| Course | HI560 Health Care Data Analytics |
|---|---|
| Unit | Unit 7 |
| Paper type | Visualization set |
| Length | About 970 words, 6 pages double-spaced |
| Format | APA 7 student paper |
| School | Purdue University Global |
| Program | MS in Health Informatics |
| Updated | October 2026 |
Free sample paper for HI560 Unit 7
Four Displays, Four Questions: A Unit 7 Visualization Set for Comparing Incomplete MRI Rates at Two Sites
[Student Name]
Purdue University Global
HI560: Health Care Data Analytics
Unit 7 Visualization Set
[Instructor Name]
[Date]
Thistlewood Health, its sites and every plotted value are composite; the sources cited are real.
Design Rules for the Set
Each display answers one question the report asks, in the order the argument needs: is there a gap, is it stable over time, does it appear in every kind of exam, and how much of it survives adjustment. Every figure carries a headline written as a finding, a subtitle naming the population and period, and a source line giving the file version, analytic file v3 of January 30, 2026. Rates are encoded as position along a common axis, because readers judge position on a shared scale more accurately than length, angle or area (Cleveland & McGill, 1984). Intervals are drawn wherever a rate is shown, and counts are printed wherever a denominator is small.
Figure 1: Crude and Standardized Rates
Headline: Fennimore ends more MRIs incomplete than the hospital, but adjustment for exam group and age shrinks the gap by a third.
Subtitle: Adult outpatient MRI exams, January 2024 to December 2025, percent ending incomplete with 95 percent intervals.
Design: a dot plot with two rows, crude and standardized, and two dots per row, one per site, each with a horizontal interval line. Crude rates are 3.64 percent for the hospital and 4.69 for Fennimore; standardized rates are 3.79 and 4.48. The axis runs from 0 to 6 percent.
Rationale: the axis starts at zero because the rates are compared as magnitudes, and a truncated axis would make a one-point gap look like a doubling. Two hues are used, a dark blue for the hospital and an orange for Fennimore, a pair that remains distinguishable for readers with the common forms of color vision deficiency, and the sites are also labeled directly beside the dots so the figure works in grayscale.
Figure 2: Quarterly Run Chart
Headline: The gap has held in seven of eight quarters, with no trend at either site.
Subtitle: Percent of exams ending incomplete by quarter, with the number of exams printed under each point.
Design: two lines across eight quarters, each point labeled with its denominator. Hospital quarters rest on about 1,230 exams and Fennimore quarters on about 1,000, so each quarterly rate is uncertain by about plus or minus 1.3 points, which the chart notes in its subtitle.
Rationale: printing the counts under each point tells readers how much a single quarter can move by chance, and it discourages anyone from reacting to one quarter's rise. A median line for each site makes it easy to see whether points cluster on one side.
A single quarter at Fennimore rests on about a thousand exams, so a rise of one point in one quarter is the sort of change chance alone produces.
Figure 3: The Nine-Cell Panel
Headline: Fennimore's rate is higher in all nine exam group and age cells, but by less than the crude gap.
Design: a three-by-three grid of small panels, exam group across and age band down, each showing the two sites' rates as dots with intervals on identical axes from 0 to 8 percent. Cells with fewer than ten incomplete exams at either site are outlined with a dashed border.
Rationale: identical scales let the eye compare panels without reading numbers, and the dashed borders mark where intervals are wide. The panel shows at a glance that head-first neuro exams carry the highest rates at both sites, as a large cohort study of claustrophobic reactions would predict (Dewey et al., 2007).
Figure 4: The Bridge
Headline: Of the 1.05-point crude excess, about a third reflects exam group and age and another third reflects slot length.
Design: a bridge chart beginning with a bar at 1.05 points, a step down of 0.35 for exam group and age, a step down of 0.32 for slot length, and an ending bar at 0.38 points. The interval for the ending figure, minus 0.24 to 1.00, is shown as a bracket beside it.
Rationale: the bridge makes each adjustment's contribution visible in one picture, which is the argument of Unit 6. The final bracket crossing zero is labeled in words, so no reader mistakes the ending bar for a firm difference.
Appendix: Two Rejected Designs
1. A pie chart of incompletion reasons by site. Rejected because the reason field is unreliable, as Unit 4 showed, and because comparing slices across two pies asks readers to judge angles, which they do poorly.
2. A clustered bar chart of crude rates with the axis starting at 3 percent. Rejected because the truncated axis made Fennimore's bar look nearly twice the hospital's when the rates differ by about a quarter.
Alt Text
Figure 1: Dot plot of percent of MRI exams ending incomplete. Crude: hospital 3.6, Fennimore 4.7. Standardized for exam group and age: hospital 3.8, Fennimore 4.5. Intervals do not overlap.
Figure 2: Two lines over eight quarters. Fennimore is above the hospital in seven quarters, both near flat, each point with about one thousand exams.
Figure 3: Nine small panels by exam group and age. Fennimore is higher in every panel; head-first neuro exams have the highest rates.
Figure 4: Bridge from a crude gap of 1.05 points to 0.70 after exam group and age, then 0.38 after slot length, with the final interval crossing zero.
Software and Reproducibility
All four figures were produced from the versioned analytic file with a script stored alongside it, so any figure can be redrawn after a data update. Practical guidance on presenting quantitative comparisons, such as removing gridlines that carry no information and labeling data directly, informed the final styling (Few, 2012).
References
Cleveland, W. S., & McGill, R. (1984). Graphical perception: Theory, experimentation, and application to the development of graphical methods. Journal of the American Statistical Association, 79(387), 531-554. https://doi.org/10.1080/01621459.1984.10478080
Dewey, M., Schink, T., & Dewey, C. F. (2007). Claustrophobia during magnetic resonance imaging: Cohort study in over 55,000 patients. Journal of Magnetic Resonance Imaging, 26(5), 1322-1327. https://doi.org/10.1002/jmri.21147
Few, S. (2012). Show me the numbers: Designing tables and graphs to enlighten (2nd ed.). Analytics Press.
HI560 Unit 7 instructions, in plain terms
The seventh unit commonly asks you to create a set of visualizations that communicate your analysis and to justify your design choices. Expect three to five figures, each with a headline, plus rationale and accessibility notes. Order the displays to follow the argument, one question per figure. Encode rates as positions on a common axis where you can, show uncertainty wherever a rate appears, and print counts when denominators are small. Explain axis choices, especially whether the axis starts at zero. Choose colors that remain distinguishable for readers with color vision deficiency and work in grayscale. Many instructors appreciate rejected designs with reasons, and alt text for each figure is increasingly expected.
Inside the HI560 Unit 7 example
A design rules section sets the order of questions and the encoding principles, citing Cleveland and McGill. Figure 1 is a dot plot of crude and standardized rates with intervals on a zero-based axis. Figure 2 tracks eight quarters with denominators printed, and the highlighted sentence explains why a one-point quarterly rise is within chance. Figure 3 is a three-by-three grid on identical scales with dashed borders for small cells, linked to the head-first finding from a large cohort study. Figure 4 is a bridge from 1.05 to 0.38 points with the final interval labeled. An appendix rejects a pie chart of reasons and a truncated bar chart, alt text is given for each figure, and a closing note covers reproducibility.
HI560 Unit 7 rubric: what earns full points
Visualization sets are usually scored on clarity of each display, appropriateness of encoding, honesty of axes and uncertainty, accessibility and the written rationale. Encoding and honesty often carry the most points: rates shown by position, intervals included, axes that do not exaggerate. Each display earns credit when its headline states a finding the figure actually supports. Accessibility is increasingly graded, including color choices and alt text. Rationale paragraphs score best when each one says what design was weighed and why it lost. Graders also check that every headline matches what its figure actually shows. Consistent styling and APA citations complete the rubric. Sets that use decorative charts, truncated bars or unexplained colors tend to lose points.
HI560 Unit 7 help from the desk
Visualization sets are frequently returned for headlines that only name the chart, such as rates by site, instead of stating a finding. Another common problem is leaving out uncertainty. Some students truncate axes to make small differences look large. Pie charts and three-dimensional charts make comparisons harder. Colors that depend on red and green exclude many readers. Missing alt text costs points in many sections, and so does a figure whose headline claims more than the plotted values support. If your analysis has a different structure, perhaps a trend over time or several groups, share your results and the prompt, and a visualization set can be designed around your argument.
Get an HI560 Unit 7 example written to your instructions
Tell us which comparison your Unit 7 prompt wants shown and attach the data or earlier results, along with the rubric and any required software. Within 24-48h, free as a first request, a visualization set comes back with a headline on every display, intervals wherever rates appear, and a rationale paragraph for each choice. The paper above is an original model document written by our desk, not a submitted student paper and not an official Purdue University Global document.
More HI560 papers and MS in Health Informatics samples
- HI560 Unit 1: Discussion Board Post
- HI560 Unit 2: Data Set Description
- HI560 Unit 3: Descriptive Statistics Report
- HI560 Unit 4: Data Quality Assessment
- HI560 Unit 5: Hypothesis Test Writeup
- HI560 Unit 6: Population Comparison
- HI560 Unit 8: Seminar Reflection
- HI560 Unit 9: Executive Summary
- HI560 Unit 10: Analytics Project Report
- HI555 Unit 7: Accounts Receivable Report
- HI550 Unit 7: Team Development Proposal
- HI545 Unit 7: Compliance Training Outline
- HI540 Unit 7: Risk Register
HI560 Unit 7 questions, answered
Should a rate chart always start the axis at zero?
Bar charts should, because bar length encodes the value. Dot plots and line charts can start elsewhere if the axis is clearly labeled and the purpose is to show change or detail, but when rates are compared as magnitudes, as in the example, starting at zero keeps the gap honest. State the choice in the rationale either way.
How many displays belong in a visualization set?
As many as the argument has steps, which is often three to five. Each should answer a different question. Repeating the same comparison in several chart types adds pages without adding evidence. The example uses four because the report asks four questions: is there a gap, is it stable, is it everywhere, and how much survives adjustment.
Which software do HI560 visualizations require?
Whatever the section specifies; many accept Excel, Tableau, Power BI, R or Python. Graders usually care more about the choices than the tool: the right encoding, honest axes, visible uncertainty and a stated finding. Include the file or script if the prompt asks for reproducibility, and export at a resolution where every label stays readable.
Why print counts under each point of a run chart?
Counts show how much a single period can move by chance, which keeps readers from reacting to one quarter's rise when each point rests on about a thousand exams.
Where can I find a free HI560 Unit 7 sample paper?
The whole Unit 7 set is on this page, with four headlined displays, design rationale, two rejected charts and alt text.