDING THE LINEAR TREND LINES USING

DATE: MICROSOFT EXCEL 2007

AIM:

To find the linear trend lines using Microsoft excel 2007.

ALGORITHM:
 Page 37 of 66

STEP 1: Start all programs MS EXCEL 2007.

STEP 2: Create 2 rows and 2 columns as year and sales revenue and
type the given data.

STEP 3: Drag the sales row column and Insert a Line chart. <Insert>
<Line> <2D>

STEP 4: Right Click the X axis (in chart) and click the “select data”.

STEP 5: Dialogue box will be appearing named “Select data source”.

STEP 6: Click “Edit” on Horizontal axis levels and select and drag the
“Year” column by using the range in the axis level (i.e. dialogue box).

STEP 7: Click the plotting of the chart and then press button on the
top. Select data levels → above.

STEP 8: For Finding Trend Click <Layout>< Trend line>< More

Trend line options>.

STEP 9: A dialogue box will be appearing named “Format trend lines”.

STEP 10: Select the regression type as “Linear”.

STEP 11: Find the forecast for 2 periods by entering “2” in forward
column. A linear trend line will be plotted in the chart.

STEP 12: Notice the trend line and corresponding Revenue in the y
axis.
 Page 38 of 66

INPUT
 Page 39 of 66

OUTPUT

SALES REVENUE FOR MERCEDES BENZ CANADA INC

Rs. 80,000.00
Rs. 70,000.00
Rs. 70,000.00 Rs. 66,000.00
Rs. 60,000.00
Rs. 60,000.00
SALES REVENUE IN `

Rs. 50,000.00 SALES REVENUE

Rs. 50,000.00
Rs. 40,000.00
Rs. 40,000.00 Linear (SALES
REVENUE)
Rs. 30,000.00
Rs. 20,000.00 Moving average (SALES
Rs. 20,000.00 REVENUE)

Rs. 10,000.00

Rs. 0.00
2008 2009 2010 2011 2012 2013
YEARS
Page 40 of 66
 Page 41 of 66

RESULT:

The Output has been verified and the revenue trend for the
forthcoming year is nearly 80,000.

EX.NO: FIND THE TRANSPORTATION COST

DATE: USING TORA

A Texas company is shipping units from three factories to 5 distribution

centres. The total supply and the total demand are equal. The cost to ship
one unit from each factory to each distribution centre is given. Minimize
the total shipping cost.

Unit shipping Dall El Fort Galves Houst Supply

costs as Paso Worth ton on (units)
Austin $20 $48 $10 $30 $40 100
Beaumont $70 $60 $55 $90 $70 80
 Page 42 of 66

Corpus
Christi $45 $80 $50 $30 $60 150
Demand
(units) 50 70 65 55 90 330\330

AIM:

To find the transportation cost using TORA

ALGORITHM:

STEP 1: Start all programs TORA.

STEP 2: Choose the Type of problem to be solved
(Transportation Model)
STEP 3: Enter the given data.
STEP 4: Click the button “Solve Menu”
STEP 5: By Clicking “Yes” save the data.
STEP6: Click<Solve Problem> <Final Solution>.

The output will be displayed. Exit Tora.

INPUT
 Page 43 of 66

OUTPUT

RESULT:
 Page 44 of 66

Thus the transportation cost is 1020 and output is verified.

EX.NO: PERFORMING T-TEST USING SPSS 14.0

DATE:

Average systolic blood pressure of a normal male is supposed to be about

129. Measurements of systolic blood pressure on a sample of 12 adult
males from a community whose dietary habits are suspected of causing
high blood pressure are listed below. Test whether the BP of males are
normal.

115 134 131

143 130 154
119 137 155
130 110 138

AIM:

To Perform T-test using SPSS 14.0

ALGORITHM:
 Page 45 of 66

STEP 1: Enter the values into a variable and previous to that create a
new variable named “BP” in the variable view

STEP 2: <Analyze> <Compare means> <One sample t test>

STEP 3: Select “Blood pressure” as the test variable and enter “129”
(the null hypothesis value-normal BP) as the test value.

STEP 4: Click the “Options” button and enter the appropriate confidence
level (98%, since alpha=0.01 for this one tailed test) if needed click
“continue “to close the option.

TEST STATISTICS

From the output T=0.9939 with 11 degree of freedom

P-value=1/2(sig(2-tailed))=1/2(0.3416)=0.1708

INPUT
 Page 46 of 66

OUTPUT
Page 47 of 66
 Page 48 of 66

RESULT:

The calculated value is 0.171 which is greater than the expected value of
0.01. So we unable to Reject null hypothesis. The Blood Pressure is
normal for the males.

EX.NO: PERFORMING MANOVA USING SPSS

DATE : 14.0(MULTIVARIATE ANALYSIS OF
VARIANCE)

MAL MAL MAL FEMAL FEMAL FEMAL FEMAL FEMAL FEMAL

GENDER E E E E E E E E E
ENG 34 56 67 65 43 35 37 78 80
MAT 43 54 53 43 77 69 87 78 78

AIM:

To compare the English and math’s score among girls and boys students
using MANOVA.

ALGORITHM:

1. Start → all programs→ SPSS 14.0 windows evaluation version.

2. In the variable view define the variables and mention the required
details.
(i.e.) create 3 variables namely gender English, maths.
3. In gender assume 1 as male and 2 as female.
4. In the data view enters the given scores.
 Page 49 of 66

5. Go to analyze → general linear model → multivariate.

6. Drop the variable named English and math’s in the dependent
variables column’
7. Drop the variable named “gender” in the fixed factor(s) column.
8. Click options drop the gender (OVER ALL) variable into the box
which is displayed in the right side.(i.e. display means for column)
9. Tick the check box named “compare main effects”.
10.Tick the check box named “descriptive statistics”.
11.Select “BONFERRONI” as a confidence interval adjustment.
12.Check for significant level (0.05).Click ok.The output will be
displayed.

INPUT
 Page 50 of 66

OUTPUT
 Page 51 of 66

RESULT:

(a) By comparing the mean, girl’s students were dominated in

the mathematics score than boys.
(i.e) Mean for girls (MATHS)-72.3
Mean for boys - 51.8

(b)With regards to English, there is no considerable difference

among boys and girls.

(c) Notice the sig value for English is 0.314 and for Maths is
0.000.

Hence there is a difference among girls and boys among mathematics

score.
 Page 52 of 66

EX.NO: LINEAR PROGRAMMING USING TORA

DATE :

Solve the following integer linear programming using Gomory’s cutting

plane algorithm.

Max Z=-5x1-6x2.

Subject to the constraints

-X1-X2 ≤ -2

-4X1-X2+X3= -4

x1,x2 ≥ 0

AIM:

To solve the Integer Linear Programming Problem using the

TORA software.

ALGORITHM:

STEP 1: Start all programs TORA.

STEP 2: Choose the Type of problem to be solved
(Linea Programming)
STEP 3: Enter the given data.
STEP 4: Click the button “Solve Menu”
STEP 5: By Clicking “Yes” save the data.
STEP6: Click<SolveProblem><Algebraic><Final Solution>
STEP7: View the solution and print the solution
Page 53 of 66
 Page 54 of 66

OUTPUT
 Page 55 of 66

EX.NO:
FINDING BEST DESCRIMINATOR IN
DATE:
CREDIT WORTHINESS USING
DISCRIMINANT ANALYSIS IN SPSS

IDBI Bank has been in the business and issuing credit cards for its
customers.

During the last 2 years their repayment default has shot up considerably.
Even though the bank charges a penalty interest on all late payments, this
high default rate is putting a lot of pressure on the banks recovery
mechanism and has now begun to impact its profitability in this activity.
The problem appears to be the credit appraisal mechanism used by the
bank to evaluate credit card applicants at the time of credit card
allotment. Hence the bank desires to revamp its appraisal system using its
past experience.

To determine this they have conducted a suitable research. Initially the

variables that have an impact on consumers credit Worthiness. Suggest
the bank on which criteria the loan can be approved based on
discrimination analysis.

FORMULA Y = a + k1.x1 + k2.x2…kn.xn…

 Page 56 of 66

AIM:

To discriminate the variables using discriminant analysis to find

the criteria for sanctioning the loan for new applicants.

ALGORITHM:

STEP 1: Enter the given data

 STEP 1: <Analyze><Classify><Discriminant>
 STEP 2: Select Previously defaulted as the grouping variable
 STEP 3: Select Years with current employer, Years at current
address, Debt to income ratio (x100), and Credit card debt in
thousands as the independent variables.
 STEP 4: Select validate as the selection variable.
 STEP 5: Select previously defaulted and click Define Range.
 STEP 6: Type 0 as the minimum.
 STEP 7: Type 1 as the maximum.
 STEP 8: Click Continue.
 STEP 9: Select validate and click Value in the Discriminant
Analysis dialog box.
 STEP 10: Type 1 as the value for selection variable.
 Page 57 of 66

 STEP 11: Click Continue.

 STEP 12: Click Statistics in the Discriminant Analysis dialogbox.
 STEP 13: Select Means, Univariate ANOVAs, and Box's M in the
Descriptives group.
 STEP 14: Select Fisher's and Unstandardized in the Function
Coefficients group.
 STEP 15: Select Within-groups correlation in the Matrices group.
 STEP 16: Select Summary table and Leave-one-out
classification.
 STEP 17: Click Continue.
 STEP 18: Click Save in the Discriminant Analysis dialog box.
 STEP 19: Select Predicted group membership and Probabilities
of group membership.
 STEP 20: Click Continue.
 Click OK in the Discriminant Analysis dialog box

These selections produce a discriminant model based on Years with

current employer, Years at current address, Debt to income ratio (x100),
and Credit card debt in thousands
 Page 58 of 66

OUTPUT

Go to Canonical Discriminant function coefficients.

Equation is Z = 0.194 (Age) + 0.000 (Income) + 0.160(Years of

Marriage) – 9.076

Z = 0.907 (Age) + 0.924 (Income) + (0.285) (Years of Marriage)

The best discriminator is income.

 Page 59 of 66

Discriminant criterion that would enable the IDBI to classify future

applicants in to high risk and low risk categories using the discriminant
function.

Therefore we get -1.269 as high risk and 1.269 as low risk.

 Page 60 of 66

RESULT:

The Discriminant score given in the last column are the predictors
of high risk and low risk . The value is which is obtained above 1.269 is
above risk and to others belong to low risk. The IDBI bank manager can
issue credit cards based on the above criteria.
 Page 61 of 66

EX.NO:
FINDING SUMMARY STATISTICS USING
DATE:
MICROSOFT EXCEL

The operating costs of the vehicle used by your company’s sales people
are too high. The majocomponent of operating expense is fuel cost; to
analyze fuel costs, you collect mileage data from the company’s two
wheelers for the previous month. Use Excel sheet for calculation.

MPL 27 29 33 21 21 12 16 25 8 17 24 34 38 15 19 19 41

Find out the

• Summary statistics.
• Histogram analysis.
• Rank and Percentile analysis tool.

AIM:

To find the Summary Statistics using Microsoft excel 2007.

ALGORITHM:

STEP 1: Start all programs MS EXCEL 2007.

STEP2: Enter the given data.

 Page 62 of 66

STEP 3: Open the Data Analysis Tool bar in Data Tab.

STEP4: Select Descriptive statistics.

STEP 5: Give the Input Range.

STEP 6: Click Summary Statistics , Confidence level for mean ,Kth

Smallest and Kth Largest.

STEP 7: Click OK.

STEP 8: Draw the Histogram Clicking Histogram in the Data tool tab
for the given data.

STEP 9: Find the Rank and percentile for the given data using “Rank
and Percentile in the data tab

INPUT
 Page 63 of 66

OUTPUT-SUMMARY STATISTICS

   
Mean 23.47059
Standard Error 2.234617
Median 21
Mode 21
Standard
Deviation 9.213561
Sample Variance 84.88971
Kurtosis -0.54692
Skewness 0.361053
Range 33
Minimum 8
Maximum 41
Sum 399
Count 17
 Page 64 of 66

HISTOGRAM

HISTOGRAM ANALYSIS
7
6
5
4 f(x) = 0.11 x + 1.03
Axis Title

R² = 0.32
3 Linear ()
2
1
0
5 10 15 20 25 30 35
Axis Title

RANK AND PERCENTILE

Colum Percen
Point n1 Rank t
100.00
17 41 1 %
13 38 2 93.70%
12 34 3 87.50%
3 33 4 81.20%
2 29 5 75.00%
1 27 6 68.70%
8 25 7 62.50%
11 24 8 56.20%
4 21 9 43.70%
5 21 9 43.70%
15 19 11 31.20%
16 19 11 31.20%
10 17 13 25.00%
7 16 14 18.70%
14 15 15 12.50%
 Page 65 of 65

6 12 16 6.20%
9 8 17 0.00%

RESULT:

Summary statistics output Generated and verified.