| Course | HS345 Biostatistics |
|---|---|
| Unit | Unit 7 |
| Paper type | Seminar reflection |
| Length | About 800 words, 5 pages double-spaced |
| Format | APA 7 student paper |
| School | Purdue University Global |
| Program | BS in Health Science |
| Updated | October 2026 |
Free sample paper for HS345 Unit 7
I Voted for the Wrong P Value: A Unit 7 Seminar Reflection on Two Trials of One Weight Program
[Student Name]
Purdue University Global
HS345: Biostatistics
Unit 7 Seminar Reflection
[Instructor Name]
[Date]
The two trials and the funding vote are composite; the statement on p-values and the methods papers cited are real.
The Slide and My Vote
The instructor opened with one slide and a role play, and I remember feeling confident, because this was the kind of question I thought the course had trained me to answer quickly: we were a health plan's benefits committee deciding whether to cover a weight program. Study A enrolled [4,200] adults and found that participants lost 0.4 kilograms more than controls at twelve months, p equals 0.01. Study B, a pilot with [48] adults, found a difference of 2.9 kilograms, p equals 0.09. We voted by show of hands. I voted to expand coverage because of Study A and to set Study B aside because it was "not significant." Most of the room voted with me. Two classmates abstained, and when the instructor asked why, one said she did not trust a study with only forty-eight people and the other said she wanted to know what the program cost. At the time I thought the second reason was beside the point, a question for the finance office rather than for us. By the end of the hour it turned out to be the most important question anyone had asked.
What the Intervals Added
The instructor then showed the confidence intervals the slide had left out. Study A: 0.1 to 0.7 kilograms. Study B: minus 0.5 to 6.3 kilograms.
The room went quiet, then argued. Study A's interval says the true benefit is very likely small, at most about two thirds of a kilogram, an amount few people would notice and that would not justify the program's cost. Study B's interval runs from a slight harm to a large benefit; it is compatible with almost anything.
The p value of 0.01 told me only that the effect was probably not zero, and the interval told me it was probably too small to matter, which is the opposite of the reason I had voted yes.
What Changed
I had been treating the p value as a measure of how important a result was. The statistical profession's own guidance on p-values warns against exactly that: the size of a benefit and its practical worth lie outside what any p value reports, and passing 0.05 should not by itself settle any decision (Wasserstein & Lazar, 2016). With [4,200] people, even a trivial difference becomes statistically significant. With [48], even a large difference may not.
Study B was also not evidence that the program fails. A nonsignificant result from a small study is absence of evidence, not evidence of absence (Altman & Bland, 1995). The right response to Study B was not to set it aside but to ask for a larger trial, since its interval included effects big enough to matter.
The second half of the seminar went through a list of common misreadings of p values, including the belief that p gives the chance that there is no real effect (Greenland et al., 2016). I recognized three of them in my own notes from the first half of the course.
What I Do Now
I now read the effect size and its interval before the p value, and I ask the committee's real question of the interval: is every value in it large enough, or small enough, to change the decision? For Study A, every value is too small to justify coverage at the program's price. For Study B, the interval is too wide to decide anything, which is itself a finding: we need more data. I have also started writing the committee's threshold down before I look at any results, for example the smallest weight loss that would justify the program's cost, so that the interval is judged against a number I chose in advance rather than one I find convenient afterward.
Had I been asked to vote again at the end of the hour, I would have voted no on expanding coverage now and yes on funding a properly sized trial of the version of the program used in Study B, which appears to differ from Study A's in session frequency.
An Open Question
What should a committee do when a large trial gives a small, precise benefit and the program is cheap? Is half a kilogram worth it at ten dollars a person? I think the answer depends on what else the money could buy, which the statistics alone cannot tell us, and I would like to hear how classmates would set that threshold.
References
Altman, D. G., & Bland, J. M. (1995). Statistics notes: Absence of evidence is not evidence of absence. BMJ, 311(7003), 485. https://doi.org/10.1136/bmj.311.7003.485
Greenland, S., Senn, S. J., Rothman, K. J., Carlin, J. B., Poole, C., Goodman, S. N., & Altman, D. G. (2016). Statistical tests, P values, confidence intervals, and power: A guide to misinterpretations. European Journal of Epidemiology, 31(4), 337-350. https://doi.org/10.1007/s10654-016-0149-3
Wasserstein, R. L., & Lazar, N. A. (2016). The ASA statement on p-values: Context, process, and purpose. The American Statistician, 70(2), 129-133. https://doi.org/10.1080/00031305.2016.1154108
The Purdue Global HS345 Unit 7 instructions
Unit 7 has students look back on a seminar about inference, usually built around a scenario where a p value and an effect size point different ways. Plan on about two pages written as I and me. Marks follow an honest account of your first judgment, the specific information or argument that changed it, sources that explain why, and a new habit you will use. Many sections ask for a fair hearing of a classmate's view that you initially dismissed. Quote or paraphrase the numbers discussed so a reader can follow. Cite guidance on p-values and at least one source on interpreting nonsignificant results.
How this HS345 Unit 7 example is built
The reflection opens with the slide and the role play, the two studies' sizes, effects and p values, the writer's vote and the two classmates who abstained. A section on what the intervals added gives both confidence intervals and the room's reaction; the highlighted sentence marks where the writer's reasoning reversed. The section on what changed cites the profession's guidance on p-values, explains why sample size drives significance, explains that Study B's wide interval leaves the question open rather than answering no, and notes misreadings the writer found in earlier notes. A section on practice describes reading the interval first against a threshold set in advance, and an open question weighs a small, cheap benefit.
Where the points sit in the HS345 Unit 7 rubric
Reflections on inference are marked chiefly on depth of understanding and on the honesty and specificity of the change described. Understanding earns credit when the writer explains why the p value misled, using the effect sizes and intervals rather than slogans. Specificity rewards concrete numbers and moments from the session. Sources should support the key claims about p values and nonsignificant results. A new habit that the writer shows in use, such as setting a decision threshold before looking at results, lifts the reflection. First-person clarity, organization and correct citations make up the writing portion. Bringing the abstaining classmate's cost question back at the end shows that the reflection weighed another view fairly.
HS345 Unit 7 help: mistakes that cost points
A frequent weakness is a reflection that condemns p values in general without explaining what went wrong in the example. Another is treating Study B's nonsignificant result as proof that the program fails. Some students describe the intervals but never connect them to the decision being made. Others leave out the cost question, which is often what turns a statistical result into a policy answer. Copying the guidance's wording instead of applying it reads as filler. If your seminar used other studies, share the effect sizes, intervals and p values discussed, so the reflection can center on the point where the numbers turned your vote. A closing question that only asks whether p values are bad leaves classmates little to answer.
Get an HS345 Unit 7 example written to your instructions
The result at the center of a reflection should be the one your own HS345 Unit 7 group argued over. Pass along what the session examined, any figures shown, the questions set for students unable to join live, and the reflection rubric. First custom samples are free, delivered inside 24-48 hours, with each statistical claim worded as a statistician would accept it. 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 HS345 papers and BS in Health Science samples
- HS345 Unit 1: Average Versus Distribution Post
- HS345 Unit 2: Descriptive Statistics Exercise
- HS345 Unit 3: Data Display Critique
- HS345 Unit 4: Probability Problem Set
- HS345 Unit 5: Sampling Distribution Exercise
- HS345 Unit 6: Confidence Interval Problem
- HS345 Unit 8: Hypothesis Test Writeup
- HS345 Unit 9: Regression Exercise
- HS345 Unit 10: Statistical Analysis Report
- HS340 Unit 7: Seminar Reflection on an Outbreak
- HS315 Unit 7: Seminar Reflection
- HS450 Unit 7: Seminar Reflection
- HS305 Unit 7: Seminar Reflection on Study Methods
HS345 Unit 7 questions, answered
Why does Study A's p value look stronger if its effect is so small?
Because a p value depends on both the size of an effect and the size of the sample. With 4,200 participants, even a 0.4-kilogram difference is measured precisely enough to be distinguished from zero. The p value reports that distinction, not whether the difference matters. The interval shows both at once, which is why the reflection leads with it.
Is it wrong to call a result statistically significant?
Not wrong, but incomplete, and some statisticians now argue against using the phrase at all. The reflection keeps the term when describing the slide and then reports the estimate and interval, which carry more information. Many instructors accept either style, provided the size of the effect appears alongside any statement about significance.
What if my seminar covered a different example?
The reflection's pattern still applies: the result as first understood, the information that changed it, a fair hearing for another view, and a concrete habit. A custom sample follows the figures and questions from your own session, whether they concerned p values, confidence intervals or a published study your instructor chose.
Where can I find a free HS345 Unit 7 sample paper?
The full Unit 7 reflection is on this page, on how confidence intervals reversed a vote based on two p values.
Can a statistically significant result be unimportant?
Yes. In a large study a very small effect can reach significance, so the effect size and its interval, judged against what would matter in practice, decide importance.