| Course | DNP 679 Biostatistics Principles of Statistical Inference |
|---|---|
| Module | Module 4 |
| Paper type | Chi-square test write-up |
| Length | About 823 words, 5 pages |
| Format | APA 7 student paper |
| School | Arizona State University |
| Program | Doctor of Nursing Practice |
| Updated | October 2026 |
Free sample paper for DNP 679 Module 4
Text, Portal or Nothing: A Chi-Square Test of Flu Vaccination by Reminder Type and a Fisher's Exact Test for the Small Subgroup
Student Name
Edson College of Nursing and Health Innovation, Arizona State University
DNP 679: Biostatistics: Principles of Statistical Inference
Instructor Name
Month Day, Year
Text, Portal or Nothing: A Chi-Square Test of Flu Vaccination by Reminder Type and a Fisher's Exact Test for the Small Subgroup
Question and Hypotheses
Reminders are a common way to raise vaccination rates in primary care, and a Cochrane review concluded that reminding and recalling patients raises immunization coverage across ages and settings (Jacobson Vann et al., 2018). In this hypothetical dataset, a clinic randomly assigned 300 adults due for influenza vaccination to one of three conditions in early fall: a text message reminder (n = 100), a message through the patient portal (n = 100) or no reminder (n = 100). The outcome was whether each patient was vaccinated by December 31.
Both variables are nominal: reminder type has three categories and vaccination status two. The chi-square test of independence is the appropriate test.
H0: Vaccination status is independent of reminder type.
H1: Vaccination status is associated with reminder type (alpha = .05).
Data Setup
In the hypothetical dataset each of the 300 patients is one row, with reminder type coded 1 (text), 2 (portal) or 3 (none) and vaccination coded 1 (yes) or 0 (no), both labeled as categorical in Intellectus. The software cross-tabulates the two variables, so no hand counting is needed, but the table was checked against the group sizes to confirm that every patient was counted once and none was missing an outcome.
Assumptions
The chi-square test requires independent observations, each person counted once, and adequate expected frequencies, conventionally at least 5 in every cell (Polit & Beck, 2021). Each patient appears in one cell only. Because the three groups are equal in size and the overall vaccination rate was 46.7%, every expected count was 46.7 for vaccinated and 53.3 for unvaccinated, well above 5.
Results
Vaccination rates were 58.0% after a text reminder, 47.0% after a portal message and 35.0% with no reminder. The association between reminder type and vaccination was statistically significant, chi-square(2, N = 300) = 10.63, p = .005, with a small to moderate strength of association, Cramer's V = .19. Adjusted residuals beyond plus or minus 1.96 identify the cells that depart from independence: more patients than expected were vaccinated in the text group (+2.78) and fewer in the no-reminder group (-2.86), while the portal group was close to expected (+0.08). Compared with no reminder, the odds of vaccination after a text reminder were 2.56 times higher (58 x 65 / 42 x 35). We reject the null hypothesis.
| Reminder type | Vaccinated, n (%) | Not vaccinated, n (%) | Total |
|---|---|---|---|
| Text message | 58 (58.0) | 42 (42.0) | 100 |
| Patient portal | 47 (47.0) | 53 (53.0) | 100 |
| No reminder | 35 (35.0) | 65 (65.0) | 100 |
| Total | 140 (46.7) | 160 (53.3) | 300 |
| Statistic | Value | ||
| Pearson chi-square | 10.63 | ||
| df | 2 | ||
| p | .005 | ||
| Cramer's V | .19 | ||
| Adjusted residual, text and vaccinated | +2.78 | ||
| Adjusted residual, portal and vaccinated | +0.08 | ||
| Adjusted residual, no reminder and vaccinated | -2.86 |
Fisher's Exact Test for a Small Subgroup
The clinic also wanted to know whether reminders helped the 14 pregnant patients in the text and no-reminder groups. Of 7 pregnant patients who received a text, 6 were vaccinated; of 7 who received no reminder, 2 were vaccinated.
In this 2 x 2 table every expected count is below 5 (4 vaccinated and 3 unvaccinated per row), so the chi-square approximation is unreliable. Fisher's exact test, which calculates the exact probability of the observed table given the margins, was used instead: p = .103 (two-sided). The rule of thumb behind this switch, an expected count below 5 in a 2 x 2 table, is the standard one for choosing between the two tests (Kim, 2017). Despite a large difference in percentages (86% versus 29%), the subgroup is too small to rule out chance.
| Pregnant subgroup | Vaccinated | Not vaccinated | Total |
|---|---|---|---|
| Text message | 6 | 1 | 7 |
| No reminder | 2 | 5 | 7 |
Interpretation
In this hypothetical trial, text reminders were associated with a 23 percentage point higher vaccination rate than no reminder, and random assignment supports reading this as an effect of the reminder. Portal messages fell between the two and did not depart from what independence would predict, possibly because fewer patients read portal messages. The pregnant subgroup points in the same direction, but with 14 patients the result is inconclusive, and subgroup findings should be treated as hypotheses for a larger study. Practically, the clinic has reason to prefer text reminders while checking that patients without mobile phones are not left out. A Cramer's V of .19 also cautions against overstating the result: reminder type explains only part of who gets vaccinated, and access, trust and past experience with the vaccine matter as well. The odds ratio of 2.56 describes a meaningful gain at the population level, but nearly half of the patients who received a text still were not vaccinated by the end of December, which suggests that a second contact, such as a follow-up text or a call from a nurse, would be worth testing next.
References
Jacobson Vann, J. C., Jacobson, R. M., Coyne-Beasley, T., Asafu-Adjei, J. K., & Szilagyi, P. G. (2018). Patient reminder and recall interventions to improve immunization rates. Cochrane Database of Systematic Reviews, 2018(1), Article CD003941. https://doi.org/10.1002/14651858.CD003941.pub3
Kim, H.-Y. (2017). Statistical notes for clinical researchers: Chi-squared test and Fisher's exact test. Restorative Dentistry & Endodontics, 42(2), 152-155. https://doi.org/10.5395/rde.2017.42.2.152
Polit, D. F., & Beck, C. T. (2021). Nursing research: Generating and assessing evidence for nursing practice (11th ed.). Wolters Kluwer.
DNP 679 Module 4 instructions, in plain terms
Week 8 of DNP 679 covers the chi-square test and Fisher's exact test, and its written assignment asks you to conduct a chi-square test in Intellectus and submit a write-up. The syllabus lists it at 10 points, normally due at the end of Week 8, with the posted schedule moving the deadline a few days later for fall break. As with the other written assignments, the dataset is hypothetical and the detailed prompt is in Canvas. A complete answer names both variables and their levels, states hypotheses in terms of independence, checks expected cell counts, reports the chi-square statistic with degrees of freedom, sample size and p value, gives a measure of association and says which cells drive the result. If any expected count falls below 5, the week's lecture points you to Fisher's exact test.
How the DNP 679 Module 4 example is put together
The sample starts with a published reason to expect reminders to work and then describes the hypothetical trial. Both variables are classified as nominal before the test is chosen, and the hypotheses use the word independence. The assumptions paragraph shows the expected counts rather than just asserting they are adequate. Results come as a contingency table with row percentages and a statistics table that includes Cramer's V and adjusted residuals for the vaccinated column. The results paragraph gives the APA form of the chi-square, then uses the residuals and an odds ratio to say where the difference lies. A separate section applies Fisher's exact test to a small subgroup and explains why. The interpretation draws a practice recommendation and a caution.
Where the marks sit in the DNP 679 Module 4 rubric
Points for the Week 8 write-up are set by the Canvas rubric; the syllabus values it at 10. Chi-square assignments usually reward correct identification of the test from the variables' levels, a stated check of expected counts, accurate reporting in the form chi-square(df, N) = value, p, a measure of effect such as Cramer's V or phi, and an interpretation that explains the direction of the association. Frequent deductions come from column percentages that answer the wrong question, a missing effect size, a chi-square applied to a table with tiny expected counts and conclusions about which group differs without residuals or follow-up comparisons. Graded work is returned within a week. Late work loses 3% a day and earns zero after five days.
DNP 679 Module 4 help from the desk
The most common confusion is between observed and expected counts; the assumption is about expected counts, so report them. Another is percentaging the table the wrong way. If the question is whether reminder type affects vaccination, compute the percentage vaccinated within each reminder group. Report the degrees of freedom as (rows minus 1) times (columns minus 1). A significant chi-square with three or more groups does not say which groups differ; use adjusted residuals or pairwise tests and say which you used. Do not apply a continuity correction or Fisher's test without explaining why. If you send the desk your Intellectus output and the prompt, it can help you check each value before you submit.
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 DNP 679 and Doctor of Nursing Practice sample papers
- DNP 679 Module 1: Post Immersion 1 Written Assignment: Descriptive Statistics on Insomnia Severity Data
- DNP 679 Module 2: Post Immersion 2 Written Assignment: Independent t-Test and Mann-Whitney U Test
- DNP 679 Module 3: Paired t-Test Written Assignment
- DNP 679 Module 5: One-Way ANOVA Written Assignment
- DNP 679 Module 6: Practice Paper Critique: Statistics in a Randomized Trial of Transitional Care
- DNP 679 Module 7: Final Paper Critique: Statistics in an Observational Study of Nurse Staffing and Surgical Mortality
- DNP 645 Module 6: Evidence-Based Practice Presentation: When the Preceptor Did Not Follow the Guideline (Acute Otitis Media)
- DNP 716 Module 4: Professional Role Analysis
- DNP 673 Module 3: Using CBT With a Client Discussion
- DNP 711 Module 6: Blog 5: Interview With a Policymaker
DNP 679 Module 4 questions, answered
Where can I find a free DNP 679 Module 4 sample paper?
This page contains a full DNP 679 Module 4 sample: the chi-square written assignment on vaccination by reminder type, with expected counts, Cramer's V, adjusted residuals and a Fisher's exact test.
When should I use Fisher's exact test instead of chi-square?
Use Fisher's exact test when expected counts are small, usually when any expected cell count in a 2 x 2 table is below 5, because the chi-square approximation becomes unreliable.
How do I report a chi-square test in APA style?
Give the degrees of freedom, sample size, statistic and p value, for example chi-square(2, N = 300) = 10.63, p = .005, then add Cramer's V to show strength.
What does Cramer's V measure?
Cramer's V measures the strength of association between two nominal variables on a scale from 0 to 1; for 2 x 2 tables it equals the phi coefficient.
How do I find which groups differ after a significant chi-square?
Examine adjusted standardized residuals, where values beyond plus or minus 1.96 mark cells that differ from expected, or run pairwise comparisons with an adjusted alpha.