| Course | PUBH 8033 Interpretation and Application of Public Health Data |
|---|---|
| Week | Week 2 |
| Paper type | Data provenance memo |
| Length | About 660 words, 4 pages |
| Format | Memo, APA 7 citations |
| School | Walden University |
| Program | PhD in Public Health |
| Updated | October 2026 |
Free sample paper for PUBH 8033 Week 2
Memorandum
To: Director of Aging Services, Larkin County
From: Doctoral Student and Program Analyst
Date: Month Day, Year
Re: Why our three older-driver numbers disagree, and which to use for what
The Three Numbers
Three figures about older drivers circulate in Larkin County, a composite county, and they appear to conflict. The county's traffic dashboard reports 9 deaths of drivers aged 70 and older over five years. The state crash file shows 412 police-reported crashes involving drivers 70 and older over the same period. And intake forms from our Safe Driving After 70 class show that 31% of enrollees reported a crash or near miss in the prior year. None of these is wrong. Each was produced by a different system for a different purpose, and each answers a different question.
Source 1: The Fatal Crash Census
The death count comes from the federal Fatality Analysis Reporting System, a census of crashes on public roads in which someone died within 30 days. National summaries built on it, such as the institute tabulations cited throughout this course (Insurance Institute for Highway Safety, 2026), are complete for deaths and detailed about vehicles and circumstances. The system was built to describe fatal crashes, not crash frequency. Because older people are more fragile, a crash that a younger driver survives may kill an older one, so deaths overstate older drivers' crash involvement relative to their injury risk (Li et al., 2003). Use it for: deaths and their circumstances. Do not use it for: how often older drivers crash.
Source 2: The State Crash File
The 412 crashes come from police crash reports, which officers complete when a crash meets the state's reporting threshold, usually an injury or property damage above a dollar amount. The file was built for enforcement, insurance and road engineering. It includes many nonfatal crashes but misses minor ones that were never reported, and its judgments about fault reflect an officer's assessment at the scene. Use it for: reportable crash involvement over time. Do not use it for: near misses or minor crashes, or rates without a denominator of drivers or miles.
Source 3: The Class Intake Form
The 31% comes from a self-administered form completed by people who chose to enroll in a safety class. It asks about any crash or near miss in the past year, as the participant remembers it. It was built to start a conversation in class, not to measure risk. People who enroll may differ from older drivers in general: attendees of one mature driver course had driving records unlike those of nonattendees even before the course (Nasvadi & Vavrik, 2007). Use it for: describing class participants. Do not use it for: estimating how common crashes are among all older drivers.
Table 1
What Each Source Was Built For
| Source | Built for | Captures | Misses | |
|---|---|---|---|
| Fatal crash census | Describing fatal crashes | Every death within 30 days | Nonfatal crashes | |
| State crash file | Enforcement, insurance, engineering | Reportable crashes | Minor and unreported crashes | |
| Class intake form | Starting class discussion | Self-reported crashes and near misses | Older drivers who do not enroll | |
Note. Larkin County figures are composite.
A Common Mistake to Avoid
One error appears often in local reports: dividing the number of police-reported crashes by the number of class participants to produce a "crash rate." The crash file counts crashes among all older drivers in the county; the class counts a small, self-selected group. The result describes neither population and should never be published.
Recommendation
Each number should travel with its source and its purpose. When the county says older drivers die at high rates, it should cite the fatal crash census and note fragility. When it describes crash involvement, it should use the state crash file with a stated denominator. When it describes class participants, it should use intake data and say they are self-selected. Mixing the three, for example dividing crash file counts by the number of class participants, produces numbers that mean nothing.
References
Insurance Institute for Highway Safety. (2026). Fatality facts 2024: Older people. https://www.iihs.org/research-areas/fatality-statistics/detail/older-people
Li, G., Braver, E. R., & Chen, L.-H. (2003). Fragility versus excessive crash involvement as determinants of high death rates per vehicle-mile of travel among older drivers. Accident Analysis & Prevention, 35(2), 227-235. https://doi.org/10.1016/S0001-4575(01)00107-5
Nasvadi, G. E., & Vavrik, J. (2007). Crash risk of older drivers after attending a mature driver education program. Accident Analysis & Prevention, 39(6), 1073-1079. https://doi.org/10.1016/j.aap.2007.02.005
What the PUBH 8033 Week 2 instructions ask for
Data provenance assignments ask students to explain where a set of figures came from and why sources that appear to describe the same thing disagree. Prompts usually require identifying each data system, its purpose, how cases enter it, what it captures and misses, and which questions it can legitimately answer. Many instructors want the answer framed for a decision maker, often as a memo. Strong submissions treat disagreement between sources as information about the systems rather than as error, give practical guidance on which source to use for which purpose, and flag misuses the reader is likely to encounter. Citation of the systems' documentation or of studies that rely on them strengthens the analysis. Some sections ask for a diagram of how each system collects its data.
How this PUBH 8033 Week 2 example is built
The memo lists the three numbers and states that none is wrong. Separate sections take each source in turn, the fatal crash census, the state crash file and the class intake form, explaining what each was built for, what it captures and what it misses, ending with a short "use it for" and "do not use it for" line. Evidence on fragility and on self-selection into driver courses supports two of the cautions. A table summarizes the three systems. A section names a common error, and the recommendation ties each number to its legitimate use. Each section closes with the same two-line format, so a director can scan for which source to use.
Where the marks sit in the PUBH 8033 Week 2 rubric
Graders look for accurate description of each data system, clear explanation of why the numbers differ and sound guidance on use. Accuracy covers inclusion rules, such as deaths within 30 days or reporting thresholds. Explanation earns most credit when it links differences to each system's purpose. Guidance should be specific enough for a nonspecialist reader to act on. Credit also goes to anticipating misuse. Memo form and correct citation are expected. Submissions that label one source "right" and the others "wrong" usually lose points on understanding. Memos that name a likely misuse, and explain why it fails, show the practical judgment this assignment rewards. Credit also goes to writers who keep each source's limitations short and concrete rather than general.
PUBH 8033 Week 2 help from the desk
Students often describe each source without explaining why they disagree. For every number, ask who records it, when, why and with what inclusion rule. Then ask which question the system was built to answer. Write a "use it for" line for each. Watch for denominators borrowed from a different system. Keep the memo short and practical. To have a provenance memo written for the conflicting figures in your setting, list the sources and what each reports. Look up each system's case definition or reporting rule, since that one sentence often explains most of the disagreement.
Get a PUBH 8033 Week 2 example written to your instructions
List the figures or data sources your section named, together with the Week 2 prompt and its rubric. A provenance memo tracing each source to its purpose, lag and blind spots is ready within 24-48h, with nothing to pay for the first. The county, its class and its numbers are fictional, and the systems behind your figures still need tracing on their own terms.
More PUBH 8033 papers and PhD in Public Health samples
- PUBH 8033 Week 1: Interpretation Post
- PUBH 8033 Week 3: Descriptive Reading
- PUBH 8033 Week 4: Estimate and Interval
- PUBH 8033 Week 5: Peer Critique
- PUBH 8033 Week 6: Confounding Analysis
- PUBH 8033 Week 7: Effect Size Argument
- PUBH 8033 Week 8: Missing Data Memo
- PUBH 8033 Week 9: Table and Figure Audit
- PUBH 8033 Week 10: Decision Brief
- PUBH 8033 Week 11: Applied Interpretation Paper
- PUBH 8048 Week 1: Orientation Post
- PUBH 8007 Week 2: Argument Analysis
- PHLT 9000 Week 2: Opening and Closing Read
- PHLT 8702 Week 2: Area Versus Personal Post
PUBH 8033 Week 2 questions, answered
Where can I find a free PUBH 8033 Week 2 sample paper?
The complete Week 2 memo is shown above, tracing three disagreeing older-driver numbers to their data systems.
What is data provenance?
The origin of a figure: which system produced it, how cases entered and what the system was built to do.
Why do crash death counts and police crash reports disagree?
One counts only deaths within 30 days of a crash, the other counts reportable crashes of all severities.
Can class intake forms estimate how common crashes are?
No; enrollees are self-selected and report from memory, so the forms describe participants only.
What is a common misuse of these sources?
Dividing countywide crash counts by the number of class participants, which produces a meaningless rate.