Upload
lamnhi
View
220
Download
0
Embed Size (px)
Citation preview
CHAPTER -VII
Data Analysis and Interpretation.
7. 1
DATA ANALYSIS & INTERPRETATION
The present study is intended to investigate about Library Effectiveness
by maintaining Library Automation in the University Libraries of
Chhattisgarh. Using appropriate statistical tables, common reference of F-
ratio was applied to test the significance of differences for verification of
various hypotheses. Scores for all the scales collected from all the samples
were analysed separately. The outcome of statistical analysis is compiled in
tables and figures followed by interpretation.
The major prerequisites for effective data analysis using ANOVA
technique are the normally distributed and homogenous data. For judging
normality of any given data, the best ways prescribed are to calculate the
skew ness and kurtosis of the distribution pertaining to the data.
A distribution is said to be skewed when the mean and median fall at
different points in the distribution, and the balance of the centre of gravity
is shifted to one side or the other – i.e. to the left or the right. Ideally the
skew ness value should therefore be exactly “0” (zero) for mean and
median to fall at the same point. The skew ness of the dependent variable
Library Effectiveness in this case is -0.233 with a standard error of 0.121.
Therefore, the data was found to insignificantly skew.
The term kurtosis refers to the flatness of a frequency distribution
compared with the normal distribution. While according to Garrett (1989)
the standard Kurtosis value of normally distributed data should be exactly
7. 2
DATA ANALYSIS & INTERPRETATION
0.263, the kurtosis value of dependent variable Library Effectiveness in this
study was found to be -0.003 with a standard error of 0.241. Therefore, it
was inferred that the data being insignificantly Kurt was almost normally
distributed.
Further, using the Levene‟s test for measuring homogeneity of the data,
significant results (p=.000) were obtained which denied the homogeneity
of data. Therefore, following McNemar (1962), as the two assumption were
not absolutely fulfilled, but ANOVA being a robust technique that
overlooks near miss cases, for further analysis of results, the level of
significance as an accept/reject criteria was kept stringent at 0.01 level i.e.
(p<.01).
As mentioned earlier, the study further uses a three-dimensional (3x2x8)
ANOVA technique at SPSS to analyse the data whereby numerical values
were assigned for various independent variables of the study. Three levels
of Library Automations were studied as low, moderate and high
respectively. For the dimension of Readers, the two categories were
Teachers and Students respectively. For the dimension of Universities, the
eight respective codes were: PRSU for Pandit Ravishankar Shukla University,
GGU for Guru Ghasidas University, IGKV for Indira Gandhi Krishi
Vishwavidyalaya, IKSV for Indira Kala Sangeet Vishwavidyalaya, HNLU for
Hidayatullah National Law University, CSVTU for Chhattisgarh Swami
Vivekanand Technical University, PSOU for Pandit Sundarlal Sharma (Open)
University and finally KBTV for Kushabhau Thakre Patrakarita Avam
7. 3
DATA ANALYSIS & INTERPRETATION
Jansanchar Vishwavidyalaya. Finally, Library Effectiveness was observed as
the dependent variable.
For the first problem, where it was hypothesised that Libraries with higher
automation level will show more effectiveness than libraries with lower level
of automation, the Table 7.1, 7.2, 7.3 and 7.4 below mention the
descriptive statistics and mean scores for the dependent variable Library
Effectiveness at low, moderate, high and total level of Library Automation
respectively.
Library Effectiveness at Low Automation Level
Table – 7.1
Automation
Level Readers Library Mean
Std.
Deviation Sample
LOW Teacher
s
PRSU 84.18 1.36802 5
GGU 80.616 2.214663 5
IGKV 74.664 3.273604 5
IKSV 71.828 1.885715 5
HNLU 69.54 1.456802 5
CSVTU 68.808 1.636802 5
PSOU 64.416 2.004665 5
KBTV 60.112 1.932698 5
Total 71.7705 7.714259 40
Students PRSU 65.7336 0.32736 5
GGU 65.148 0.32736 5
IGKV 63.0252 0.24552 5
IKSV 62.32972 0.353051 5
HNLU 61.8906 0.621912 5
CSVTU 60.99024 0.821912 5
PSOU 59.7996 0.650223 5
KBTV 57.0964 1.843376 5
Total 62.00167 2.744664 40
Total PRSU 74.9568 9.724556 10
GGU 72.882 8.153608 10
IGKV 68.8446 6.512903 10
IKSV 67.07886 5.166834 10
HNLU 65.7153 4.031588 10
CSVTU 64.89912 4.297442 10
PSOU 62.1078 2.809582 10
KBTV 58.6042 2.386723 10
Total 66.88609 7.566813 80
7. 4
DATA ANALYSIS & INTERPRETATION
Library Effectiveness at Moderate Automation Level
Table –7.2
Automation Level Readers Library Mean Std. Deviation Sample
MODERATE Teachers PRSU 191.784 2.004665 5
GGU 185.864 3.923325 5
IGKV 178.608 1.636802 5
IKSV 174.212 2.010154 5
HNLU 127.368 6.547207 5
CSVTU 123.708 1.636802 5
PSOU 119.292 2.03797 5
KBTV 88.572 1.636802 5
Total 148.676 36.52433 40
Students PRSU 143.89 1.459893 5
GGU 139.446 3.006997 5
IGKV 133.956 1.227601 5
IKSV 130.659 1.507616 5
HNLU 95.526 4.910405 5
CSVTU 92.781 1.227601 5
PSOU 89.519 1.460776 5
KBTV 70.0524 5.755634 5
Total 111.9787 26.71526 40
Total PRSU 167.837 25.29644 10
GGU 162.655 24.68539 10
IGKV 156.282 23.57317 10
IKSV 152.4355 23.01549 10
HNLU 111.447 17.64683 10
CSVTU 108.2445 16.35693 10
PSOU 104.4055 15.78054 10
KBTV 79.3122 10.54443 10
Total 130.3273 36.76739 80
7. 5
DATA ANALYSIS & INTERPRETATION
Library Effectiveness at High Automation Level
Automation Level Readers Library Mean Std. Deviation Sample
HIGH Teachers PRSU 265.716 2.004665 5
GGU 262.056 2.004665 5
IGKV 256.892 1.661421 5
IKSV 210.084 2.004665 5
HNLU 204.96 1.653735 5
CSVTU 203.496 2.004665 5
PSOU 199.776 1.953735 5
KBTV 193.98 1.387635 5
Total 224.62 29.41744 40
Students PRSU 172.7154 1.303032 5
GGU 170.3364 1.303032 5
IGKV 167.0998 1.031647 5
IKSV 157.563 1.503498 5
HNLU 153.72 1.387635 5
CSVTU 152.627 1.496678 5
PSOU 149.877 1.503498 5
KBTV 145.485 1.786451 5
Total 158.678 9.653105 40
Total PRSU 219.2157 49.04153 10
GGU 216.1962 48.36675 10
IGKV 211.9959 47.3426 10
IKSV 183.8235 27.73136 10
HNLU 179.34 27.00585 10
CSVTU 178.0615 26.86214 10
PSOU 174.8265 26.35039 10
KBTV 169.7325 25.55911 10
Total 191.649 39.6745 80
Table – 7.3
7. 6
DATA ANALYSIS & INTERPRETATION
Total of Library Effectiveness at All Automation Levels
Table – 7.4
Automation Level Readers Library Mean Std. Deviation Sample
TOTAL Teachers PRSU 180.56 77.16646 15
GGU 176.1787 77.0355 15
IGKV 170.0547 77.28931 15
IKSV 152.0413 60.66289 15
HNLU 133.956 57.53472 15
CSVTU 132.004 57.26245 15
PSOU 127.828 57.56999 15
KBTV 114.2213 59.61868 15
Total 148.3555 68.31486 120
Students PRSU 127.4463 46.79474 15
GGU 124.9768 45.72796 15
IGKV 121.3603 44.94379 15
IKSV 116.8506 41.50914 15
HNLU 103.7122 39.35248 15
CSVTU 102.1328 39.33995 15
PSOU 99.73187 38.80941 15
KBTV 90.87793 40.47065 15
Total 110.8861 42.87564 120
Total PRSU 154.0032 68.27422 30
GGU 150.5777 67.47143 30
IGKV 145.7075 66.87448 30
IKSV 134.446 54.11668 30
HNLU 118.8341 50.8155 30
CSVTU 117.0684 50.60491 30
PSOU 113.7799 50.31182 30
KBTV 102.5496 51.4542 30
Total 129.6208 59.92886 240
7. 7
DATA ANALYSIS & INTERPRETATION
Table 7.4, reveals the overall mean score of 129.62 making a
favourable indication that Library Automations positively effects the Library
Effectiveness perception of Readers. Further, for the effects of various levels
of Library Automations on Library Effectiveness, the mean scores of 66.89,
130.33 and 191.64 respectively at the low, moderate and higher levels of
Library Automation make it clearly evident that higher the Library
Automation more will be the Library Effectiveness perception of the Readers.
For the second problem, that Teachers will perceive higher library
effectiveness compared to Students, the respective mean scores of
Teachers and Students as 148.36 and 110.87 proved that the Teachers of all
libraries perceived their library as more effective compared to their students.
Analysis of Variance Summary Table: Overall Library Effectiveness
Source
Type III
Sum of
Squares
df Mean
Square F
Level of
Significance
MAIN EFFECTS
1 Automation Level 622691.1 2 311345.5 30.148 0.000
2 Readers 84237.36 1 84237.36 16.52 0.001
3 Library 77203.63 7 11029.09 24.15 0.001
FIRST ORDER INTERACTION
1 Automation Level X
Readers 31572.19 2 15786.1 19.74 0.000
2 Automation Level X Library 31515.94 14 2251.139 19.21 0.001
3 Readers X Library 7213.936 7 1030.562 27.168 0.002
SECOND ORDER INTERACTION
1 Automation Level X
Readers X Library 3055.843 14 218.274 14.114 0.000
Error 871.021 192 4.537
Total 4890733 240
R Squared = .999 (Adjusted R Squared = .999)
Table – 7.5
7. 8
DATA ANALYSIS & INTERPRETATION
The Table 7.5 entitled as the “Analysis of Variance Summary Table:
Overall Library Effectiveness” exhibits the three way ANOVA results for the
dependent variable „Library Effectiveness‟.
According to Table 7.5 whereby significant main effect value (F =
20.148, p=.000) was found thus there remained no two ways to accept the
first hypothesis that Library Automations strongly affect the Library
Effectiveness.
Further the Figure 7.1 below also reveals that with the increase in level of
Library Automation level from low to higher, Library Effectiveness scores also
increase proportionately.
LOW MODERATE HIGH
Estimated Marginal Means of Library Effectiveness
at Various Levels of Library Automation
FIGURE : 1
Library
Effectiveness
(in Reader’s
Perception)
increases with
Library
Automation
Level
LOW MODERATE HIGH
Estimated Marginal Means of Library Effectiveness
at Various Levels of Library Automation
FIGURE : 1
Library
Effectiveness
(in Reader’s
Perception)
increases with
Library
Automation
Level
Library
Effectiveness
(in Reader’s
Perception)
increases with
Library
Automation
Level
Figure – 7.1
7. 9
DATA ANALYSIS & INTERPRETATION
For the second problem, that Teachers will show higher Library
Effectiveness compared to their Students National Companies. The Table
7.5, with significant main effect value (F = 16.52, p=.001) exhibited that
there are significant differences between perceptions of Teachers and
Students for the overall Library Effectiveness perceptions higher Library
Automations in their University Library. Further, the Figure 7.2 also shows such
significant difference among the two types of Readers for their perceptions
over Library Effectiveness. Therefore in view of such results, the second
hypothesis too was accepted.
Figure –7.2
TEACHERS STUDENTS
Estimated Marginal Means of Library Effectiveness
for Different Readers
Perceptions on
Library
Effectiveness
Varies Between
(Readers)
Teachers &
Students
(Teachers-High;
Students-Low)
ReadersTEACHERS STUDENTS
Estimated Marginal Means of Library Effectiveness
for Different Readers
Perceptions on
Library
Effectiveness
Varies Between
(Readers)
Teachers &
Students
(Teachers-High;
Students-Low)
Readers
7. 10
DATA ANALYSIS & INTERPRETATION
The third main effect, „Libraries‟ i.e. the eight University Libraries of
Chhattisgarh, studies the different levels of Automation in subjected
Libraries and its effect on the perception of the Readers over its
Effectiveness state. According to the Table 7.5, again the significant main
effect value (F = 24.15, p=.0001), indicated that the Libraries in the present
study vary with their levels of Automation and resulting in a varying reader
perception over their Effectiveness status.
Figure 7.3 below exhibits the above stated result that the reader
perception on Library Effectiveness varies across PRSU, GGU, IGKV, IKSV,
HNLU, CSVTU, PSOU & KBTV.
PRSU
Estimated Marginal Means of Library Effectiveness
at Different Libraries
GGU IKSV HNLU PSOUCSVYU KBTVIGKV
Libraries
Library
Effectiveness
(in Reader’s
Perception)
Varies at
Different
Libraries
PRSU
Estimated Marginal Means of Library Effectiveness
at Different Libraries
GGU IKSV HNLU PSOUCSVYU KBTVIGKV
Libraries
Library
Effectiveness
(in Reader’s
Perception)
Varies at
Different
Libraries
Figure – 7.3
7. 11
DATA ANALYSIS & INTERPRETATION
So far, we have discussed the role of independent variables – Level of
Library Automation, Readers and, Libraries. It would also provide useful and
important information if the joint effects of any two or more factors are
studied. The greatest advantage we get from analysis of variance technique
is that it provides an opportunity to examine the interaction between two or
more variables at a time.
It is possible for a treatment to affect one group differentially than it does to
another. Also it is possible for the effect of one treatment to depend on the
specific circumstances under which it is administered. When the effect of one
treatment depends on a second treatment, an interaction is obtained. Here,
in the three-way analysis of variance, we get three such first-order interactions
between any two factors, and one second-order interaction among all the
three factors.
The three first-order interactions that the present study undertook were the
interactions between (1) Level of Library Automation and Reader (2) Level of
Library Automation and Libraries and (3) Readers and Libraries. According to
Table 7.5, all three first-order order interactions were found to have significant
results. Table 7.5 exhibits these significant results as (F = 19.74, p =.000) for Level
of Library Automation and Reader; (F = 19.21, p =.001) for Level of Library
Automation and Libraries; (F = 27.168, p =.002) for Readers and Libraries. From
7. 12
DATA ANALYSIS & INTERPRETATION
such results it could be inferred that highly significant relationships exist
between the three independent variables used in the present study.
The figure – 7.4 exhibits the first order interaction between the Library‟s
Automation Level and their Readers. The figure suggests a visible gap in
perceptions of Readers i.e. Teachers and Students. Further, the perception of
Readers for Library Effectiveness Increases more with the movement from Low
to Moderate Level of Automation as compared to the movement from
Moderate to High Level of Automation. It is also worthwhile to mention that
with the change in Level of Library Automation the relative increase in Library
Effectiveness perception of Teachers is relatively higher as compared to that
of their Students.
Estimated Marginal Means of Library Effectiveness for Different Readers
at Various Levels of Library Automation
TEACHERS STUDENTS
LOW
MODERATE
HIGH
Readers
First Order
Interaction
Library
Effectiveness
Perceptions of
Teachers &
Students at All
Levels of
Library
Automation
Estimated Marginal Means of Library Effectiveness for Different Readers
at Various Levels of Library Automation
TEACHERS STUDENTS
LOW
MODERATE
HIGH
Readers
First Order
Interaction
Library
Effectiveness
Perceptions of
Teachers &
Students at All
Levels of
Library
Automation
Readers
First Order
Interaction
Library
Effectiveness
Perceptions of
Teachers &
Students at All
Levels of
Library
Automation
Figure – 7.4
7. 13
DATA ANALYSIS & INTERPRETATION
The figure 7.5 below exhibits the next first order interaction of Libraries at
various Levels of Automation. The figure clearly indicates that there is a
variance among the scores of various Libraries at the each Level of
Automation. Pandit Ravishankar Shukla University Library scored highest at
all levels, followed by Guru Ghasidas University, Indira Gandhi Krishi
Vishwavidyalaya, Indira Kala Sangeet Vishwavidyalaya, Hidayatullah
National Law University, Chhattisgarh Swami Vivekanand Technical
University, Pandit Sundarlal Sharma (Open) University and lastly Kushabhau
Thakre Patrakarita Avam Jansanchar Vishwavidyalaya. Notably, the
Effectiveness scores of highest and lowest scoring libraries vary least at low
level of automation followed by high level of Automation and vary most at
the moderate level of Automation.
Estimated Marginal Means of Library Effectiveness for Different Libraries
at Various Levels of Library Automation
LOW
MODERATE
HIGH
PRSU GGU IKSV HNLU PSOUCSVYU KBTVIGKV
Libraries
First Order
Interaction
Library
Effectiveness
Perception
Scores of all
Libraries at
Various Levels
of Library
Automation
Estimated Marginal Means of Library Effectiveness for Different Libraries
at Various Levels of Library Automation
LOW
MODERATE
HIGH
PRSU GGU IKSV HNLU PSOUCSVYU KBTVIGKV
Libraries
First Order
Interaction
Library
Effectiveness
Perception
Scores of all
Libraries at
Various Levels
of Library
Automation
First Order
Interaction
Library
Effectiveness
Perception
Scores of all
Libraries at
Various Levels
of Library
Automation
Figure – 7.5
7. 14
DATA ANALYSIS & INTERPRETATION
The second-order interaction giving the combined effect of Level of
Library Automation, Readers and, Libraries with the dependent variable Library
Effectiveness was also studied. According to Table 7.5, significant F-value for
this second-order interaction (F = 14.114, p=.000) was obtained for this joint
interaction indicating a significant interaction of all the independent variables
together with the dependent variable „Library Effectiveness‟. For Teachers, as
shown in Figure 7.6, it was revealed that Library Effectiveness perceptions of
Teachers increases with a rise in Automation level in all the University Libraries
covered in the present study. Also, this change in perception of teachers in all
libraries varies most at Moderate level of Automation followed by High level of
Automation and least at the Low level of Automation.
FOR TEACHERS
PRSU
GGU
IKSV
HNLU
PSOU
CSVYU
KBTV
IGKV
Low Moderate High
Estimated Marginal Means for Library Effectiveness
Libraries
Second Order
Interaction
Perceptions of
Teachers from
all Libraries at
all Levels of
Library
Automation
FOR TEACHERS
PRSU
GGU
IKSV
HNLU
PSOU
CSVYU
KBTV
IGKV
PRSU
GGU
IKSV
HNLU
PSOU
CSVYU
KBTV
IGKV
Low Moderate High
Estimated Marginal Means for Library Effectiveness
Libraries
Second Order
Interaction
Perceptions of
Teachers from
all Libraries at
all Levels of
Library
Automation
Second Order
Interaction
Perceptions of
Teachers from
all Libraries at
all Levels of
Library
Automation
Figure – 7.6
7. 15
DATA ANALYSIS & INTERPRETATION
Further, for Students, the Figure – 7.7 below indicates that like Teachers,
the Library Effectiveness perceptions of Students also increases with a rise in
Automation level in all the University Libraries. Also, this change in perception in
all libraries varies most at Moderate level of Automation followed by High level
of Automation and least at the Low level of Automation. However, as
compared to that of the Teachers, such variance is less at Low level and
relatively more at High level and highest at the Moderate level of Automation.
The Table-7.5 also reveals the overall area of association (R Squared
= .999) between the combined independent variables (Library
Automation, Readers, and Libraries) on the dependent variable (Library
FOR STUDENTS
PRSU
GGU
IKSV
HNLU
PSOU
CSVYU
KBTV
IGKV
Low Moderate High
Estimated Marginal Means for Library Effectiveness
Libraries
Second Order
Interaction
Perceptions of
Students from
all Libraries at
all Levels of
Library
Automation
FOR STUDENTS
PRSU
GGU
IKSV
HNLU
PSOU
CSVYU
KBTV
IGKV
PRSU
GGU
IKSV
HNLU
PSOU
CSVYU
KBTV
IGKV
Low Moderate High
Estimated Marginal Means for Library Effectiveness
Libraries
Second Order
Interaction
Perceptions of
Students from
all Libraries at
all Levels of
Library
Automation
Figure –7.7
7. 16
DATA ANALYSIS & INTERPRETATION
Effectiveness) to a significant 99.9%. The aforesaid figure of 99.9% for the
independent variables of the present study leaves only a mere 0.1% scope
for all other variables to influence the Library Effectiveness.