Sie sind auf Seite 1von 17

METHODOLOGY ADOPTED

The study has been carried out in a three phased manner.

In first phase –

Exploratory Research Design, for the qualitative research - A preliminary informal study
was carried out in order to develop an understanding and get an aerial view about the present
product mix, menu for each day and various dishes being offered by the mess – cum –
canteen at present. This involve the in depth interview with the owner of the mess – cum –
canteen.

In Second Phase –

On the basis of the study done in first phase, a questionnaire was drafted in order to get the
information and the thinking, perception about the product mix, menu and the different dishes
being offered by the institute mess – cum – canteen for the students.

In third phase –

In this phase, the analysis and interpretation of the results findings and output got by the
application of statistical tool SPSS on the data collected in the second phase. The
recommendation has also been provided to the owner about the product mix, menu and the
different dishes so that students can derive maximum satisfaction and can get value of their
money spend.

ANALYSIS: OUTPUT SHEET GENTERATED BY USING SPSS

Case Processing Summary


Cases

Valid Missing Total

N Percent N Percent N Percent

food and snacks 83 100.0% 0 .0% 83 100.0%

unwind, relax and hangout 83 100.0% 0 .0% 83 100.0%

meeting with friends 83 100.0% 0 .0% 83 100.0%

place for dating and flaunting 83 100.0% 0 .0% 83 100.0%

place for discussion 83 100.0% 0 .0% 83 100.0%

no reasons 83 100.0% 0 .0% 83 100.0%

variety in menu 83 100.0% 0 .0% 83 100.0%

price charged 83 100.0% 0 .0% 83 100.0%


quality of foods/products 83 100.0% 0 .0% 83 100.0%

availabilty of foods 83 100.0% 0 .0% 83 100.0%

delivery promptness 83 100.0% 0 .0% 83 100.0%

The case processing summary is showing that there are 83 respondents in total and no data is
missing.

Reliability check of the model

Reliability refers to the extent to which a scale produces consistent results if measurements
are made. It is assessed by determining the proportion of systematic variation in scale. This is
done by determining the association between scores obtained from different administration of
the scale. If the association is high, the scale yields consistent results and therefore reliable.
Approaches for assessing reliability include the test-retest, alternative forms, and internal
consistency methods. We have considered internal consistency method for our reliability
check.

Scale: ALL VARIABLES


Case Processing Summary
N %

Cases Valid 83 100.0

Excludeda 0 .0

Total 83 100.0

a. Listwise deletion based on all variables in the procedure.

Reliability Statistics
Cronbach's Alpha Based on
Cronbach's Alpha Standardized Items N of Items

.746 .754 11

Internal consistency method for reliability check: In this we have considered the
coefficient alpha or Cronbach’s Alpha, is the average of all possible split half coefficient
resulting from different ways splitting the scale items. This coefficient varies from 0 to 1 and
a value of 0.6 or less generally indicates unsatisfactory internal consistency reliability. An
important property of coefficient alpha is that its value tends to increase with an increase in
the number of scale items. The value of cronbach’s Alpha should be greater than 0.6 for the
internal consistency reliability. In our case, the cronbach’alpha or coefficient alpha is 0.746
This shows that our data is internally consistent having control over the random error.
Henceforth our measurement is reliable.

Descriptive Statistics
Std. Varianc
N Mean Deviation e Skewness Kurtosis
Std. Std. Std.
Statistic Statistic Error Statistic Statistic Statistic Error Statistic Error

food and snacks 83 3.9639 .10206 .92980 .865 -1.233 .264 2.136 .523

unwind, relax and 83 3.4337 .10454 .95244 .907 -.630 .264 .438 .523
hangout

meeting with friends 83 3.3253 .10991 1.00132 1.003 -.698 .264 -.100 .523

place for dating and 83 2.1687 .12922 1.17722 1.386 .629 .264 -.618 .523
flaunting

place for discussion 83 2.5301 .11414 1.03990 1.081 .185 .264 -.637 .523

no reasons 83 2.7590 .13777 1.25514 1.575 .054 .264 -.887 .523

variety in menu 83 2.5060 .10757 .97996 .960 .262 .264 -.642 .523

price charged 83 3.3012 .09348 .85161 .725 -.506 .264 -.018 .523

quality of 83 2.6265 .10386 .94625 .895 .112 .264 -.212 .523


foods/products

availabilty of foods 83 2.7831 .09855 .89780 .806 .032 .264 -.109 .523

delivery promptness 83 2.8193 .09567 .87156 .760 .024 .264 -.529 .523

Valid N (listwise) 83

NORMALITY CHECK OF THE DATA

The normality check has performed in order to get to know whether the data is following
Normal Distribution or not. The normal distribution is the distribution of the values of a
sample statistic computed for each possible sample that could be drawn from target
population under a specified sampling plan. To check this we have considered One-Sample
Kolmogorov-Smirnov Test.

NPar Tests
One-Sample Kolmogorov-Smirnov Test

unwin place
d, meeti for
food relax ng dating
and and with and place for no variet price quality of availabi delivery
snac hango friend flaunti discussi reaso y in charg foods/produ lty of promptne
ks ut s ng on ns menu ed cts foods ss

N 83 83 83 83 83 83 83 83 83 83 83

Mean 3.963 3.433 3.325 2.1687 2.5301 2.759 2.506 3.301 2.6265 2.7831 2.8193
9 7 3 0 0 2
Normal Std. . . 1.001 1.1772 1.03990 1.255 . . .94625 .89780 .87156
Parameter Deviati 9298 95244 32 2 14 9799 85161
sa,,b on 0 6

Most Absolut .299 .242 .280 .237 .189 .203 .239 .252 .220 .234 .209
Extreme e
Differences Positiv .207 .180 .190 .237 .189 .159 .239 .180 .190 .212 .200
e

Negativ -.299 -.242 -.280 -.160 -.180 -.203 -.158 -.252 -.220 -.234 -.209
e

Kolmogorov- 2.721 2.205 2.550 2.161 1.721 1.846 2.181 2.295 2.002 2.132 1.901
Smirnov Z

Asymp. Sig. (2- .000 .000 .000 .000 .005 .002 .000 .000 .001 .000 .001
tailed)

a. Test distribution is Normal.

b. Calculated from data.

In this case, H0: the distribution is not normal


H1: the distribution follows normal distribution.

The level of significance in all cases is less than .05, which means our H0 has rejected,
suggesting the data follows normal distribution. This will now help us for further proceedings
such as which type of test we could use in analysis of our set objective.

Regression Model for Level of satisfaction


In order to analyse the association of level of satisfaction of the students with the other factor
such as delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods, we have used regression analysis. Regression Analysis is a powerful
and flexible statistical procedure for analyzing associative relationships between a metric
dependent variable and one or more independent variables. The regression model tries to
explain the participation for variation of each independent variable in order to explain
variation in the dependent variable.

Here, we have tried to find out which independent variable (delivery promptness, quality of
foods/product, variety in menu, price charged and availability of foods) explains well the
variation in dependent variable (level of satisfaction) for the students of the institute. That
means out of the given five independent variables which are more participative in satisfying
the students.
Variables Entered/Removed

Model Variables Entered Variables Removed Method

1 delivery promptness, quality of . Enter


foods/products, variety in menu,
price charged, availabilty of foodsa

a. All requested variables entered.


ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 42.164 5 8.433 37.106 .000a

Residual 17.499 77 .227

Total 59.663 82

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

The validity of the considered model has been checked through ANOVA, i.e., whether the
considered model is significant for our above stated study or not.
Hypothesis: H0: the model is insignificant
H1: the model is significant
The level of significance is less than 0.05 thereby rejecting our null hypothesis, suggesting
that regression model is valid to carry out the study.

STRENGTH OF THE MODEL


Model Summaryb

Durbin-
Change Statistics Watson
Std. Error
Mode R Adjusted R of the R Square F Sig. F
l R Square Square Estimate Change Change df1 df2 Change

1 .841a .707 .688 .47672 .707 37.106 5 77 .000 1.764

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

R Square: R square is a squared correlation index that indicates the proportion of variance
of the optimally scaled data that can be accounted for the procedure. This is a goodness-of-fit
measure. Here, from the given model summary table R Square is coming 0.0707, suggesting
that there is strong correlation index. Henceforth, around 70.7% of variance in the dependent
variable (level of satisfaction) is explained by the regression model (independent variables)
out of the total variance. Rest 29.3% variance is in the level of satisfaction is explained by
some other factors which have not taken into consideration for the study.
Adjusted R Square: adjusted R Square is same as R Square; however it depicts the
percentage of variation more precisely after making certain level of adjustment. The value
from the model summery is 0.688; showing 68.8% of variance in level of satisfaction is
explained by our regression model, rest 31.2% is explained some other factors not
considered in during our study.
R: R is a coefficient correlation between the observed and the predicted value i.e., the value
estimated by the regression model. The value of R is coming out as 0.841 showing strong
correlation among the observed and predicted value, thereby suggesting the model is strong.
ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 42.164 5 8.433 37.106 .000a

Residual 17.499 77 .227

Total 59.663 82

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

The validity of the considered model has been checked through ANOVA, i.e., whether the
considered model is significant for our above stated study or not.
Hypothesis: H0: the model is insignificant
H1: the model is significant
The level of significance is less than 0.05 thereby rejecting our null hypothesis, suggesting
that regression model is valid to carry out the study.

STRENGTH OF THE MODEL


Model Summaryb

Durbin-
Change Statistics Watson
Std. Error
Mode R Adjusted R of the R Square F Sig. F
l R Square Square Estimate Change Change df1 df2 Change

1 .841a .707 .688 .47672 .707 37.106 5 77 .000 1.764

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

R Square: R square is a squared correlation index that indicates the proportion of variance
of the optimally scaled data that can be accounted for the procedure. This is a goodness-of-fit
measure. Here, from the given model summary table R Square is coming 0.0707, suggesting
that there is strong correlation index. Henceforth, around 70.7% of variance in the dependent
variable (level of satisfaction) is explained by the regression model (independent variables)
out of the total variance. Rest 29.3% variance is in the level of satisfaction is explained by
some other factors which have not taken into consideration for the study.
Adjusted R Square: adjusted R Square is same as R Square; however it depicts the
percentage of variation more precisely after making certain level of adjustment. The value
from the model summery is 0.688; showing 68.8% of variance in level of satisfaction is
explained by our regression model, rest 31.2% is explained some other factors not
considered in during our study.
R: R is a coefficient correlation between the observed and the predicted value i.e., the value
estimated by the regression model. The value of R is coming out as 0.841 showing strong
correlation among the observed and predicted value, thereby suggesting the model is strong.
ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 42.164 5 8.433 37.106 .000a

Residual 17.499 77 .227

Total 59.663 82

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

The validity of the considered model has been checked through ANOVA, i.e., whether the
considered model is significant for our above stated study or not.
Hypothesis: H0: the model is insignificant
H1: the model is significant
The level of significance is less than 0.05 thereby rejecting our null hypothesis, suggesting
that regression model is valid to carry out the study.

STRENGTH OF THE MODEL


Model Summaryb

Durbin-
Change Statistics Watson
Std. Error
Mode R Adjusted R of the R Square F Sig. F
l R Square Square Estimate Change Change df1 df2 Change

1 .841a .707 .688 .47672 .707 37.106 5 77 .000 1.764

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

R Square: R square is a squared correlation index that indicates the proportion of variance
of the optimally scaled data that can be accounted for the procedure. This is a goodness-of-fit
measure. Here, from the given model summary table R Square is coming 0.0707, suggesting
that there is strong correlation index. Henceforth, around 70.7% of variance in the dependent
variable (level of satisfaction) is explained by the regression model (independent variables)
out of the total variance. Rest 29.3% variance is in the level of satisfaction is explained by
some other factors which have not taken into consideration for the study.
Adjusted R Square: adjusted R Square is same as R Square; however it depicts the
percentage of variation more precisely after making certain level of adjustment. The value
from the model summery is 0.688; showing 68.8% of variance in level of satisfaction is
explained by our regression model, rest 31.2% is explained some other factors not
considered in during our study.
R: R is a coefficient correlation between the observed and the predicted value i.e., the value
estimated by the regression model. The value of R is coming out as 0.841 showing strong
correlation among the observed and predicted value, thereby suggesting the model is strong.
ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 42.164 5 8.433 37.106 .000a

Residual 17.499 77 .227

Total 59.663 82

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

The validity of the considered model has been checked through ANOVA, i.e., whether the
considered model is significant for our above stated study or not.
Hypothesis: H0: the model is insignificant
H1: the model is significant
The level of significance is less than 0.05 thereby rejecting our null hypothesis, suggesting
that regression model is valid to carry out the study.

STRENGTH OF THE MODEL


Model Summaryb

Durbin-
Change Statistics Watson
Std. Error
Mode R Adjusted R of the R Square F Sig. F
l R Square Square Estimate Change Change df1 df2 Change

1 .841a .707 .688 .47672 .707 37.106 5 77 .000 1.764

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

R Square: R square is a squared correlation index that indicates the proportion of variance
of the optimally scaled data that can be accounted for the procedure. This is a goodness-of-fit
measure. Here, from the given model summary table R Square is coming 0.0707, suggesting
that there is strong correlation index. Henceforth, around 70.7% of variance in the dependent
variable (level of satisfaction) is explained by the regression model (independent variables)
out of the total variance. Rest 29.3% variance is in the level of satisfaction is explained by
some other factors which have not taken into consideration for the study.
Adjusted R Square: adjusted R Square is same as R Square; however it depicts the
percentage of variation more precisely after making certain level of adjustment. The value
from the model summery is 0.688; showing 68.8% of variance in level of satisfaction is
explained by our regression model, rest 31.2% is explained some other factors not
considered in during our study.
R: R is a coefficient correlation between the observed and the predicted value i.e., the value
estimated by the regression model. The value of R is coming out as 0.841 showing strong
correlation among the observed and predicted value, thereby suggesting the model is strong.
ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 42.164 5 8.433 37.106 .000a

Residual 17.499 77 .227

Total 59.663 82

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

The validity of the considered model has been checked through ANOVA, i.e., whether the
considered model is significant for our above stated study or not.
Hypothesis: H0: the model is insignificant
H1: the model is significant
The level of significance is less than 0.05 thereby rejecting our null hypothesis, suggesting
that regression model is valid to carry out the study.

STRENGTH OF THE MODEL


Model Summaryb

Durbin-
Change Statistics Watson
Std. Error
Mode R Adjusted R of the R Square F Sig. F
l R Square Square Estimate Change Change df1 df2 Change

1 .841a .707 .688 .47672 .707 37.106 5 77 .000 1.764

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

R Square: R square is a squared correlation index that indicates the proportion of variance
of the optimally scaled data that can be accounted for the procedure. This is a goodness-of-fit
measure. Here, from the given model summary table R Square is coming 0.0707, suggesting
that there is strong correlation index. Henceforth, around 70.7% of variance in the dependent
variable (level of satisfaction) is explained by the regression model (independent variables)
out of the total variance. Rest 29.3% variance is in the level of satisfaction is explained by
some other factors which have not taken into consideration for the study.
Adjusted R Square: adjusted R Square is same as R Square; however it depicts the
percentage of variation more precisely after making certain level of adjustment. The value
from the model summery is 0.688; showing 68.8% of variance in level of satisfaction is
explained by our regression model, rest 31.2% is explained some other factors not
considered in during our study.
R: R is a coefficient correlation between the observed and the predicted value i.e., the value
estimated by the regression model. The value of R is coming out as 0.841 showing strong
correlation among the observed and predicted value, thereby suggesting the model is strong.
ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 42.164 5 8.433 37.106 .000a

Residual 17.499 77 .227

Total 59.663 82

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

The validity of the considered model has been checked through ANOVA, i.e., whether the
considered model is significant for our above stated study or not.
Hypothesis: H0: the model is insignificant
H1: the model is significant
The level of significance is less than 0.05 thereby rejecting our null hypothesis, suggesting
that regression model is valid to carry out the study.

STRENGTH OF THE MODEL


Model Summaryb

Durbin-
Change Statistics Watson
Std. Error
Mode R Adjusted R of the R Square F Sig. F
l R Square Square Estimate Change Change df1 df2 Change

1 .841a .707 .688 .47672 .707 37.106 5 77 .000 1.764

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

R Square: R square is a squared correlation index that indicates the proportion of variance
of the optimally scaled data that can be accounted for the procedure. This is a goodness-of-fit
measure. Here, from the given model summary table R Square is coming 0.0707, suggesting
that there is strong correlation index. Henceforth, around 70.7% of variance in the dependent
variable (level of satisfaction) is explained by the regression model (independent variables)
out of the total variance. Rest 29.3% variance is in the level of satisfaction is explained by
some other factors which have not taken into consideration for the study.
Adjusted R Square: adjusted R Square is same as R Square; however it depicts the
percentage of variation more precisely after making certain level of adjustment. The value
from the model summery is 0.688; showing 68.8% of variance in level of satisfaction is
explained by our regression model, rest 31.2% is explained some other factors not
considered in during our study.
R: R is a coefficient correlation between the observed and the predicted value i.e., the value
estimated by the regression model. The value of R is coming out as 0.841 showing strong
correlation among the observed and predicted value, thereby suggesting the model is strong.
ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 42.164 5 8.433 37.106 .000a

Residual 17.499 77 .227

Total 59.663 82

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

The validity of the considered model has been checked through ANOVA, i.e., whether the
considered model is significant for our above stated study or not.
Hypothesis: H0: the model is insignificant
H1: the model is significant
The level of significance is less than 0.05 thereby rejecting our null hypothesis, suggesting
that regression model is valid to carry out the study.

STRENGTH OF THE MODEL


Model Summaryb

Durbin-
Change Statistics Watson
Std. Error
Mode R Adjusted R of the R Square F Sig. F
l R Square Square Estimate Change Change df1 df2 Change

1 .841a .707 .688 .47672 .707 37.106 5 77 .000 1.764

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

R Square: R square is a squared correlation index that indicates the proportion of variance
of the optimally scaled data that can be accounted for the procedure. This is a goodness-of-fit
measure. Here, from the given model summary table R Square is coming 0.0707, suggesting
that there is strong correlation index. Henceforth, around 70.7% of variance in the dependent
variable (level of satisfaction) is explained by the regression model (independent variables)
out of the total variance. Rest 29.3% variance is in the level of satisfaction is explained by
some other factors which have not taken into consideration for the study.
Adjusted R Square: adjusted R Square is same as R Square; however it depicts the
percentage of variation more precisely after making certain level of adjustment. The value
from the model summery is 0.688; showing 68.8% of variance in level of satisfaction is
explained by our regression model, rest 31.2% is explained some other factors not
considered in during our study.
R: R is a coefficient correlation between the observed and the predicted value i.e., the value
estimated by the regression model. The value of R is coming out as 0.841 showing strong
correlation among the observed and predicted value, thereby suggesting the model is strong.
ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 42.164 5 8.433 37.106 .000a

Residual 17.499 77 .227

Total 59.663 82

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

The validity of the considered model has been checked through ANOVA, i.e., whether the
considered model is significant for our above stated study or not.
Hypothesis: H0: the model is insignificant
H1: the model is significant
The level of significance is less than 0.05 thereby rejecting our null hypothesis, suggesting
that regression model is valid to carry out the study.

STRENGTH OF THE MODEL


Model Summaryb

Durbin-
Change Statistics Watson
Std. Error
Mode R Adjusted R of the R Square F Sig. F
l R Square Square Estimate Change Change df1 df2 Change

1 .841a .707 .688 .47672 .707 37.106 5 77 .000 1.764

a. Predictors: (Constant), delivery promptness, quality of foods/products, variety in menu, price charged,
availabilty of foods

b. Dependent Variable: Satisfaction Level

R Square: R square is a squared correlation index that indicates the proportion of variance
of the optimally scaled data that can be accounted for the procedure. This is a goodness-of-fit
measure. Here, from the given model summary table R Square is coming 0.0707, suggesting
that there is strong correlation index. Henceforth, around 70.7% of variance in the dependent
variable (level of satisfaction) is explained by the regression model (independent variables)
out of the total variance. Rest 29.3% variance is in the level of satisfaction is explained by
some other factors which have not taken into consideration for the study.
Adjusted R Square: adjusted R Square is same as R Square; however it depicts the
percentage of variation more precisely after making certain level of adjustment. The value
from the model summery is 0.688; showing 68.8% of variance in level of satisfaction is
explained by our regression model, rest 31.2% is explained some other factors not
considered in during our study.
R: R is a coefficient correlation between the observed and the predicted value i.e., the value
estimated by the regression model. The value of R is coming out as 0.841 showing strong
correlation among the observed and predicted value, thereby suggesting the model is strong.
Consider the relevance or participation of individual predictors in determining the satisfaction
level of the students. From the given five predictors (variety in menu, price charged for
products, food/product quality, availability of food/product and delivery promptness), three
predicators (price charged for products, food/product quality and delivery promptness) have
been selected on the basis of the hypothesis formulated for their level of significance.

H0: the predictor is insignificant in explaining the satisfaction level of students


H1: the predictor is significant in explaining the satisfaction level of students

Among the five given predictors, the three predictors have qualified the criteria of sig..e. i
Less than 0.05 thereby, rejecting our null hypothesis that the predictor is insignificant
suggesting that these three (price charged for products, food/products quality and delivery
promptness) are having more effect on satisfaction level in comparison to rest two (variety in
menu and availability of food/products).

Regression model for the satisfaction level

Satisfaction Level = - 0.626 + 0.370 (Price charged for products) + 0.270


(delivery Promptness) + 0.239 (quality of food/products) + 0.131 (availability of
food/products) + 0.106 (Variety in Menu)

Collinearity Diagnosticsa
Variance Proportions

quality of delivery
Mode Dimensio Eigenvalu Condition (Constant variety in price foods/product availabilty promptnes
l n e Index ) menu charged s of foods s

1 1 5.718 1.000 .00 .00 .00 .00 .00 .00

2 .094 7.800 .04 .12 .00 .24 .00 .36

3 .073 8.850 .04 .71 .04 .21 .00 .03

4 .046 11.089 .05 .12 .00 .10 .93 .05

5 .041 11.840 .25 .05 .21 .43 .01 .49

6 .028 14.256 .61 .00 .76 .02 .05 .07

a. Dependent Variable: Satisfaction Level

Collinearity Diagnostics – the co linearity diagnostics has been done in order to judge whether
there is any existence of the multi-co linearity among the stated predictors. Multicollinearity arises
when intercorrelations among the predictors are very high. Multi co linearity can result in several
problems such as:
 The partial regression coefficient may not be estimated precisely.
 The standard error likely to be high, it become difficult to assess the relative importance of
the level of satisfaction (independent variable) in explaining the variation in the dependent
variables,
 Predictor variables may be incorrectly included or removed in stepwise regression.
Therefore, the existence of multi - co linearity is a big problem. However, it could be easily reduced
by using FACTOR ANAYSIS.
For checking the existence of multi co-linearity, we have considered co-linearity statistics
(Tolerance and VIF) from the given coefficient table.

The variance inflation factor (VIF) is approximately near to 2 for all the predictors
(independent variables), which is much lower than its thumb value of 10. ( if, VIF is greater
than 10, suggesting existence of multi co-linearity) thereby showing hardly any existence of
multi co-linearity in our regression model.

Tolerance is also one of the co-linearity statistic, inverse of the VIF, provides proportion of
variance not accompanied by other predictors. The tolerance statistic in coefficient table also
showed that there is no existence of multi co-linearity in our regression model.

All this signifies that our regression model for the satisfaction level of the students of the
institute is absolutely perfect.

Correlations between frequency of visit and level of satisfaction


Here, we have tried to find out whether there is any existence of correlation between the
frequency of visit by students to canteen and the satisfaction level of students.
Descriptive Statistics

Mean Std. Deviation N

Satisfaction Level 2.6145 .85299 83

frequency of visit to canteen 5.1928 1.29217 83

Correlations

frequency of visit to
Satisfaction Level canteen

Satisfaction Level Pearson Correlation 1 .168

Sig. (2-tailed) .129

Sum of Squares and Cross- 59.663 15.169


products

Covariance .728 .185

N 83 83

frequency of visit to canteen Pearson Correlation .168 1

Sig. (2-tailed) .129

Sum of Squares and Cross- 15.169 136.916


products

Covariance .185 1.670


N 83 83

The correlation table shows that, there is very low correlation between these two variables.
That is the frequency of visit to canteen is not strongly related to the satisfaction level.

Correlations between price charged and the quality of food/products

Here, we have tried to find out whether correlation exist between price charged and the
quality of the food/products as most of the time it happens that as per the quality price of the
product is also stated.
Descriptive Statistics

Mean Std. Deviation N

price charged 3.3012 .85161 83

quality of foods/products 2.6265 .94625 83

Correlations

quality of
price charged foods/products

price charged Pearson Correlation 1 .505**

Sig. (2-tailed) .000

Sum of Squares and Cross- 59.470 33.337


products

Covariance .725 .407

N 83 83

quality of foods/products Pearson Correlation .505** 1

Sig. (2-tailed) .000

Sum of Squares and Cross- 33.337 73.422


products

Covariance .407 .895

N 83 83

**. Correlation is significant at the 0.01 level (2-tailed).

Therefore from the given, correlation table, the r = 0.5 thereby we can conclude that there is
good correlation between the price and quality of the food/product offered by the college
canteen

Das könnte Ihnen auch gefallen