Week 14 Discussion — Does "Not Significant" Mean "No Difference"? — Traditional alternative (no AI)
Instructors: publish this instead of the adaptive version if you prefer, and unpublish or delete the adaptive one.
Hook
A headline says a new tutoring program made "no difference" to grades. A company says its two checkout pages convert "the same." A study of penguins finds the sex split "consistent with even." Each claim rests on a test that failed to reject a null hypothesis, and this week you saw why "not significant" is not the same as "no difference." You also saw a 1,375.35 g gap between Gentoo and Adelie penguins that was both significant and large. Deciding what a test result should change in the real world is where statistics meets judgment.
Your discussion question — choose Option A or Option B; they carry the same weight and the same rubric, and you say which you picked.
Option A: Pick a comparison you care about from your life, your major, your job, or your community, such as two study methods, two clinic schedules, two prices, two training plans, or a claimed average or claimed share. Say which of this week's four procedures (the one-sample t test, the two-sample t test, the one-proportion z test, or the two-proportion z test) fits it and why, which condition you would worry about most, and what you would do if the test came back "not significant."
Option B: Take a position on this claim: "When a study finds no statistically significant difference, people should act as if there is no difference." Use a setting from your major or your work, such as a nurse comparing two treatments, a manager comparing two suppliers, or a city comparing two bus routes, to argue when acting that way is reasonable and when it is risky. Along the way, explain how a confidence interval could change the decision.
There is no single right answer. A small study, a huge study, a cheap change, or a costly one can each push a careful person in a different direction. Pick one you actually care about, and tell us the story.
Expectations
Activity format: one initial post followed by two substantive peer replies. Plan on about 45 minutes across the two deadlines; your instructor sets both due dates in Canvas.
Your initial post — by the first due date (early in the module week):
- Say which option you chose.
- Describe your real comparison or report in plain words, so a reader who was not there knows what was measured, on whom, and in how many groups.
- Use at least two of this week's terms (null value, one-sample t test, two-sample t test, one-proportion z test, two-proportion z test, pooled proportion, independent samples, duality of tests and intervals) correctly.
- Give your position with a reason, and name the procedure, condition, or decision your reason rests on.
- Length: roughly 150–250 words if written. You may instead record your post as audio or video (about two minutes) and attach a transcript; both forms are scored by the same rubric.
Your replies — by the second due date (the end of the module week):
- Reply substantively to at least two classmates.
- A substantive reply does more than agree: ask whether the poster's procedure matches a mean or a proportion and one group or two, test whether their "not significant" quietly became "no difference", or ask what a confidence interval would add to their decision. "Nice point!" on its own does not count.
What a strong post looks like:
I chose Option B. In a pharmacy, two pill-counting machines could be compared on the share of bottles that come out miscounted, which is a two-proportion z test. If that test came back not significant from only a few hundred bottles, I would not call the machines equal. The data would be consistent with no difference, but a confidence interval might still allow a gap big enough to matter for patients, so I would collect more data before choosing the cheaper machine.
Notice how it names a procedure with a reason, keeps "fail to reject" separate from "no difference", and ties the result to a real decision. That is the bar.
Participation rubric
This discussion is worth 10 points. The three criteria below look at your initial post and your peer replies.
| Criterion | Full credit | Partial credit | No credit |
|---|---|---|---|
| Quality of the initial post (4 pts) | A real, specific comparison or report is described, a matching procedure is named with the reason it fits, and the position is tied to a real decision | An example is present, but the position is asserted without a reason | Missing, off-topic, or no reasoning about a test |
| Use of course concepts (3 pts) | Uses this week's terms precisely, never treats "fail to reject" as proof of no difference, and separates statistical from practical significance or uses an interval to show plausible differences | Uses a term loosely or with a small error | No course terms, or used incorrectly |
| Engagement with peers (3 pts) | Two or more substantive replies that extend or challenge a classmate's reasoning | One substantive reply, or replies that only agree | No replies, or "I agree" with nothing added |
Post early if you can — the best threads happen when people have time to reply before the second due date.
Built with The Course Maker · samples.thecoursemaker.com