Upload
others
View
10
Download
0
Embed Size (px)
Citation preview
CHAPTER-6
RELIABILITY AND VALIDITY OF THE
SPIRITUAL INTELLIGENCE SCALE
6.1.0 Introduction
6.2.0 Reliability
6.2.1. Methods of Determining Reliability
6.2.2. Reliability of the Spiritual Intelligence Scale
6.3.0 Validity
6.3.1. Methods of Validity
6.3.2. Validity of the Spiritual Intelligence Scale
6.4.0 Conclusion
142
CHAPTER-6
RELIABILITY AND VALIDITY OF THE
SPIRITUAL INTELLIGENCE SCALE
6.1.0 Introduction
The procedure of construction of the scale has already been mentioned. Now it is
necessary to examine that whether the constructed scale will give the same result at
different occasions. This can be checked through determining the reliability of the
Spiritual Intelligence scale. It is compulsory to evaluate reliability for standardization of
any scale. In this chapter reliability and validly of the scale are discussed.
6.2.0 Reliability
Reliability is one of the essential characteristics of sound research tool. A scale must
yield a reliable estimate of the activity. If a tool gives same result on different occasion,
of the abilities of those whom it is applied, it is said to be reliable. Reliability hence
means consistency of the result. According to Anastasi & Urbina1 (2002),
"Reliability refers to the consistency of scores obtained by the same persons when they are reexamined with the same test on different occasions, or with different sets of equivalent items, or under other variable examining conditions"
6.2.1. Methods of Determining Reliability
Test reliability can be measured by various methods. Four procedure of
estimating the same are given below :
1. Test-retest method
2. Internal Consistency Reliability
(B1) Split Half Reliability
t Spearman and Brown Formula
t Rulon/Guttman’s Formula
t Flanagan Formula
(B2) Cronbach's Alpha (α)
3. Parallel Forms Methods
4. Methods of Rational Equivalence
143
1. Test-Retest Method
Reliability using this method is estimated as the Pearson Product-Moment
Correlation Coefficient between two administrations of the same measure. As per
this method, estimation is based on the correlation between two or more
administrations of the same item, same scale, or instrument for different times,
location, or populations, when the administrations do not differ on other relevant
variables.
2. Internal Consistency Reliability
As per this method, estimation is based on the correlation of two equivalent forms
scale. Spearman-Brown Split Half Reliability Coefficient, also called the Spearman-
Brown Prophecy Coefficient, is a form of split halves reliability measure. The
Spearman-Brown Prophecy Coefficient is used to estimate full test reliability based
on split-half reliability measures. The Pearson correlation of split forms estimates the
half-test reliability. The Spearman-Brown “Prophecy Formula” predicts what the full
test reliability would be, based on the half test correlation. This coefficient will be
higher than the half-test reliability coefficient.
Rulon / Guttman Split Half Reliability coefficient is an adaptation of the
Spearman-Brown coefficient, but one which does not require equal variances
between the two split forms. The best will be that in which each half contains highly
inter-correlated items.
3. Parallel Forms Methods
When parallel form of a test can be constructed, the correlation between Form A
for, example and form B may be taken as a measure of the self correlation of the test.
Under this condition, the reliability coefficient becomes an index of the equivalence
of the two forms of the test. Parallel forms are usually available form standard
psychological and educational achievement test.
The alternate form method is satisfactory when sufficient time has intervened
between the administration of the two forms to waken or eliminate memory and
practice effects. When form B of a test follows form A closely scores on the second
form of the test will often be increased because of familiarity. If such increase are
approximately constant, the reliability coefficient of the test will not be affected,
since the paired A and B scores maintain the same relative positions in the two
distributions. If the mean increases due to practise is know a constant may be
subtracted from form B scores to render them comparable to those of Form A.
144
In drawing up alternate test forms, care must be exercised to match test material
for content, difficulty and form; and precaution must be taken not to have the items
in the two forms too similar. When alternate forms are virtually identical, reliability
will be too high; whereas when parallel forms are not sufficiently alike, reliability
will be too low. For well-made standard test, the parallel forms method is usually the
most satisfactory way to determining reliability. If possible, an interval of at least two
to four weeks should be allowed between administrations of the test.
4. Methods of Rational Equivalence
Rational Equivalence is a concept where a given test of equivalent to a
hypothetical parallel forms such that every item on each form is interchangeable.
Kuder and Richardson (1973) devised a procedure for estimating the reliability of a
test. It has become the standard for estimating reliability for single administration of
a single for. Kuder-Richardson measure inter-item consistency. It is similar to doing
a Split-Half Reliability on all combinations of items resulting form different splitting
of the test.
When item level data or technological assistance is not available to assist in the
computation of a large number of cases and items, the simpler, and sometimes less
precise reliability estimate known as Kuder-Richardson Formula 21 is an acceptable
general measure of internal consistency. The formula requires only the test mean, the
variance and the number of items on the test. It assumes that all items are of
approximately equal difficulty.
6.2.2. Reliability of the Spiritual Intelligence Scale
As we discussed various types of reliability for the present study reliability of the
spiritual intelligence scale calculated by following methods :
t Test-Retest Reliability
t Internal Consistency Reliability
� Split Half Reliability
� Spearman and Brown Formula
� Rulon/Guttman’s Formula
� Flanagan Formula
t Cronbach's Alpha (α)
145
���� Test-Retest Reliability
In the present study, Spiritual Intelligence Sale was constructed by researcher.
For Spiritual Intelligence Scale, Test-Retest Reliability was estimated. Details about
the sample for colleges selected for the data collection are given Table-6.1
Table-6.1
Sample for Test-Retest Reliability
Gender Male Female
Area Urban Rural Urban Rural
Sr
No.
College
Name
Category G R G R G R G R
Tot
al
1 M.Ed. Colleg, Vadu 01 00 01 08 02 02 04 10 28
2 Smt. B. V. P. P. College of
Education, Kadi 02 03 17 16 05 03 17 24 92
3 S.D. Shethiya college of
Education, Katcch 02 04 03 13 14 25 12 11 84
Total 05 07 21 37 21 30 34 45 204
According to Table-6.1, total 204 students and 3 colleges were selected for the
sample to find out Test-Retest reliability. The present scale was administered after one
month period.
The most obvious method for finding the reliability of the test scores is by repeating
the identical test on a second occasion. The reliability coefficient in this case is simply
the correlation between the scores obtained by the same persons on the two
administrations of the test. This is done using the Pearson Product-Moment Correlation
Coefficient (r). The value of "r" always falls within the range –1 to +1. Guilford (1956)
offers an informal interpretation of the value r, as shown in Table 6.2.
Table-6.2
Interpretation of Pearson Product-moment correlation Coefficient (r)
Value of r Informal interpretation
Less than 0.20 Slight, almost no relationship
0.21-0.40 Low, correlation; definite but small relationship
0.41-0.70 Moderate correlation; substantial relationship
0.71-0.90 High correlation; strong relationship
0.91-1.00 Very High correlation; very dependable relationship
146
Another way of establishing a relationship between two sets of scores is by
examining a scatter plot drawn from the data. To estimate the Test-Retest Reliability of
the Spiritual Intelligence Scale, the scale was first administered on the sample as shown
in Table 6.1. After one month (4 weeks) again these forms were administered on the
same sample. For these two sets of data the Pearson Product-Moment Correlation
Coefficients were calculated with the help of MS-Office Microsoft Excel software
application. The formula for the Pearson Product Moment Correlation Coefficient, r, is:
r =
Where x and y are the sample means Average (array1 (test)) and Average (array2
(retest)).Results obtained for the reliability coefficient are as follows:
Spiritual Intelligence Scale Test-Retest Reliability Coefficient r = 0.82 and
SE of r = 0.023
Considering Guilford's value in Table 6.1, the correlation between test and re-test
was 0.82 can be considered as high, indicating a strong relationship. Hence, Spiritual
Intelligence Scale is reliable.
���� Reliability Coefficient Using Scatter Diagram Method
The reliability coefficient was also calculated with scatter diagram method.
Scatter diagram scores on test and retest for Spiritual Intelligence Scale is shown in
Table 6.3.
147
Table-6.3
Scatter diagram of Scores on Test -Retest for Spiritual Intelligence Scale
Re-Test Test
201 - 225 226 - 250 251 - 275 276 - 300 301 - 325 326 - 350 351 - 375 376 - 400 401 - 425 426 - 450 fy y' fyY' fyY' 2 x'y' 201 – 225 1 1 2 -4 -8 32 20 226 – 250 1 1 -3 -3 9 6 251 – 275 1 4 1 6 -2 -12 24 12 276 – 300 2 4 6 6 1 19 -1 -19 19 18 301 – 325 1 2 8 10 3 24 0 0 0 0 326 – 350 1 18 25 14 58 1 58 58 51 351 – 375 1 6 14 27 9 57 2 114 228 215 376 – 400 1 2 12 11 1 27 3 81 243 211 401 - 425 6 2 8 4 32 128 68 426 - 450 2 2 5 10 50 40 Total(fx) 3 9 13 40 51 57 26 5 204 253 791 641
x' -4 -3 -2 -1 0 1 2 3 4 5 fxX' 0 -9 -18 -13 0 51 114 78 20 0 223 fxX'2 0 27 36 13 0 51 228 234 80 0 669 x'y' 18 24 12 0 59 206 238 84 0 0 641
r=0.81
148
= 641 N = 204 Cx = 1.09 Cy = 1.24
= 1.44 =1.53
r= 0.81
From Table-6.3 the value of Correlation coefficient r = 0.81. Thus, the value of
reliability coefficient is high which indicates that the Spiritual Intelligence is reliable.
���� Internal Consistency Reliability
Test-retest method reliability methods have the disadvantage that they are time
consuming. In most cases the researcher wants to estimate the reliability from a single
administration of a test. This requirement has led to the measuring of internal
consistency, or homogeneity. Internal consistency measures consistency within the tool.
Several internal consistency methods exist. All internal consistency measurements have
one thing in common, namely that the measurement is based on the results of a single
measurement. In the present study to estimate the internal Consistency Reliability the
Spiritual Intelligence Scale was administered on the sample of 300 students of colleges.
In the present study Split-Half technique and Cronbach's Alpha method were used to
estimate the internal consistency reliability. The statistical analysis for Split half
reliability (Spearman and Brown formula and Guttmann's formula) and Cronbach's
Alpha reliability, for the calculation Ms-Excel software was used.
���� Split Half Reliability
In the Split-Half Reliability method, the Spiritual Intelligence Scale was first divided
into two equivalent halves and the correlation coefficient between scores of these half-
test was found. This correlation coefficient denotes the reliability of the half test. The
self correlation coefficient of the whole test is estimated by different formulas. The
measuring instrument can be divided into two halves in a number of ways. But the best
way to divide the measuring instrument into two halves is to find the correlation
coefficient between scores of odd numbered and even numbered items.
149
In the present study the correlation coefficient was calculated by using following
formulas:
t Spearman and Brown Formula
t Rulon/Guttmann's Formula
t Flanagan Formula
(A) Spearman and Brown Formula
Spearman-Brown Split Half Reliability is also called the Spearman Brown Prophecy
Coefficient. The Spearman and Brown formula was designed to estimate the reliability of
a test one times as long as the one for which we know a self correlation. From the
reliability of the half test, the self-correlation coefficient of the whole test is estimated by
the following Spearman and Brown formula:
r tt =
where,
rtt = reliability of the whole scale
rhh = self correlation of half test (Reliability coefficient of the half test)
The scale was administered over 4455 students and among them 300
respondent’s Spiritual Intelligence Scale were selected. The usual method of dividing the
scale into two equivalent halves is to take odd items in one half and all even items in the
other half to calculate the reliability by this method. In this case Spearman-Brown
Prophecy formula mentioned above was applied to find out the reliability. Reliability of
the half test was 0.90 and reliability of the whole scale is 0.95. The reliability of the
Spiritual Intelligence Scale is quite high. Hence, it can be said that the Spiritual
Intelligence Scale is reliable.
(B) Rulon/Guttmann's Formula
An alternate method for finding Split-Half Reliability was developed by Rulon.
Rulo/Guttman Split Half Reliability Coefficient is an adaption of the Spearman-Brown
Coefficient, but one which does not require equal variances between the two split forms.
The best split will be that in which each half contains highly inter-correlated items. This
is an alternative split-half model which computes Rulon / Guttman’s lower bound for
true reliability. Split-Half Reliability, which measure equivalence, is also called parallel
form reliability or internal consistency reliability. The formula of Rulon is:
150
Where,
rtt= reliability value of whole test
= variance between two halve of scores
= Variance of whole test
The present Spiritual Intelligence Scale administered on 300 students for
reliability. With the help of the MS- Excel software statistical calculation was done.
Statistical values are given in Table-6.4.
Table-6.4
Reliability Coefficient and Standard Error by Rulon Method
SD of difference 14.522
SD of total score 70.071
r tt 0.96
SEr 0.0064
Form above Table-6.4, it is clear that value of reliability determined by Rulon’s
formula is 0.96 whereas the standard error is 0.0064 which is showing the moderately
high value of reliability of the scale. Hence, it can be said that the Spiritual Intelligence
Scale is reliable.
(C) Flanagan Formula
Flanagan has given formula for finding reliability using split half method. In
which standard deviation of the difference of scores on odd and even scores of the test
and standard deviation of the scores on the test or scale used.
Flanagan's Formula for reliability is described below:
Where,
= Reliability of the test
= Standard Deviation (S.D.) of Scores of 1st Half
= Standard Deviation (S.D.) of Scores of 2st Half
= Standard Deviation (S.D.) of Scores of whole Test
The present Spiritual Intelligence Scale administered on 300 students for finding
reliability. With the help of the MS-Excel software statistical calculation was done.
Statistical values are given in Table-6.5.
151
Table-6.5
Reliability Coefficient and Standard Error by Flanagan’s Method
SD of odd nos. 37.556
SD of Even Numbers 35.912
70.071
r tt 0.90
SEr 0.0144
Form above Table-6.5, it is clear that value of reliability determined by
Flanagan’s formula is 0.90 whereas the standard error is 0.0144 which is showing the
moderately high value of reliability of the scale.Hence, it can be said that the Spiritual
Intelligence Scale is reliable.
� Cronbach's Alpha ( )
Cronbach's Alpha is mathematically equivalent to the average of all possible split-
half estimates. A statistical analysis computer programme SPSSS 17 was used to
calculate the Cronbach's Alpha (). The value of rtt for Spiritual Intelligence Scale is
0.94 Hence, as per the value of Cronbach's Alpha (), both the forms are reliable.
� Comprehensive view of the Reliability of the Spiritual Intelligence Scale
In Table 6.6, reliability coefficients for different methods have been shown:
Table-6.6
Reliability by different method for Spiritual Intel ligence Scale
Sr. No. Methods of Reliability Sample r tt
Reliability Coefficient 1 Test-Retest 204 0.82 2 Split-Half
A Spearmen and Brown Formula
300 0.95
B Rulon /Guttmann’s formula 300 0.96
C Flanagan’s formula 300 0.90
3 Cronbach Alpha( ) 300 0.94
In Table-6.6, the values of reliability using Test-Retest, Split-Half Methods and
Cronbach Alpha ( ) are shown, which are moderately high. Thus, it can be said that the
reliability of the Spiritual Intelligence Scale is moderately high.
152
6.3.0 Validity
The validity refers to the degree to which the test or scale actually measures what it
claims to measure. Test or scale is also the extent to which inferences, conclusion and
decisions made on the basis of test or scale scores are appropriate and meaningful.
Test validity is requisite to test reliability. if a scale or test is not valid, then
reliability is moot. In other words, if a test is not valid there is no point in discussing
reliability because test validity is required before reliability can be considered in any
meaningful way. Likewise if a test is not reliable it is not valid. According to H.E.
Guilford2 (1956),
“The validity of a test or of any measuring instrument depends upon the fidelity with which it measures what it propose to measure”
According to Lindquist3 (1971), “The validity of a test is an estimate of the correlation between the raw test and ‘true’(That is perfectly reliable) criterion score”
According to Charles Jackson4 (1960), “Validity is the extent to which the test measures what it is intended to measure. Evidence to justify the way a test has been developed and is used.”
The evaluation of the test does not end with the estimation of the stability and
precision of its measurement. It only brings there. A highly reliable test may not measure
what is intends to measure. Besides, it is necessary to know how or what is intended, is
measured as well as to be sure that nothing else is measured. The question is
fundamental with ‘assessment’ test but not with the predictor test. Such tests are more
concerned with which are termed as ‘concept’ or construct’ validity.
Validity establishment against an external criterion is of the sounded type, provided
a suitable criterion measure is used. But that is the crux of the validity problem. The task
of developing criterion measure appears to be almost insurmountable with regard to the
measurement years of practice have establishment traditional and validation of test is not
subjects of hot controversies. Though perfection in the matter is not to assumed to have
been reached, one can undertake the work with a fair degree of confidence.
6.3.1. Methods of Validity
Validity of a test or evaluation device can be defined as the degree to which the test
measures what it is intended to measure. Validity is a relative term and has reference to
particular purpose or situation. The question “Is the test valid?” can be answered only by
replying to the question “Valid, for what?” Hence, there are different types of validity
meant for different purposes.
153
t Types of Validity
���� Content Validity
Content validity is evaluated by showing how well the content of the test
samples the class of situations or subject matter about which conclusions are to be
drawn. It is based on a comparison of the analysis of test content with the analysis of
the course content and the instructional objectives. It is seen as to how well the
former represents the latter. The analysis is done essentially through logical, rational
and judgmental process. That is why, sometimes the content validity may be referred
to as ‘rational’ or ‘logical validity’.
���� Face Validity
Face validity has something to do with mere appearance of a test. A test is said
to have face validity when by appearance it ‘looks like’ measuring what it is meant to
measure. The appearance of the reasonableness is spoken of as ‘face validity’.
���� Concurrent Validity
Concurrent validity is evaluated by showing how well the test scores
correspond to already accepted measure of performance or status made at the same
time. For example a newly constructed test of intelligence may be validated by
finding its correlation with another already existing well accepted test in this area. In
these cases, a correlation coefficient between the two sets of measures is calculated
as an index of validity. The main problem is to set up a criterion which is
independent and reliable.
���� Criterion Related Validity
In Concurrent Validity, the test is validated against a criterion at the same
point of time. However, the researcher may be interested in using a test to predict
some future outcome. For example a clerical aptitude test may be used to predict
success on the jobs as clerks. The researcher is thus interested in prediction of
success or performance in the future. This process is called Predictive Validity.
���� Construct Validity
Sometimes questions like the following are asked, “What does this test mean
or signify?” “What does the score tell us about the individual?” “Does it correspond
to some meaningful trait or construct that will help us in understanding him?”. These
questions are related with the construct validity of the test. For any test that presumes
to measure a trait or quality, we can formulate a network of theory leading to definite
154
predictions. In so as they are borne out, the validity of the test as a measure of the
trait or construct is supported. In so far as the predictions fail to be verified, the
researcher is led to doubt the validity of our test or our theorizing, or both. Evidence
of construct validity is partly rational and partly empirical and judgement and
evidence join together in the validation enterprise.
���� Factorial Validity
Factorial validity is, in a way, extension of the construct validity. The inter
correlations of a large number of tests are explained and if possible accounted for in
terms of a much smaller number of more general ‘factors’ or trait categories.
Sometimes 3 or 4 factors may account for the intercorrelations among 15 to 20 tests.
The factorial validity of a test is defined by its correlation with a factor, called factor
loading.
6.3.2. Validity of the Spiritual Intelligence Scale
For estimating the validity of the present scale, concurrent validity method was
used. To determine the concurrent validity, the correlation coefficient between other
similar spiritual intelligence scale and the spiritual intelligence scale has been calculated.
� The Validity of the Spiritual Intelligence Scale was determined by using
following methods :
���� Face Validity for the items constructed by the researcher was deliberated
by sending the tool the subject experts and by subsequent improvements
suggested by the experts.
� Concurrent Validity :
Concurrent Validity refers to the degree to which the operationalization
correlates with other measures of the same construct that are measured at the same time.
To determine the concurrent validity, the correlation coefficient between Spiritual
Intelligence Scale prepared by the investigator and Spiritual Intelligence Scale prepared
by the Bhavin D. Shah were administered on the sample mentioned in Table-6.7. Both
the scales were administered with the gap of one period only.
155
Table-6.7
Sample for Validity Estimation for Spiritual Intell igence Scale
Sr.
No.
College Name No.
Students
1 Smt. S. I. Patel Ipcowala College of Education, Petlad 84
2 Adardsh B.Ed. College, Botad, 64
3 M.Ed. College, Radhanpur 26
4 I. J. Patel M.Ed. College, Moghari 24
Total 198
Thus, Spiritual Intelligence Scale prepared by the researcher and Spiritual
Intelligence Scale prepared by Bhavin D. Shah were administered on total 198 students
to establish the Validity of the Scale. Correlation coefficient between the scores of the
both Spiritual Intelligence Scale was calculated. Scatter diagram given in the table-6.8
and formula given below :
156
Table-6.8
Scatter diagram for Concurrent Validity
Spiritual Intelligence Scale (Bhavin D. Shah) Class 145-
164 165-184
185-204
205-224
225-244
245-264
265-284
285-304
Grand Total
y' fyY' fyY'2 x'y'
260-284 1 1 1 3 -3 -9 27 3 285-309 2 1 3 -2 -6 12 12 310-334 15 5 3 2 25 -1 -25 25 38 335-359 1 28 13 6 2 50 0 0 0 0 360-384 6 16 22 6 50 1 50 50 78 385-409 1 7 29 6 43 2 86 172 250 410-434 3 6 9 18 3 54 162 180 435-459 6 6 4 24 96 96 Grand Total
1 1 18 41 32 41 43 21 198 174 544 657
x' -1 -2 -3 0 1 2 3 4 fxX' -1 -2 -54 0 32 82 129 84 270 fxX'2 1 4 162 0 32 164 387 336 1086
Spi
ritua
l Int
ellig
ence
Sca
le
x'y' 3 6 57 0 13 80 246 252 657
r = 0.79
156
157
= 657 N = 198 Cx = 1.36 Cy = 0.88
= 1.90 =1.41
r= 0.79
According to table-6.8, Correlation coefficient between the scores of Spiritual
Intelligence Scale and Spiritual Intelligence Scale prepared by Bhavin D. Shah was 0.79.
Authority letter for using Spiritual Intelligence Scale given by Bhavin D. Shah, Spiritual
Intelligence Scale and Manual prepared by Bhavin D. Shah Presented in Appendix-E.
� Convergent Validity :
To estimate the Convergent Validity of the Spiritual Intelligence Scale the correlation
coefficient between the scores of Spiritual Intelligence Scale and Verbal and Non verbal
Intelligence Test Prepared by Dr. K.G. Desai and published by Institute of
Psychological and Educational Research and Guidance, Ahmedabad was calculated.
Spiritual Intelligence Scale and Verbal and Non verbal Intelligence Test were
administered on the sample mentioned in Table-6.9. Both the tools were administered
with the gap of one month period only.
Table-6.9 Sample for Estimation of Convergent Validity
Sr.
No.
College Name No.
Students
1 Swami Vivekanand Sarvoday Bank Education
College, Mehsana
93
2 Swami Vivekanand Sarvoday Bank Education
College Post Graduate Department, Mehsana
28
3 Banaskantha Kadva Patidar Sankar Mandal,
M.Ed. College, Palanpur
16
4 K. B. Dave M.Ed. College, Vijapur 23
Total 160
Thus, Spiritual Intelligence Scale and Verbal and Non verbal Intelligence Test
were administered on total 160 students to establish the Validity of the Scale. Correlation
coefficient between the scores of the Spiritual Intelligence Scale and Verbal and Non
verbal Intelligence Test was calculated. Scatter diagram given in the table-6.10.
158
Table-6.10
Scatter diagram for Convergent Validity
Verbal Non Verbal Intelligence Test (Dr. K.G. Desai)
75-84 85-94 95-104 105-114 115-124 125-134 135-144 Total (fy)
y' fyY' fyY' 2 x'y'
240-264 1 2 3 -4 -12 48 28
265-289 3 3 6 -3 -18 54 45
290-314 2 10 6 3 1 22 -2 -44 88 62
315-339 2 6 29 13 1 1 52 -1 -52 52 43
340-364 1 11 16 3 2 33 0 0 0 0
365-389 5 14 7 2 28 1 28 28 6
390-414 2 3 7 12 2 24 48 34
415-439 1 2 3 3 9 27 15
440-464 1 1 4 4 16 8
Total(fx) 08 22 51 48 16 14 01 160 -61 361 241
x' -3 -2 -1 0 1 2 3
fxX' -24 -44 -51 0 16 28 3 -72
fxX' 2 72 88 51 0 16 56 9 292
Spi
ritua
l Int
ellig
ence
Sca
le
x'y' 57 86 36 0 13 52 -3 241
r = 0.72
158
159
= 241 N = 160 Cx = -0.45 Cy = -0.38
= 1.27 =1.45
r= 0.72
Correlation coefficient between the scores of Spiritual Intelligence Scale and Verbal
and Non verbal Intelligence Test was 0.72. Verbal and Non verbal Intelligence Test and
manual Prepared by Dr. K.G. Desai and published by Institute of Psychological and
Educational Research and Guidance, Ahmedabad attached in Appendix-F.
The values of correlation coefficient are moderately high so that it can be said that the
present Spiritual Intelligence Scale is valid.
� Factor Validity :
Factor analysis is a statistical method used to describe variability among observed
variables in terms of a potentially lower number of unobserved variables called factors.
Correlation between dimensions (Factors) of the Spiritual Intelligence Scale with help of Ms-
Excel Software was calculated. Table-6.11 shows the correlation matrix of the scores of
Spiritual Intelligence Scale. It shows the Pearson Correlation Coefficient between all pairs of
dimensions.
160
Table-6.11
Correlation Matrix of various factors of Spiritual Intelligence Scale
Dimension God and
Religious
Self
Awareness
Religious
Concept
Spiritual
Changes
Religious
Experience Values
Helping
Behaviours
Social
Maturity
Soul,
Meditation
and Yoga
Soul, Meditation
and Yoga 0.64 0.51 0.50 0.52 0.55 0.59 0.63 0.58 1
Social Maturity 0.63 0.57 0.49 0.48 0.61 0.65 0.71 1
Helping Behaviours 0.64 0.53 0.58 0.42 0.55 0.69 1
Values 0.61 0.58 0.53 0.37 0.52 1
Religious Experience 0.71 0.57 0.50 0.61 1
Spiritual Changes 0.66 0.30 0.45 1
Religious Concept 0.56 0.44 1
Self Awareness 0.50 1
God and Religious 1
160
161
6.4.0 Conclusion
In this chapter, reliability and validity have been discussed and the values for the
same for the Spiritual Intelligence Scale that is constructed by the researcher have been
measured using different methods. The values show satisfactory values of reliability and
validity of the constructed scale. In the Chapter-7 data analysis and Interpretations
discussed in detail.
162
REFERENCES
1. A., Anastasi, & A., Urbina, (2002). Psychological Testing (7th Edition). New
Delhi: Pearson Education (Singapore) Pvt. Ltd., Indian Branch, Page No.- 84.
2. Guilford H. E. (1956). Fundamental of Static in Psychology and Education,
New York : Mc Craul Hall Book Company, Page No.- 379.
3. E. F. Lindquist (1971). A First Course in Statistics, Boston , Mifflin : Revised
Edition, Page No- 213.
4. Charles Jackson (1960). Undertaking Psychological Testing, Jaico Publishing
House, Bombay, page No- 169.