You are on page 1of 4

Theoretical knowledge: Theoretical knowledge acquired in the classroom setting is necessary to enhance

the clinical performance of nursing students in the same way that the latter reinforces what is learned in
the classroom. However academic grade does not always reflect the competence of students in clinical
setting. This study was conducted to determine a possible correlation between student academic
performance in the nursing specialization subjects and their clinical performance. (Paragraph copied from
an online article, Correlation of the academic and clinical performance of Libyan nursing students.)

Design and Method: The research employed an experimental approach using non-existing data sets. The
objective of this research is to determine the strength of linear relationship between Self-efficacy and Clinical
Performance.

Hypothesis testing

Ho: There is no correlation between self-efficacy and clinical performance of student nurses-that is,
linear relationship among the independent variables does not exists.

Ha: There is a correlation between self-efficacy and clinical performance of student nurses-that is,
linear relationship among the independent variables does not exists.

𝐻0 : 𝜌 = 0; 𝐻1 : 𝜌 ≠ 0
Assumptions test was used in order to verify the correct method to be used for correlational analysis

Assumptions Test

Variables:

1. Self-efficacy
This variable was computed from three sub-variables namely; Skills, Attitude, and
Knowledge. Ordinal level, though Likert scale, was used to assess respondents’ skills
and attitude. On the other hand, ratio level was used for knowledge. Using the
concept of cost-averaging in financial markets, these three sub-variables was
integrated through grading system. Since ordinal scale was used for the two sub-
variables and ratio for the other one, Self-efficacy-as a whole, was established as a
ratio level.

2. Clinical performance
The data of this variable was based from the respondents’ academic results on their
clinical performance. Because of this, it is classified as a variable under ratio level.

Outliers and Normality Tests

Graphical and formal tests were used to establish the validity of data under normal distribution. First,
for the graphical test, boxplots were formulated. According to Figure 1, both of the two variables manifested
outliers in their respective boxplots.
Because of this, the data collected from the two variables does not follow normal distribution.
However, in order to establish a verify conclusion to its normality, another graphical test was tested. This
time, normal probability plots were used for the two variables.

Two normal probability plots presented above showed vague results. In order to classify a variable
that follows normality, one must show its data points in probability plots close to the line. Most of the data
points for both probability plots are close to their respective lines. However, there are data points that are too
far. These lines can cause erratic and biased results under normal distribution. Moreover, these data points
are also found in outlying regions of the normal probability plots.

To finalize the assumption on normality, formal tests were conducted for verification. Wilk-Shapiro
test was used for this sub-assumption.

𝐻0 : 𝑇ℎ𝑒 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑠𝑎𝑚𝑝𝑙𝑒 𝑓𝑜𝑙𝑙𝑜𝑤𝑠 𝑛𝑜𝑟𝑚𝑎𝑙 𝑑𝑖𝑠𝑡𝑟𝑖𝑏𝑢𝑡𝑖𝑜𝑛;

𝐻1 : 𝑇ℎ𝑒 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑠𝑎𝑚𝑝𝑙𝑒 𝑑𝑜𝑒𝑠 𝑛𝑜𝑡 𝑓𝑜𝑙𝑙𝑜𝑤 𝑛𝑜𝑟𝑚𝑎𝑙 𝑑𝑖𝑠𝑡𝑟𝑖𝑏𝑢𝑡𝑖𝑜𝑛;


Using PAST Statistical Software, data points were calculated to assess the normality of the two
variables. According from this, the calculated p-value is 0.006897.

Decision rule: 𝑝 − 𝑣𝑎𝑙𝑢𝑒𝑆𝐸𝐿𝐹−𝐸𝐹𝐹𝐼𝐶𝐴𝐶𝑌 = 0.006897 < 0.05


𝑝 − 𝑣𝑎𝑙𝑢𝑒𝐶𝐿𝐼𝑁𝐼𝐶𝐴𝐿 𝑃𝐸𝑅𝐹𝑂𝑅𝑀𝐴𝑁𝐶𝐸 = 0.01542 < 0.05
Decision: reject 𝐻0
Because of this, both of the variables does not follow normal distribution. Hence, the data sets
presented in this research follows non-parametric distribution.

Linearity

There must be a monotonic relationship between the two variables. A monotonic relationship exists
when either the variables increase in value together, or as one variable value increases, the other variable
value decreases. There are a number of ways to see monotonicity of the variables, scatterplot was used in
this research.
NOTE: Spearman's correlation determines the degree to which a relationship is monotonic. Put
another way, it determines whether there is a monotonic component of association between two continuous
or ordinal variables. As such, monotonicity is not actually an assumption of Spearman's correlation. However,
you would not normally want to pursue a Spearman's correlation to determine the strength and direction of a
monotonic relationship when you already know the relationship between your two variables is not monotonic.
Instead, the relationship between your two variables might be better described by another statistical measure
of association. For this reason, it is not uncommon to view the relationship between your two variables in a
scatterplot to see if running a Spearman's correlation is the best choice as a measure of association or whether
another measure would be better.

Therefore, monotonic relationship can be found in the existing data sets.

From all the assumptions examined using formal and graphical tests, it has noted that the
suited correlational method to be used for this analysis is Spearman’s Rank Order Correlation Test.
This specific test was suited for non-parametric data, including this research, which is found not
under normal distribution. Moreover, Spearman’s Rank Order test minimizes truncate errors than
the Parametric-Pearson’s r test.

Spearman’s Rank Order Test

Ho: There is no correlation between self-efficacy and clinical performance of student nurses-that is,
linear relationship among the independent variables does not exists.

Ha: There is a correlation between self-efficacy and clinical performance of student nurses-that is,
linear relationship among the independent variables does not exists.

𝐻0 : 𝜌 = 0; 𝐻1 : 𝜌 ≠ 0
Decision Rule: 𝑅𝑒𝑗𝑒𝑐𝑡 𝑡ℎ𝑒 𝑛𝑢𝑙𝑙 ℎ𝑦𝑝𝑜𝑡ℎ𝑒𝑠𝑖𝑠 𝑖𝑓 𝑝 − 𝑣𝑎𝑙𝑢𝑒 < 0.05, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒, 𝑓𝑎𝑖𝑙 𝑡𝑜 𝑟𝑒𝑗𝑒𝑐𝑡 𝐻0
Self-efficacy Clinical Performance
Self-Efficacy r=0.25762
Clinical Performance P-value=0.16135
Decision: p-value=0.16135>level of significance=0.05, fail to reject the null hypothesis
Fail to reject the null hypothesis

Conclusion: At 5% level of significance, we provided enough evidence to say that there is no


enough evidence of a linear relationship between Self-efficacy and Clinical Performance. However,
results also showed a significant yet small amount of r (r=0.25762). This only means that even
though hypothesis testing concluded that no enough evidence for a linear relationship for the
variables mentioned above, it is still safe to say that the linear relationship between Self-efficacy
and clinical performance is very weak.

Hypothesis testing conclusion: no enough evidence of correlation between the variables


R: a very small correlation but also very weak linear relationship

You might also like