HLT-362V · Topic 5 · sample paper

HLT-362V Topic 5: sample paper, in real form

Reviewed by Imogen Stackhouse, MSN, RN Grand Canyon University True APA form Annotated

This page holds a complete HLT 362V Topic 5 example in true form: a quantitative write-up that tests whether a nurse-driven early mobility protocol shortened length of stay for 128 composite pneumonia admissions. It reports descriptive figures, names the test, and says in plain language what the result means for a care decision. Written for Applied Statistics for Health Care Professionals in the Grand Canyon University RN-to-BSN program.

1

Does a Nurse-Driven Early Mobility Protocol Shorten Length of Stay? An Independent-Samples t Test on 128 Medical-Surgical Admissions for Pneumonia

[Author Name]

College of Nursing and Health Care Professions, Grand Canyon University

HLT-362V Applied Statistics for Health Care Professionals

Topic 5 Assignment

[Instructor Name]

August 11, 2026

Composite data set written as a model document. No real hospital, employer or patient is described.

What this page is doingThe title asks the question the numbers answer, names the test and states the sample size, so a reader knows what was measured and on how many cases before turning a page. Statistics papers lose credit at exactly this point when they are titled after the course instead of after the analysis. The course line uses the classroom's own vocabulary rather than an invented deliverable name, and the closing line marks the data set as a composite.
2

The Practice Question and the Data Set

A 34-bed medical-surgical floor in a composite 240-bed community hospital introduced a nurse-driven early mobility protocol, under which nursing staff mobilize eligible patients within 12 hours of admission and three times daily afterward without waiting for a separate order. Bed rest costs older adults strength quickly, and mobilization during hospitalization has been associated with shorter stays and fewer complications (Kalisch et al., 2014). The question tested here is narrow enough to answer with data the hospital already keeps: among adults admitted with community-acquired pneumonia, is mean hospital length of stay shorter after the protocol than before it? Everything that follows exists to answer that one question.

The data set is a composite built for this paper and holds 128 adult admissions drawn from two 6-month periods on the same floor, 64 before implementation and 64 after. Records were included when the patient was 18 or older, carried a primary diagnosis of community-acquired pneumonia, and was admitted to the floor from the emergency department. Nine records were removed before analysis: 6 transfers to critical care, 2 discharges to hospice and 1 stay longer than 30 days, all of which measure something other than routine recovery. Removing them before the test rather than after is what keeps the comparison from being tuned to a result.

Two variables carry the analysis. The independent variable is group membership, a dichotomous nominal variable with the values before protocol and after protocol. The dependent variable is hospital length of stay in days, a continuous ratio-level variable with a true zero. A third variable, hours from admission to first documented ambulation, is also ratio level and is used for a correlation later in the paper. Level of measurement decides the test, and a ratio-level outcome compared across two independent groups points to an independent-samples t test rather than to a chi-square, which would require both variables to be categorical.

What this page is doingNotice the order: question, then sample, then variables with their levels of measurement, and only then a test. Naming length of stay as ratio level and group as nominal is what makes the choice of a t test defensible instead of habitual. The exclusions are declared before any analysis, which forecloses the suspicion that records were dropped until the result improved. Graders reading for data literacy look for that sequence before they look at any output.
3

Descriptive Statistics and Test Selection

Before the protocol, mean length of stay was 5.8 days (SD = 1.9, n = 64), with a median of 5.6 days and a range of 2 to 11 days. After the protocol, mean length of stay was 4.9 days (SD = 1.7, n = 64), with a median of 4.8 days and a range of 2 to 10 days. Mean hours from admission to first documented ambulation fell from 31.4 (SD = 12.6) to 19.8 (SD = 9.7). The groups were similar on the demographics available: mean age 68.2 years (SD = 14.1) before and 69.5 years (SD = 13.4) after, with men making up 53 percent and 55 percent of each group. The standard deviations matter as much as the means, because a gap of 0.9 days between groups that each spread by nearly 2 days is not something an eye can see on a report.

Four conditions justify the test that follows. Observations are independent, since no patient appears in both groups and each admission is counted once. The dependent variable is continuous. Both distributions are close enough to normal to proceed, with skewness of 0.42 and 0.31, values inside the plus or minus 1 range usually treated as acceptable, and Shapiro-Wilk results of p = .21 and p = .34 that give no reason to reject normality. Levene's test for equality of variances returned F(1, 126) = 0.62, p = .43, so equal variances are assumed and the pooled-variance form of the test is used (Field, 2018).

The hypotheses are stated before the test is run rather than after the output appears. The null hypothesis is that mean length of stay is the same in the two groups, which is to say that the difference between the population means is zero. The alternative hypothesis is that the two means differ. A two-tailed test is used, because a change in practice could plausibly lengthen a stay as well as shorten it, and alpha is set at .05 in advance. A paired test was rejected because the groups contain different patients, and analysis of variance was unnecessary with only two groups to compare (Polit & Beck, 2021).

What this page is doingMeans never travel alone here. Each mean carries its standard deviation and its sample size, a median gives the reader a check on skew, and the assumption paragraph tests what the t test needs rather than assuming it. Levene's result is what licenses the pooled-variance form, so it earns its place in the paper. Stating alpha and the hypotheses before the result appears is a small move that separates a test from a story told backward.
4

Results

Mean length of stay was 0.9 days shorter after the protocol than before it, and the independent-samples t test found that difference statistically significant, t(126) = 2.82, p = .005, 95 percent CI [0.27, 1.53]. Because the confidence interval [0.27, 1.53] does not contain zero, the interval and the p value tell the same story: a true difference of no days at all is not compatible with these data. Cohen's d was 0.50, a medium effect by conventional benchmarks, which answers a question the p value cannot answer at all, namely how large the difference is rather than whether it exists. The null hypothesis is rejected at the .05 level.

A second analysis tested whether the timing of mobilization tracked the outcome across all 128 admissions, without regard to group. The Pearson correlation between hours to first documented ambulation and length of stay was r = .48, n = 128, p < .001, a moderate positive relationship in which later first ambulation went with longer stays. Squaring the coefficient gives r squared of .23, so roughly 23 percent of the variation in length of stay is shared with the timing of first ambulation and 77 percent is not. Correlation of this kind cannot establish direction, and sicker patients both mobilize later and stay longer, which is a competing explanation the data cannot rule out.

What this page is doingThe result is reported in the form APA expects: test statistic with degrees of freedom, exact p value, confidence interval and effect size in one line. The p value answers whether, the effect size answers how much, and the interval answers how precisely, which is why all three appear together. The correlation is reported with its limits attached in the same paragraph, since a coefficient without that caution invites a causal reading it cannot support.
5

Interpretation for the Care Decision

In plain language, a p value of .005 says that if the protocol made no difference at all, a gap this large or larger would appear in about 5 of every 1,000 samples like this one. It does not say there is a 99.5 percent chance the protocol works, and by itself it says nothing about how much good the protocol does. The confidence interval carries that information: the honest sentence for a manager is that the true average saving is probably somewhere between about 0.3 and 1.5 days, with 0.9 days as the single best estimate from these data (Grove & Gray, 2019).

Whether 0.9 days is worth acting on is a clinical and operational question rather than a statistical one. On a floor that admits roughly 260 patients with pneumonia in a year, an average saving of 0.9 days per admission is about 234 bed days, which is capacity the hospital does not have to build. For the patient the argument is stronger than the arithmetic: each additional hospital day carries exposure to hospital-acquired infection, disrupted sleep and further loss of strength in adults who are already older than 68 on average. A medium effect size supports treating the difference as real rather than as noise worth ignoring.

The design limits how far the claim can travel. This is a before-and-after comparison of two independent groups, not a randomized trial, so anything else that changed between the two periods travels with the protocol: seasonal severity, staffing, a new discharge coordinator, or a shift in who is admitted at all. The data set carries no severity score, so the groups may not have been equally sick even though age and sex looked similar. The defensible recommendation is to continue the protocol, to add a severity measure to the data collected, and to repeat the same test after another 6 months, rather than to treat one significant result as the end of the question.

What this page is doingThis is the sheet that separates a statistics paper from a spreadsheet. The p value is translated into a sentence a manager could repeat correctly, the common misreading is named and refused, and the difference is converted into bed days and into patient consequences. The limits paragraph then protects the whole paper: a before-and-after comparison cannot carry a causal claim, and saying so earns more credit than overstating what one significant result proved.
6

References

American Psychological Association. (2020). Publication manual of the American Psychological Association (7th ed.).

Centers for Disease Control and Prevention. (2024). Pneumonia. U.S. Department of Health and Human Services. https://www.cdc.gov/pneumonia/

Field, A. (2018). Discovering statistics using IBM SPSS statistics (5th ed.). Sage.

Grove, S. K., & Gray, J. R. (2019). Understanding nursing research: Building an evidence-based practice (7th ed.). Elsevier.

Kalisch, B. J., Lee, S., & Dabney, B. W. (2014). Outcomes of inpatient mobilization: A literature review. Journal of Clinical Nursing, 23(11-12), 1486-1501.

Polit, D. F., & Beck, C. T. (2021). Nursing research: Generating and assessing evidence for nursing practice (11th ed.). Wolters Kluwer.

How this HLT 362V Topic 5 example is structured

In many sections this topic asks you to apply a statistical test to health care data and explain the result, not to write an essay about statistics; your classroom's instructions and rubric decide the exact form, including whether the work is submitted on a spreadsheet, so read the assignment page before you use this HLT 362V Topic 5 example as a shape. The paper is ordered the way a quantitative write-up is read. The practice question and the data set come first, with the variables and their levels of measurement named. Descriptive figures and the reasons for choosing the test come next, because a test defended after the fact is not defended. Results are reported in APA form, with the effect size and the confidence interval beside the p value. Interpretation comes last, written for the person who has to make the care decision. The data set is a composite.

HLT-362V Topic 5 questions, answered

What does HLT 362V Topic 5 usually ask for?

In many sections this topic asks you to run and interpret a test on health care data, often on a spreadsheet with a short written interpretation attached. Your classroom's instructions and rubric decide the exact form, including which test and which data set, so read the assignment page first and treat an example like this one as a shape rather than as the requirement.

How do I choose the right statistical test?

Three questions settle most choices. What is the level of measurement of the outcome, how many groups are being compared, and are the groups independent or paired? A ratio-level outcome across two independent groups gives an independent-samples t test, three or more groups give analysis of variance, and two categorical variables give a chi-square test of independence.

What belongs in the interpretation section of a statistics paper?

Say what the p value means in plain terms, then say how big the difference is using the effect size and the confidence interval, then say what a care team should do about it. Name the limits of the design in the same breath. An interpretation that only repeats that the result was significant leaves most of the available credit on the table.

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 Grand Canyon 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.

Request this one custom, free All HLT-362V topic samples All courses