Benchmark – What Are the Data Saying
University:
GCU
Benchmark – What Are the Data Saying
Paper Instructions
Assessment Description
The DNP must have a basic understanding of statistical measurements and how they apply within the parameters of data management and analytics.
In this assignment, you will demonstrate understanding of basic statistical tests by performing the appropriate test for the given project data below using SPSS and by reporting the analyzed results in written paper.
General Requirements
Use the following information to ensure successful completion of the assignment
Use the “Comparison Table of the Variable’s Level of Measurement,” located in the DNP-830A folder of the DNP PI Workspace, to complete the assignment.
Review the “Working with Inferential Statistics” and “Working With Descriptive Statistics” tutorials, located in the DNP-830A folder of the DNP PI Workspace, for assistance as needed.
Doctoral learners are required to use APA style for their writing assignments. The APA Style Guide is located in the Student Success Center.
This assignment uses a rubric. Review the rubric prior to beginning the assignment to become familiar with the expectations for successful completion.
You are required to submit this assignment to LopesWrite. A link to the LopesWrite technical support articles is located in Class Resources if you need assistance.
Learners will submit this assignment using the assignment dropbox in the digital classroom. In addition, learners must upload this deliverable to the Learner Dissertation Page (LDP) in the DNP PI Workspace for later use.
Directions
Part 1
Using the data in the “Comparison Table of the Variable’s Level of Measurement” display the dependent variables and the level of measurement in a comparison table. You will attach the comparison table as an appendix to your paper.
After downloading the data set, run the appropriate statistics in SPSS based on the steps listed below.
Provide a conclusive result of the data analyses based on the guidelines below for statistical significance.
PAIRED SAMPLE T-TEST
Identify the variables BaselineWeight and InterventionWeight. Using the Analysis menu in SPSS, go to Compare Means, Go to the Paired Sample t-test. Add the BaselineWeight and InterventionWeight in the Pair 1 fields. Click OK. Report the mean weights, standard deviations, t-statistic, degrees of freedom, and p level. Report as t(df)=value, p = value. Report the p level out three digits.
INDEPENDENT SAMPLE T-TEST
Identify the variables InterventionGroups and PatientWeight. Go to the Analysis Menu, go to Compare Means, Go to Independent Samples t T-test. Add InterventionGroups to the Grouping Factor. Define the groups according to codings in the variable view (1=Intervention, 2 =Baseline).
Add PatientWeight to the test variable field. Click OK. Report the mean weights, standard deviations, t-statistic, degrees of freedom, and p level. Report t(df)=value, p = value. Report the p level out three digits
CHI-SQUARE
(Independent) Identify the variables BaselineReadmission and InterventionReadmission. Go to the Analysis Menu, go to Descriptive Statistics, go to Crosstabs. Add BaselineReadmission to the row and InterventionReadmission to the column. Click the Statistics button and choose Chi-Square. Select eta to report the Effect Size. Click suppress tables.
Click OK. Report the frequencies of the total events, the chi-square statistic, degrees of freedom, and p Report ê“2 (df) =value, p =value. Report the p level out three digits.
MCNEMAR (Paired)
Identify the variables BaselineCompliance and Go to the Analysis Menu, go to Descriptive Statistics, go to Crosstabs. Add BaselineCompliance to the row and InterventionCompliance to the column. Click the Statistics button and choose Chi-Square and McNemars. Select eta to report the Effect Size. Click suppress tables.
Click OK. Report the frequencies of the events, the Chi-square, and the McNemar’s p level. Report (p =value). Report the p level out three digits.
MANN WHITNEY U
Identify the variables InterventionGroups and Using the Analysis Menu, go to Nonparametric Statistics, go to LegacyDialogs, go to 2 Independent samples. Add InterventionGroups to the Grouping Variable and PatientSatisfaction to the Test Variable. Check Mann Whitney U. Click OK. Report the Medians or Means, the Mann Whitney U statistic, and the p level. Report (U =value, p =value). Report the p level out three digits.
WILCOXON Z
Identify the variables BaselineWeight and InterventionWeight. Go to the Analysis Menu, go to Nonparametric Statistics, go to LegacyDialogs, go to 2 Related samples. Add the BaselineWeight and InterventionWeight in the Pair 1 fields. Click OK. Report the Mean or Median weights, standard deviations, Z-statistic, and p Report as (Z =value, p =value). Report the p level out three digits.
Part 2
Write a 1,000-1,250-word data analysis paper outlining the procedures used to analyze the parametric and nonparametric variables in the mock data, the statistics reported, and a conclusion of the results. Include the following in your paper
- Discussion of the types of statistical tests used and why they have been chosen.
- Discussion of the differences between parametric and nonparametric tests.
- Description of the reported results of the statistical tests above.
- Summary of the conclusive results of the data analyses.
- Attach the SPSS outputs from the statistical analysis as an appendix to the paper.
- Attach the “Comparison Table of the Variable’s Level of Measurement” as an appendix to the paper.
Use the following guidelines to report the test results for your paper
- Statistically Significant Difference When reporting exact p values, state early in the data analysis and results section, the alpha level used for the significance criterion for all tests in the project. Example An alpha or significance level of < .05 was used for all statistical tests in the project. Then if the p-level is less than this value identified, the result is considered statistically significant. A statistically significant difference was noted between the scores before compared to after the intervention t(24) = 2.37, p = .007.
- Marginally Significant Difference If the results are found in the predicted direction but are not statistically significant, indicate that results were marginally Example Scores indicated a marginally significant preference for the intervention group (M = 3.54, SD = 1.20) compared to the baseline (M= 3.10, SD = .90), t(24) = 1.37, p = .07. Or there was a marginal difference in readmissions before (15) compared to after (10) the intervention ê“2(1) = 4.75, p = .06.
- Nonsignificant Trend If the p-value is over .10, report results revealed a non-significant trend in the predicted direction. Example Results indicated a non-significant trend for the intervention group (14) over the baseline (12), ê“2(1) = 1.75, p = .26.
- The results of the inferential analysis are used for decision-making and not hypothesis testing. It is important to look at the real results and establish what criterion is necessary for further implementation of the project’s findings. These conclusions are a start.
Portfolio Practice Immersion Hours
It may be possible to earn portfolio practice immersion hours for this assignment. Enter the following after the References section of your paper
Practice Immersion Hours Completion Statement DNP-830A
I, (INSERT NAME), verify that I have completed and logged (NUMBER OF) clock minutes/hours in association with the goals and objectives for this assignment. I also have tracked said practice immersion hours in the Lopes Activity Tracker for verification purposes and will be sure that all approvals are in place from my faculty and practice immersion preceptor/mentor before the end of the course.
We Work Hard So That You Don’t
We’ll write a 100% plagiarism-free paper in under 1 hour.
Sample Answer
Data analysis and interpretation form a critical part of research since it leads to the fulfillment of the project objectives. Through data interpretation, the researchers are capable of fully understanding the results in relation to the research questions and objectives since the raw data may not provide useful insights and meaning in connection to the project.
The implication is that the data should carefully be interpreted following the laid down principles to get the full meaning. Upon collecting the raw data, the data is then taken through statistical analysis and then represented in graphs, charts, and percentages as a way of data visualization (Kim et al.,2020).
As such, the purpose of this assignment is to carry run appropriate statistics in SPSS, provide the results for the analyzed data, and compose an analysis explaining the procedure used in the analysis of the non-parametric and parametric variables.
The Statistical Tests Used
Independent Sample T-test
This is a parametric test usually applied to explore if two groups or populations have a similar mean based on a particular variable. The independent T-test is used when the data to be analyzed has a continuous dependent variable not related within the groups, a categorical independent variable of at least two groups, while the data should have a normal distribution and must be a random sample (Gerald, 2018).
In addition, the data to be analyzed should possess an equal variance across the group with no outliers. Besides, every group must also have at least six study subjects, with each group having an equal number of study participants. As such, in the cases of the data provided, this test was chosen to help in exploring and determining the means between the two groups provided.
Paired Sample T-test
This is a statistical test usually used in comparing means from the same data sample to find out if the compared means are significantly different. Therefore, paired sample T-test is usually used in research designs such as control experiments, pre-test and post-test, and experimental designs.
It is particularly applied when a researcher needs to make comparisons between two points, measurements, conditions, or matched pair (Afifah et al.,2022).
It is worth noting that the tests are not applicable in cases where there are unpaired samples with no normal distribution around the mean and have more than two units.
This test has been chosen since there is a need to compare the weight at baseline and the intervention weight with the main focus of determining if there is a significant difference. As such, through the test, it will be possible to determine if there has been a change in weight.
McNemar
This is another test that has been applied to the provided data sample. The McNemar test is used as a way of checking the marginal homogeneity of two different dichotomous variables. As such, it is used for two groups having similar participants and when the data is paired.
The data to be analyzed should have an independent variable with two related groups, and the groups to be considered should be mutually exclusive and with a random sample (Pembury Smith & Ruxton, 2020). Therefore, the McNemar test was used in this case for comparing the compliance of the baseline to that of the intervention for the research subjects’ data.
Chi-square
This statistical test is usually applied in determining how two variables are associated; hence it is also referred to as the chi-square test of association. While it is key to identifying associations between variables, it cannot be used to draw inferences. For the Chi-Square test to be used, the data under consideration should have two categorical variables at least two categories in every variable (Connelly, 2019).
The subjects should also be of a large sample and unrelated. As such, this test was also chosen in this case since there was a need to explore the intervention readmission and baseline readmission associations.
Wilcoxon Z
Wilcoxon Z is a statistical test used to compare the means of related samples. As such, it is applied in the analysis of repeated measures without or with intervention. Therefore, this test can be used in cases where there are matched subjects without an intervention and another with an intervention (Kim et al.,2020).
For it to be used appropriately, the pair should be from a random sample and also independent of other pairs. This test was chosen to help in comparing the mean ranks of the intervention weight pairs and those of the baseline weight.
Mann Whitney U
Mann Whitney U test is a statistical test used when comparing the difference between independent samples that do not possess normal distribution. For the test to be used, all the variables should be in ordinal or continuous scales.
In most cases, this test is used in cases when one of the considered parameters does not allow the use of independent sample t-tests (Kim et al.,2020). As such, the statistical test was used as there was a need to evaluate if there was a difference in satisfaction between the intervention and baseline data.
Parametric and Non-Parametric Tests
Parametric and non-parametric tests are both used in data tests and analysis. The parametric tests are tests that make the assumption that sample data or population has a normal distribution around the mean. Examples of these tests include paired t-test, 2-sample test, 1-sample t-test, and one-way ANOVA.
On the other hand, the non-parametric tests do not consider such an assumption; hence using such an assumption during the analysis may lead to inappropriate interpretations (Orcan, 2020). Some of the non-parametric tests include the 1-sample Wilcoxon test, Mann-Whitney Test, Signed-rank test, and Kruskal Wallis test.
The non-parametric test is used in cases when meaningful interpretations can be drawn from the median with data samples not appearing normal and small sample.
Summary of Results
Paired Sample T-test
Analysis was performed on the sample data provided. While the baseline weight mean was found to be 217.5 lbs, with an SD of 53.40, that of the intervention was found to be 178.3 lb, with an SD of 44.88. The results from the SPSS output show that t=7.188, df=29 t(df)=2.05, with a 95% confidence interval. The p-value is 0.000, and p<0.005. Therefore, the difference between the means was statistically significant.
Independent Sample T-test
This test shows that the mean weight for the intervention group is 218.3 lb with an SD of 54.8, a p-value of 0.934, and t (28) = 0,084 at a 95% confidence interval. The assumption made is that the variance is equal. The output t=0.084 is lower than 1.074, which is the critical value. Hence the result is insignificant. As such, the sampling variability affects the baseline weight and the intervention weight mean.
McNemar
The McNemar test shows that the frequency of events is 30 with a chi-square value of 1.639 and a p-value of 0.007. The implication is that it is statistically significant since it is lower than 0.05. As such, there is a difference between the intervention and baseline compliance is significant.
Chi-square
The analysis using Chi-Square shows a chi-square value of 1.639 with 1 df and a p-value of 0.008. This value is lower than 3.84, which is the critical value. As such, the difference between the intervention and baseline readmissions is significant.
Wilcoxon Z
The analysis using Wilcoxon Z shows a mean difference of 11.5, Z=-4.307, and p=.000. The implication is that the mean ranking between baseline weight and intervention weight is statistically significant.
Mann Whitney U
The analysis using Mann Whitney U shows 18.8 and 12.2 as the baseline and intervention group mean, respectively. The Mann-Whitney test is 63.0 with a p-value of 0.035, a value lower than 0.05. The implication is that the result is that there is a statistical difference. The mean level of satisfaction is also lower in the intervention group in comparison to the baseline.
Conclusion
The SPSS software was used in analyzing the data to give results that can be interpreted to enhance an understanding of the collected data. Various statistical tests were used to obtain the required interpretation. Specifically, they offer appropriate information regarding the efficacy of the used intervention. For example, there was a significant difference in weight when an intervention was used. The groups also displayed a variance in both satisfaction and readmission.
References
- Afifah, S., Mudzakir, A., & Nandiyanto, A. B. D. (2022). How to calculate paired sample t-test using SPSS software From step-by-step processing for users to the practical examples in the analysis of the effect of application anti-fire bamboo teaching materials on student learning outcomes. Indonesian Journal of Teaching in Science, 2(1), 81-92. https //doi.org/10.17509/ijotis.v2i1.45895
- Connelly, L. (2019). Chi-square test. Medsurg Nursing, 28(2), 127–127. https //www.proquest.com/openview/04d2ff080887f9111b68eb7490a9630a/1?pq-origsite=gscholar&cbl=30764
- Gerald, B. (2018). A brief review of independent, dependent and one sample t-test. International Journal of Applied Mathematics and Theoretical Physics, 4(2), 50-54. Doi 10.11648/j.ijamtp.20180402.13
Kim, M., Mallory, C., & Valerio, T. (2020). Statistics for evidence-based practice in nursing. Jones & Bartlett Publishers.
Orcan, F. (2020). Parametric or non-parametric Skewness to test normality for mean comparison. International Journal of Assessment Tools in Education, 7(2), 255–265. https //doi.org/10.21449/ijate.656077
- Pembury Smith, M. Q., & Ruxton, G. D. (2020). Effective use of the McNemar test. Behavioral Ecology and Sociobiology, 74, 1–9. Doi 10.1007/s00265-020-02916-y
We Work Hard So That You Don’t
We’ll write a 100% plagiarism-free paper in under 1 hour