Running Head: UNIT 6 ASSIGNMENT 1
Unit 6 Assignment 1
Introduction
Correlation is as easy as understanding that one thing may be an association
... [Show More] with
another, as it’s measured to analyze how precisely two variables relate. Through
correlation a strong or weak relationship between variable can be seen (Warner el at,
2013). For this Unit’s assignment, a dataset will be analyzed to the assumptions of
correlation for GPA and Final, as providing supporting details of the strengths and
limitations of the correlational analysis.
Section 1: Data File Description
The dataset displays the relationship between gender, GPA, total and final grade.
Gender can be categorized as female or male and is considered a nominal scale of
measurement because of the nonexistence of intrinsic order (Warner el at, 2013).An
interval scale on the scale of measurement can be viewed in the variables of GPA, total
and final grade., in which, the GPA column represents the average value of the
accumulated final grades earned for the courses, the Totals are described as total numers
of points earned and the Final grade reflects the number of questions answered correctly
on the final exam. For this dataset, the correlation used would be known as Pearson’s r
since it is used to describe the strength of a linear relationship between two quantitative
variables (Warner, 2013). When analyzing the interval scale dataset, some figures can be
2
Running Head: UNIT 6 ASSIGNMENT 1
determined. For example, the sample size of 105 students with a GPA ranging from 1.14
to 4.00.
Section 2: Assumptions of Correlation
Figure 1
3
Running Head: UNIT 6 ASSIGNMENT 1
Figure 2
4
Running Head: UNIT 6 ASSIGNMENT 1
Some assumptions can be made for this dataset since it’s identified as a Pearson’s
r correlation. For instance, X and Y seem to be independent displaying a normal
distribution of the liner relationship between the variables.
In Figure 1 histogram, one can assess that there is a negative skewness being
displayed with a unimodal distribution showing low outliers data points. In addition,
Figure 1 reflects a positive kurtosis value since it indicates that the distribution has a
heavier tail and a sharper peak than the normal distribution (Warner, 2013). Warner
(2013) further explains that in cases like this, it may mean that the outliers may be a
variability in the measurement indicating experimental error.
In Figure 2 histogram, the analysis of the relationship between frequency and
GPA shows more of a normal curve being displayed with a multimodal distribution since
it has two reflecting peaks. In addition, a normal Kurtosis reflects in the histograms since
the peak is not as sharp as in Figure 1.
Figure 3
5
Running Head: UNIT 6 ASSIGNMENT 1
Descriptive Statistics
N Mean
Std.
Deviation Skewness Kurtosis
Statisti
c
Statisti
c Statistic
Statisti
c
Std.
Error
Statisti
c
Std.
Error
gpa 105 2.9950 .67370 -.317 .236 -.656 .467
final 105 61.48 7.943 -.335 .236 -.332 .467
Valid N
(listwise)
105
Figure 3 displays the descriptive statistics on GPA and Final Scores where
amounts of skewness and kurtosis was added to the chart. The IBM SPSS Statistics 23
Step by Step (2016) Textbook describes that a variable is recognized as perfectly
associated with itself when the diagonals are at 1.000s. This means that both skewness
and Kurtosis may confirm a statistic level of 1.000s or more to be considered at an
excellent range. Once the values increase to close to an amount of 2.000s then they are
considered acceptable but if it may surpass values of more than 2.000s, it becomes
considered unacceptable. Based on the above displayed data, one can determine that there
is an excellent range for both skewness and kurtosis. The standard deviation for the final
scores is of 7.943 with a mean of 61.48. For GPA, the standard deviation is of .67370
with a mean of 2.9950.
6
Running Head: [Show Less]