Testing Lecture Comprehension Through Listening-to-summarize Cloze Tasks

with their normal teaching agenda. In a word, there must be a balance between
reliability of the sample size and validity of the survey and hence the sample size
for questionnaire survey in this project has been enlarged to its utmost based on the
facilities and resources available.

5.5.2.2 Teachers

According to statistics generated from teacher questionnaires, Cronbach’s Alpha
(see Table5.5) in the reliability statistics is 0.976, a very highfigure showing
satisfactory internal reliability of the questionnaire, which means all the items of the
questionnaire are valid to probe into the skills represented by TEM 8 Mini-lecture
and Gap-filling task.
In the Kaiser-Meyer-Olkin (KMO) and Bartlett’s test table (see Table5.6), the
KMO measures the sampling adequacy which should be greater than 0.6 as a
suggested minimum for a satisfactory factor analysis to proceed. KMO measure
above 0.9 demonstrates a marvelous indication of doing factor analysis. The current
KMO measure for the teacher questionnaire is 0.953, very suitable for main factor
analysis. In the same table there is the Bartlett’s Test of Sphericity which testifies
the null hypothesis that the correlation matrix is an identity matrix, or in another
word, the variables are independent and the corresponding P << 0.05. It rejects the
null hypothesis that variables in the questionnaire are independent of each other. In
this case, the Bartlett’s Test of Sphericity of the teacher questionnaire is significant
and the correlation matrix is not an identity matrix, which means the variables are
correlated and the datafit an exploratory factor analysis.
The Table of Total Variance (see Table5.7) shows all the factors extracted from
the analysis along with their eigenvalues, the percent of variance attributable to
each factor, and the cumulative variance of the factor and the previous factors. The
table shows that thefirst factor accounts for 55.433% of the variance, which means
thefirst extracted factor can actually explain more than half of the total variance, the
second 5.154%, the third 4.426% and the fourth 3.505%. The four factors altogether

Table 5.5 Reliability
statistics of teacher
questionnaire

Reliability statistics

Cronbach’s Alpha N of items

0.976 35

Table 5.6 KMO and
Bartlett’s test of teacher
questionnaire

KMO and Bartlett’s test

Kaiser-Meyer-Olkin measure of sampling

adequacy

0.953

Bartlett’s test of

sphericity

Approx. Chi-square 5941.637

Df 595

Sig. 0.000

5.5 Results of Questionnaire Survey 51