Professional Documents
Culture Documents
09 - Chapter 3
09 - Chapter 3
09 - Chapter 3
Research Methodology
3.1 Definitions
3.2 Objectives
3.3 Hypothesis
3.7.3 T-Test
3.1 Definitions
3.2 Objectives
The present study explores the current marketing practices adopted by private
and corporate hospitals of Indore city. The study also performs a comparative
study of marketing practices adopted by private hospitals and corporate
hospitals, to identify the similarities and dissimilarities of marketing strategies
of these hospitals.
3.3 Hypothesis
2 18 18
3 14 14
4 6 6
5 6 6
As can be seen in Table 3.2 the total population for group 2, group 3, group 4
and group 5 hospitals is very small. Hence we have conducted the survey for all
the hospitals in these groups without incorporating any sampling method.
However, for group 1 hospital out of total population of 77, we selected the
sample of 64 hospitals using convenience sampling method.
From the above discussion, it can be established that our sample has balanced
mix of small, medium and big size private hospitals of varying bed capacities. It
is good representative of private hospitals operating in Indore. The total of 108
participants participated in the survey. The respondents were holding
managerial positions in the hospitals. Fig. 3.1 shows the sample distribution.
The distribution is based on number of beds in hospital.
Sample Distribution
Group 4 GrouP5
Fig. 3.1
The primary data for this study was collected from the hospital management
needed to support the study was also collected from secondary sources like:
The standard procedure was followed for developing and standardizing the
scale. List of 54 items was prepared after reviewing the relevant literature. The
initial screening by eliminating the repetition and irrelevant items provided 42
items. The selected 42items were presented to a sample of 18 judges (10 from
private and corporate hospitals and 8 from academia representing marketing
specialisation) along with definition of private and corporate hospitals for
assessing content and construct validities of each. The list of 30 items (with
71.43% acceptance amongst judges) was finalised. Then each item was
presented on five point likert scale ranging from ‘Strongly Agree (5)’ to
‘Strongly Disagree (1)’ and finally administered on the sample of 108
respondents.
Collected data was analysed for eliminating the weak or insignificant items by
measuring internal consistency through item-total correlation. In the first
iteration, values of correlation coefficient between each ‘item and ‘total of
items’ was found. One item (item no.l 1-1 believe website help us promote our
services) was found insignificant, hence it was dropped. In the second iteration
remaining 29 items were again subjected to item-total correlation. None of these
items were found to be insignificant and therefore all 29 items were selected for
final scale.
After ensuring the content and construct validities of the items selected, the
reliability of the scale was determined by Cronbach’s Alpha method. The
reliability coefficient alpha (a) was found to be 0.838 that showed high
reliability of the scale. The closer the reliability coefficient alpha (a) is to 1.00,
the greater the internal consistency of items in the instrument being assessed
(George, Darren and Mallery, 2011). When a scale is developed for a particular
situation and no other standardised instrument is available the reliability index
based on reliability coefficient (square root of reliability coefficient) can be
taken as equivalent to validity of the scale (Zikmund, 2003). Since the scale
developed for present study was also unique in nature, the validity was taken to
be equivalent to reliability index and computed as 0.954.
Profile
Author : Self
Nature : Verbal
Reliability : 0.0911
Validity : 0.954
Source : Self
Description
Scoring
The following statistical tools were applied using Statistical package of Social
Science (SPSS 17.0) and MS Excel 2007 for the analysis of collected data and
to arrive at meaningful conclusions.
value (p-value) for this test was found to be 0.579 (greater than 0.05) and
indicated that the distribution of final points does not differ significantly from
normal distribution. This inferred that the assumption of normality with respect
to the sample chosen was valid. Therefore the experiments and analysis based
on normality concept could be carried out with the sample of 108 respondents
Skewness and Kurtosis as the measures of deviation from normality were also
calculated. A value between +/-2.0 for both skewness and kurtosis is acceptable
for showing normality of data (George, Darren and Mallery, 2011). The value
of skewness was found to be -1.926 and for kurtosis it was 0.434. In both the
cases values fell within acceptable range of +/- 2.0. The values of standard error
for kurtosis (0.917) and skewness (0.099) found sufficiently small, which were
indicating greater stability of data.
3.7.3 T-Test
This test is used only when the two population variances are assumed to be
different (the two sample sizes may or may not be equal) and hence must be
estimated separately. In our study, as the population variance of private hospital
and corporate hospital is assumed different and sample sizes are known to be
different, hence T-test is used to compare the marketing strategy of private
hospital with corporate hospital.
The t statistic to test whether the population means are different can be
calculated as follows:
t=
Xt - x2
A 1-A2
where,
SXi-Xi
7l\ ft 2
2
Where s is the unbiased estimator of the variance of the two samples, n =
number of participants, 1 = group one, 2 = group two. Note that in this case,
_ a
A’i-A'2 is not a pooled variance. For use in significance testing, the distribution
of the test statistic is approximated as being an ordinary Student's t distribution
with the degrees of freedom calculated using
The present study was conducted amongst private and corporate hospitals of
Indore city alone. This limits its generalisation to other cities and states of India.
Again this study was conducted only on private hospitals, hence it limits its
application to government hospitals and hospitals which are not using any
marketing practices.