Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 5

FAKULTI PENDIDIKAN TEKNIKAL DAN VOKASIONAL

Universiti Tun Hussein Onn Malaysia (UTHM)


86400 Parit Raja Batu Pahat, Johor.

MBE 12303 : EDUCATIONAL DATA ANALYSIS AND


REASONING SECTION 1

ASSIGNMENT 4:
t – Tests and Non-Parametric
Tests

PREPARED BY: SUNARDI

MATRIKS NO : GB220138

LECTURER : PROF. MADYA DR. KAHIROL BIN MOHD SALLEH


Using the College Student data file, do the following problems. Develop table/figure and discuss the
key parts of the output.

1. RQ : Is there a significant difference between the genders on average student height? Explain, and provide
a full interpretation of the result

The gender difference in average student height was determined using an independent sample t test.
Examination of the two group means reveals that female students' height (M=64.13) is substantially
lower than male students' height (M=70.23). Further details the Levene's Test on the premise that the
variances of the two groups are identical. As is, the Levene's F is statistically significant (Sig. 0.05). The
Equal variances not assumed line with t = 8.802, df = 45.863 and Sig. = 0.273 is utilized in this instance
(p 0.001).

Table 1.1 : Independent samples t-test (n = 50)

Variable M SD t df p d
Student height 8.80 45.86 0.27 0.25
in inches
Male 70.23 2.80
Female 64.13 2.07

2. RQ: is there a difference and also an association between the number of hours students study and the
hours they work?

We used paired sample t tests to compare students' study time to their job time. Table 2.1 displays the
matched Sample Statistics for time spent studying against time spent working. Mean weekly hours spent
working are 26.12, whereas the mean weekly hours spent studying are 15.53. The association coefficient
between how much time students spend studying and how much time they spend working is rather poor
(r = 0.22). Using a paired samples test, we find that the significance level is 0.001. Table 2.2 shows that,
on average, students put in more time studying than working each week, with a mean difference of
15.53 hours per week; however, the effect size is calculated by dividing the mean of the paired
difference by the standard deviation of the difference, which is 15.34 hours per week, yielding a value of
d = 0.69.
Table 2.1 : Paired Sample Statistic (n = 49)

Variable Mean SD r Sig.


Hours of study per week 15.53 8.37 0.22 0.13
Hours per week spent 26.12 14.86
working

Table 2.1 : Paired Sample Test (n = 49)

Variable M SD t df d
Hours of study per -10.59 15.34 -4.82 48 0.69
week - Hours per
week spent working
P < 0.001

3. Write another question that can be answered from the data using a paired sample t test. Run the t test
and provide a full interpretation.

RQ : Is there an association between the student’s height and same sex parent’s height?

We used the paired sample t test. The figures shown above reflect the average height of pupils as well
as the height of their parents. According to the findings, the average height of pupils is much more
than the average height of their parents. On the other hand, the correlation value of 0.842
demonstrates that there is a strong relationship between the two variables. The height of the parent
will rise in proportion to the student's growing stature, and vice versa.

Table 3.1 : Paired sample t test (n = 50)

Variable M SD t df p r d
Student’s height 67.30 3.94 1.32 48 0.19 0.84 0.28
Parent’s height 66.78 5.10
4. Are there differences between males and females in regard to the average number of
hours they
(a) study
(b) work
(c) watch TV?
Hours of study is quite skewed so compute an appropriate nonparametric
statistic.

To determine the differences between males and females in terms of average hours spent
studying, working, and watching television, non-parametric tests were used. Except for the
disproportionate hours of study, all assumptions were satisfied. Table 4.1 reveals a
statistically significant difference between males and females in terms of study hours (p =
0.045) between males and females. A comparison of the two group means reveals that the
average number of hours spent studying by females (M=18.02) is considerably fewer than
that of males (M=13.35). 4.67 points separate the respective norms. The magnitude of the
effect, r = 0.28. Males and females did not differ in working hours (p=0.99), but males
spent more time at work. observing television for longer (p=0.20), which was statistically
significant.

Table 4.1 : Non-parametric test

Variable M SD t df p r
Hours of study per week -2.07 44.76 0.045 0.28
Males 13.35 7.27
Females 18.02 8.80
Hours per week spent 0.16 47 0.99

Males 26.15 15.95


Females 26.09 13.87
Amount of TV watched 1.29 48 0.20

Males 13.04 6.33


Females 10.83 5.75

You might also like