You are on page 1of 11

SPSS Exercise

Comparing Means:
One or Two Samples t-Tests

t- Test and Z-Tests are commonly used for making comparisons between the means of
the two samples or between some standard value and the mean of one sample.

One sample test:


A Business school in its advertisement claims that the average salary of its graduates in a
particular lean year is at par (or greater) with average salary offered at the top five
business schools. A sample of 30 graduates from the business school, whose claim was to
be verified, was taken at random. There salaries are given at random below:
Salary (000)
750
600
600
650
700
780
860
810
780
670
690
550
610
715
755
770
680
670
740
760
775
845
870
640
690
715
630
685
780
635
Average salary in that year was 7,50,000
H0: There is no difference between the average salary of the business school in
question and the average salary of the top five business schools.

Syntax Analyse-Compare means-one sample test


Fill in test value as 750

Results:
One-Sample Statistics
N Mean Std. Std. Error
Deviation Mean
salary of 30 713.50 81.26 14.84
the
graduate
student

One-Sample Test
Test Value
= 750
t df Sig. (2- Mean 95%
tailed) Difference Confidenc
e Interval
of the
Difference
Lower Upper
salary of -2.460 29 .020 -36.50 -66.84 -6.16
the
graduate
student

Result: Since the p value has come out to be .020 therefore the difference is significant to
reject the null hypothesis.

Paired t-test
1. A corporate training institution claimed that its training program can greatly enhance
the efficiency of the call centre employees. A big call centre sent some of its employees
for the training program. The efficiency was measured by the no. of deals closed by each
employee in a one month period. Data was collected for a one month period before
sending the employees for the training program. After the training program the data was
again collected on the same program. After the training program, data was collected on
the same employees for a month period.
Variables: Employee, before, after
Data View:

Emp before after


1 41 44
2 35 36
3 40 48
4 50 47
5 39 40
6 45 52
7 35 35
8 36 51
9 44 46
10 40 55
11 46 39
12 42 40
13 37 36
14 34 39
15 38 50
16 42 46
17 46 49
18 39 42
19 40 51
20 45 37
H0: There is no significant diff between employees before and after the training
program.

H1: There is sig diff between employees before and after the training program.

Syntax:
Analyse-Compare means-paired sample t-test

Paired Samples Statistics

Std. Error
Mean N Std. Deviation Mean
Pair 1 before 40.70 20 4.318 .965
after 44.15 20 6.158 1.377

Paired Samples Correlations

N Correlation Sig.
Pair 1 before & after 20 .281 .230
Paired Samples Test

Paired Differences
95% Confidence Interval
of the Difference
Std. Error
Mean Std. Deviation Mean Lower Upper t df Sig. (2-tailed)
Pair 1 before - after -3.450 6.452 1.443 -6.470 -.430 -2.391 19 .027

Since the p value is coming out to be .027 which is very much lower than .05 so the null
hypothesis is rejected at 5% level of significance.

Chi Square Test:


Scale prerequisite: nominal scale
To find out the significance of association between educational background of PGDBM
students and their performance in terms of grade.
Both the variables are coded as code and grade code representing educational
background and grade obtained. Educational background their codes are given below:
Educational
Background Code
B.com. 1
B.E. 2
B.Sc. 3
BBA. 4
B.A. 5

Grade codes are as follows:

Grade obtained: grade code


A 1
B 2
C 3
These two variables cross tabulated for twenty five observations. A cross Tabulation with
a chi-square test is performed

Syntax: Analyse- Descriptive- cross tabs- select one variable in row and the other one in
column.

Ho: There is no relationship between the grades obtained and educational background of
the students P=0.117
H1: There is relationship between the grades obtained and educational background of the
students
Case Processing Summary

Cases

Valid Missing Total

N Percent N Percent N Percent

educational back groubd of 25 96.2% 1 3.8% 26 100.0%


the student * grades obtained

educational back ground of the student * grades obtained Cross tabulation

Count

grades obtained

a B C Total

educational back groubd of B.Com 1 2 2 5


the student
B.E 4 1 0 5

B.SC. 0 2 3 5

BBA 1 2 2 5

5 1 0 4 5

Total 7 7 11 25

Chi-Square Tests

Asymp. Sig. (2-


Value Df sided)

a .117
Pearson Chi-Square 12.857 8

Likelihood Ratio 15.868 8 .044

Linear-by-Linear Association 2.240 1 .135

N of Valid Cases 25

a. 15 cells (100.0%) have expected count less than 5. The minimum


expected count is 1.40.

CONCLUSION: SINCE THE PVALUE OF NULL HYPOTHESIS BEING TRU IS


GREATER THAN ALPHA 0.05 THEREFORE, ACCEPT THE NULL HYPOTHESIS
AND CONCLUDE THAT TERE IS NO RELATIONSHIP BETWEEN TH E TWO
VARIABLES
ANOVA-
SCALE PREREQUISITE
Dependent variable- Metric (Interval or ratio scale)
Independent Variable-Non Metric (Nominal or ordinal)

Case: This problem relates to the taste/ quality of food dishes served to 28 customers in Taj Group Hotel
Chain. The customers, who are basically from HIG, were asked to give their opinion about the quality/taste
of the four common non-vegetarian dishes served to them. The following are the common dishes:
Code Dish Name:
Dish 1(not 2 3 4 5 6 7 8 9 10(most
type like at preferred)
all
1 Chicken
Platter
2 Honey
Chicken
3 Chicken
Spinach
4 Tandoori
Chicken

1 Chicken Platter
2 Honey Chicken
3 Chicken Spinach
4 Tandoori Chicken
The Taj Group wants to test, which of the above mentioned groups of dishes are preferred by HIG
customers. At random 28 customers are asked for their preference on a scale of 10(1=not liked at all, and
10= most preferred) and these data have been tabulated.

Dish type rating


1 6
1 7
1 8
1 5
1 9
1 8
1 7
2 8
2 8
2 9
2 8
2 7
2 9
2 8
3 7
3 6
3 6
3 5
3 7
3 7
3 5
4 6
4 6
4 7
4 6
4 8
4 7
4 6

Syntax- Analyse- Compare Mean-One Way ANOVA- Options- Descriptive- Post Hoc-
Scheffe test (to compare which of the groups differ significantly).

Ho: Mean rating for all the dishes are same.


H1: Mean rating for at least two of the groups differs significantly.

Descriptive

PREFERENCE GRADE
95% Confidence Interval for
Mean

N Mean Std. Deviation Std. Error Lower Bound Upper Bound Minimum Maximum
CHICKEN PLATTER 7 7.14 1.345 .508 5.90 8.39 5 9
HONEY CHIKEN 7 8.14 .690 .261 7.50 8.78 7 9
CHICKEN SPINACH 7 6.14 .900 .340 5.31 6.97 5 7
TANDOORI CHICKEN 7 6.57 .787 .297 5.84 7.30 6 8
Total 28 7.00 1.186 .224 6.54 7.46 5 9

ANOVA

PREFERENCE GRADE
Sum of
Squares df Mean Square F Sig.
Between Groups 15.714 3 5.238 5.641 .005
Within Groups 22.286 24 .929
Total 38.000 27

Post Hoc (To see which groups differ significantly in terms of rating)

Multiple Comparisons

Dependent Variable: PREFERENCE GRADE


Scheffe

95% Confidence Interval


Mean
(I) DISH SELLECTED BY (J) DISH SELLECTED BY Difference
THE RESPONDENT THE RESPONDENT (I-J) Std. Error Sig. Upper Bound Lower Bound
CHICKEN PLATTER HONEY CHIKEN -1.000 .515 .312 -2.55 .55
CHICKEN SPINACH 1.000 .515 .312 -.55 2.55
TANDOORI CHICKEN .571 .515 .747 -.98 2.12
HONEY CHIKEN CHICKEN PLATTER 1.000 .515 .312 -.55 2.55
CHICKEN SPINACH 2.000(*) .515 .008 .45 3.55
TANDOORI CHICKEN 1.571(*) .515 .046 .02 3.12
CHICKEN SPINACH CHICKEN PLATTER -1.000 .515 .312 -2.55 .55
HONEY CHIKEN -2.000(*) .515 .008 -3.55 -.45
TANDOORI CHICKEN -.429 .515 .874 -1.98 1.12
TANDOORI CHICKEN CHICKEN PLATTER -.571 .515 .747 -2.12 .98
HONEY CHIKEN -1.571(*) .515 .046 -3.12 -.02
CHICKEN SPINACH .429 .515 .874 -1.12 1.98
* The mean difference is significant at the .05 level.

Refer table2; p value has come out to be .005<.05 therefore null hypothesis is rejected
and it is concluded that the mean rating scale is not same.

Table: Multiple Comparisons: P value where ever it is less that .05 is sig.
Honey Chicken-Chicken Spinach- .008<.05- Difference is significant
Honey chicken Tandoori Chicken-.46>.05-- Difference is significant.

Regression Analysis

Scale perquisite: Interval/ratio Scale


Armands Pizza Parlous is a chain of Italian Food restaurants located in a five state area.
The most successful locations for Armands have been near college campuses. The
manager believes that the quarterly sales of these restaurants (denoted by Y) are related
positively to the size of the student population (denoted by X); that is the restaurant near
campuses with a large population tend to generate more sales than those located near
campuses with a small population. Use regression analysis to predict the sale of
restaurant for a given data of 16000 students.

Students population and quarterly sales data for 10 Armands Pizza Parlors

Restaurant Student population(000) Quarterly sales (in 000)


1 2 58
2 6 105
3 8 88
4 8 118
5 12 117
6 16 137
7 20 157
8 20 169
9 22 149
10 26 202

Variables Entered/Removedb

Variables Variables
Model Entered Removed Method
1 populationa . Enter

a. All requested variables entered.

b. Dependent Variable: Qtrly_sales

Model Summary

Adjusted R Std. Error of the


Model R R Square Square Estimate

1 .950a .903 .891 13.82932 Commented [a1]: High correlation


Commented [a2]: 89% of the variance is explained by
a. Predictors: (Constant), population independent variable student population therefore the regression
model is a good fit.

ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 14200.000 1 14200.000 74.248 .000a

Residual 1530.000 8 191.250

Total 15730.000 9

a. Predictors: (Constant), population

b. Dependent Variable: Qtrly_sales

Coefficientsa

Standardized
Unstandardized Coefficients Coefficients

Model B Std. Error Beta t Sig.

1 (Constant) 60.000 9.226 6.503 .000

population 5.000 .580 .950 8.617 .000

a. Dependent Variable: Qtrly_sales

Regression model= Y=60+5X1

Case II
The owner of the pizza Corner Bangalore would like to build a regression model
consisting of six factors to predict the sale of pizza. Data for the past 15 months on sales
and six different factors were collected for the purpose.
Input:

Dependent variables:

Y=Monthly sales in rs.


Independent variables:
X1= No. of delivery boys.
X2=Cost of ad in Rs.
X3=No. of out lets
X4=Variety of pizzas
X5=Competitors activity index
X6=No. of existing customers (000)

S.no. Sales boys Adcost outlets var comp customers


1 81 15 20 35 17 4 70
2 23 10 12 10 13 4 43
3 18 7 11 14 14 3 31
4 8 2 6 9 13 3 10
5 16 4 10 11 12 4 17
6 4 1 5 6 12 5 8
7 29 4 14 15 15 2 39
8 22 7 12 16 16 3 40
9 15 5 10 18 15 4 30
10 6 3 5 8 13 2 16
11 45 13 17 20 14 2 30
12 11 2 9 10 12 3 20
13 20 5 12 15 12 3 25
14 60 12 18 30 15 4 50
15 5 1 5 6 12 5 20

Factor Analysis

The Problem

Private domestic airline operators raised their airfare in December 2000. Indian Airlines,
the government-owned carrier, was the only domestic airline which did not follow suit.
Information available (source-Economic Times) showed that people still prefer to fly Jet
Airways. Our group set out to ascertain the reasons for the above preference, as according
to Indian Airlines officials domestic flyers are price-conscious customers.
Our study consisted of 20 respondents who had recently flown with Jet Airways.
They were asked to indicate on a seven point scale (1 = completely agree, 7 = completely
disagree), their agreement or disagreement with the set of 10 statements relating to their
perceptions and attributes of the airline.

The 10 statements were as follows:

1. They (Jet Airways) are always on time.


2. The seats are very comfortable.
3. I love the food they provide.
4. Their air-hostesses are very beautiful.
5. My boss/friend flies with the same airline.
6. The airlines have younger aircrafts.
7. I get the advantage of a frequent flyer program.
8. It (the flight timing) suits my schedule.
9. My mom feels safe when I fly Jet.
10. Flying Jet compliments my lifestyle and social standing in the society.

Scale Perquisite: Metric data-interval/ratio

You might also like