| Course | NUR 617 Foundational Concepts in Science and Statistics |
|---|---|
| Module | Module 4 |
| Paper type | SPSS data analysis assignment with output and interpretation |
| Length | About 1,042 words, 6 pages |
| Format | APA 7 student paper |
| School | Arizona State University |
| Program | Doctorate of Professional Practice in Regulatory and Clinical Research Management |
| Updated | October 2026 |
Free sample paper for NUR 617 Module 4
Did the Sleep Hygiene Sessions Lower Insomnia Scores? Dependent and Independent Samples t-Tests on Illustrative Pilot Data
Student Name
Edson College of Nursing and Health Innovation, Arizona State University
NUR 617: Foundational Concepts in Science and Statistics
Instructor Name
Month Day, Year
Did the Sleep Hygiene Sessions Lower Insomnia Scores? Dependent and Independent Samples t-Tests on Illustrative Pilot Data
Data and Research Questions
The datasets for this assignment are provided in the course shell. This sample uses an illustrative dataset built to demonstrate the same procedures, so its numbers describe no real study. The scenario is a four-week pilot of nurse-led sleep hygiene education in which 48 adults with insomnia symptoms were randomly assigned to education (n = 24) or usual care (n = 24). Insomnia severity was measured at baseline and at week 4 with the Insomnia Severity Index (ISI), a seven-item scale scored from 0 to 28 on which 0 to 7 indicates no clinically significant insomnia, 8 to 14 subthreshold insomnia, 15 to 21 moderate insomnia and 22 to 28 severe insomnia (Bastien et al., 2001). The total score was treated as an interval-level variable, as is usual for summed rating scales.
Two research questions guided the analysis. First, within the education group, did ISI scores change from baseline to week 4? Because the same 24 people were measured twice, this calls for a dependent samples t-test. The null hypothesis is that the mean difference is zero, tested two-tailed at alpha = .05. Second, at week 4, did ISI scores differ between the education and usual care groups? Because the groups contain different people, this calls for an independent samples t-test, with the null hypothesis that the two population means are equal.
Assumption Checks
For the dependent samples test, the assumption that matters is that the difference scores are approximately normal. A Shapiro-Wilk test on the 24 difference scores gave W = .93, p = .077, and the boxplot showed no extreme values, so the assumption was judged reasonable. Polit (2010) observes that the t-test tolerates mild skew well, more so when the two groups are equal in size.
For the independent samples test, three assumptions were checked. Observations are independent because each participant belongs to only one group. ISI scores in each group were roughly symmetric on histograms. Homogeneity of variance was tested with Levene's test, F = 1.04, p = .313. Because this test was not significant, the "equal variances assumed" row of the SPSS output is the one interpreted below.
SPSS Output: Dependent Samples t-Test
In the education group, ISI scores fell from a mean of 15.75 (SD = 3.74) at baseline to 12.33 (SD = 4.26) at week 4, a mean reduction of 3.42 points, 95% CI [2.32, 4.51], t(23) = 6.47, p < .001. The effect size for paired data, d = 3.42 / 2.59 = 1.32, is large by conventional benchmarks (Lakens, 2013). On average, the group moved from the bottom of the moderate range into the subthreshold range. The interval does not include zero, which matches the significant test, and it indicates that the true mean reduction is plausibly between about 2 and 4.5 points.
A significant p value says nothing by itself about whether the change matters to patients. Morin et al. (2011) linked a drop of roughly 8 points on the ISI to moderate improvement rated by clinicians, so a mean change of 3.42 points is real but modest. A pre-post design without a comparison group also cannot rule out improvement that would have happened anyway, which is why the second question matters.
| Paired Samples Statistics | Mean | N | Std. Deviation | Std. Error Mean |
|---|---|---|---|---|
| ISI baseline | 15.75 | 24 | 3.74 | 0.76 |
| ISI week 4 | 12.33 | 24 | 4.26 | 0.87 |
| Paired Samples Test (baseline minus week 4) | Value | |||
| Mean difference | 3.42 | |||
| Std. deviation of differences | 2.59 | |||
| Std. error mean | 0.53 | |||
| 95% CI of the difference | 2.32 to 4.51 | |||
| t | 6.47 | |||
| df | 23 | |||
| Sig. (2-tailed) | < .001 | |||
| Correlation, baseline with week 4 | r = .80 |
SPSS Output: Independent Samples t-Test
At week 4, the education group's mean ISI score (M = 12.33, SD = 4.26) was 4.79 points lower than the usual care group's (M = 17.12, SD = 5.28), t(46) = -3.46, p = .001, 95% CI [-7.58, -2.00]. Using the pooled standard deviation of 4.79, Cohen's d = 1.00, a large difference. The negative sign reflects SPSS subtracting the usual care mean from the education mean; lower scores mean fewer insomnia symptoms, so the difference favors education.
| Group Statistics at Week 4 | N | Mean | Std. Deviation | Std. Error Mean |
|---|---|---|---|---|
| Education | 24 | 12.33 | 4.26 | 0.87 |
| Usual care | 24 | 17.12 | 5.28 | 1.08 |
| Independent Samples Test | Equal variances assumed | Equal variances not assumed | ||
| Levene's F (Sig.) | 1.04 (.313) | not applicable | ||
| t | -3.46 | -3.46 | ||
| df | 46 | 44.03 | ||
| Sig. (2-tailed) | .001 | .001 | ||
| Mean difference | -4.79 | -4.79 | ||
| Std. error difference | 1.38 | 1.38 | ||
| 95% CI of the difference | -7.58 to -2.00 | -7.58 to -2.00 |
Conceptual Questions
Why use a dependent samples test for the first question? The baseline and week 4 scores come from the same people and correlate strongly (r = .80). The dependent test works with each person's difference score, which removes stable differences between people from the error term. Running an independent test on these data would ignore the pairing, inflate the standard error and reduce power.
What does p = .001 mean here? Suppose education and usual care produced identical population means. Samples of this size would then show a gap of 4.79 points or more, in either direction, only about once in 1,000 draws. Nor is the figure a 99.9% probability that the education helps.
What limits the week 4 comparison? The groups were not equal at baseline. Usual care participants started at 17.29 (SD = 4.13) against 15.75 for the education group; this gap was not significant, t(46) = -1.35, p = .18, but it accounts for about 1.5 of the 4.79 points seen at week 4. Usual care scores barely moved (17.29 to 17.12). A stronger analysis would compare change scores between groups or adjust for baseline with analysis of covariance, a method beyond Chapter 6.
Conclusion
In this illustrative pilot, insomnia severity fell significantly within the education group and was significantly lower than usual care at week 4, with large effect sizes in both analyses. The size of the within-group change falls short of a clinically meaningful benchmark, and the baseline imbalance means part of the between-group difference predates the intervention, so the results support a larger trial rather than a conclusion about effectiveness.
References
Bastien, C. H., Vallieres, A., & Morin, C. M. (2001). Validation of the Insomnia Severity Index as an outcome measure for insomnia research. Sleep Medicine, 2(4), 297-307. https://doi.org/10.1016/S1389-9457(00)00065-4
Lakens, D. (2013). Calculating and reporting effect sizes to facilitate cumulative science: A practical primer for t-tests and ANOVAs. Frontiers in Psychology, 4, Article 863. https://doi.org/10.3389/fpsyg.2013.00863
Morin, C. M., Belleville, G., Belanger, L., & Ivers, H. (2011). The Insomnia Severity Index: Psychometric indicators to detect insomnia cases and evaluate treatment response. Sleep, 34(5), 601-608. https://doi.org/10.1093/sleep/34.5.601
Polit, D. F. (2010). Statistics and data analysis for nursing research (2nd ed.). Pearson.
Reading the NUR 617 Module 4 assignment instructions
Assignment 1 is the first of three 20-point analysis assignments in NUR 617, and it covers Chapter 6, dependent and independent samples t-tests. The syllabus describes the same process for all three: download a Word document holding the instructions, run the analysis in SPSS on the dataset provided in Canvas, type your answers into the document, paste your output tables and upload the finished file as a .docx or .pdf. Each assignment asks you to conduct the analysis, obtain output, interpret the results and demonstrate conceptual understanding, and the detailed questions and grading rubric sit in the course shell. Expect at least one question that needs a paired test and one that needs a test for two separate groups, plus questions on assumptions and on what the numbers mean in plain terms.
Inside the NUR 617 Module 4 example
Built as a completed answer document, the sample follows the order an analyst works in. It opens by disclosing that the dataset is illustrative, describes the variables and scale, and states each research question with its test and null hypothesis. Assumption checks come next, each tied to the output it governs, including Levene's test and the choice of row. Then each test has its own output tables, copied in the layout SPSS produces, followed by an APA results sentence carrying the means and standard deviations, the t statistic with its df, the exact p and the interval. Effect sizes are calculated by hand and explained. A section of conceptual answers covers test choice, the meaning of p and a design problem in the data, and a short conclusion keeps the findings in proportion.
Reading the NUR 617 Module 4 grading rubric
Since the rubric for each assignment is in Canvas rather than the syllabus, read it before you start. In SPSS assignments like this one, points usually divide among choosing and running the correct test, including complete and readable output, reporting results accurately in APA style and answering the conceptual questions with reasons. Accuracy carries the most weight: a correct t value reported with the wrong degrees of freedom, or the wrong Levene row, costs points even when the conclusion is right. Interpretations that go beyond "significant" to state direction, size and meaning tend to score at the top. Faculty return written feedback within 72 hours, according to the syllabus, so use Assignment 1's comments to sharpen the next two analyses. Late work loses 10% per week.
NUR 617 Module 4 help: mistakes that cost marks
Many students paste every table SPSS produces and then interpret none of them. Paste only what the question needs and refer to it by name. The second most frequent slip is reading the "equal variances not assumed" row without checking Levene's test first, or reading it backward. Report exact p values to three decimals, writing p < .001 only when SPSS shows .000, and never write p = .000. State the direction of a difference in words, since a negative t confuses readers. Check that your degrees of freedom match the test, n minus 1 for paired data and total n minus 2 for two groups. If you send the desk your output and the assignment questions, the interpretation can be drafted around your own numbers.
Write yours, or have the desk draft it
This paper is an original model document written by our desk, not a submitted student paper and not an official Arizona State University document. Read it for the moves, then write your own to the instructions in your classroom. If you want one built to your exact prompt and rubric, the first custom sample is free and arrives in 24 to 48 hours.
More NUR 617 and Doctorate of Professional Practice in Regulatory and Clinical Research Management sample papers
- NUR 617 Module 3: Discussion Board 2: Challenging Concept (Confidence Intervals and Statistical Inference)
- NUR 617 Module 5: Assignment 2: One-Way ANOVA in SPSS
- NUR 617 Module 7: Assignment 3: Correlation and Simple Linear Regression in SPSS
NUR 617 Module 4 questions, answered
Where can I find a free NUR 617 Module 4 sample paper?
The NUR 617 Module 4 sample on this page is a complete Assignment 1 answer document with paired and independent t-tests, SPSS output tables, effect sizes and conceptual answers on illustrative data.
What is the difference between a dependent and an independent t-test?
A dependent test compares two scores from the same people, such as before and after; an independent test compares the means of two separate groups of people.
Which row of the independent samples t-test output do I read?
Check Levene's test first; if its significance is above .05, read "equal variances assumed," and if it is .05 or below, read "equal variances not assumed."
How do I calculate Cohen's d for a t-test?
Divide the mean difference by a standard deviation: the pooled standard deviation for two groups, or the standard deviation of the difference scores for paired data.
How is NUR 617 Assignment 1 submitted?
You type answers into the provided Word document, paste your SPSS output tables, and upload it as a .docx or .pdf in Canvas by the Week 4 due date.