| Course | PHLT 8044 Advanced Program Evaluation |
|---|---|
| Week | Week 5 |
| Paper type | Peer reply |
| Length | About 450 words, 3 pages |
| Format | Discussion reply, APA 7 citations |
| School | Walden University |
| Program | PhD in Public Health |
| Updated | October 2026 |
Free sample paper for PHLT 8044 Week 5
Week 5 Discussion: Response to a Classmate
Peer Reply on a Proposed Comparison of Bottle Carriers and Non-Carriers in the Same Schools: The Selection Problem It Leaves Open and a School-Level Comparison That Sidesteps It
Response
Keisha, your proposal is to evaluate the school water program by comparing students who carry their program bottles with students who do not, within the same schools, on daily sugary drink intake. I like that it uses data the program could collect easily, a quick classroom count of bottles plus the student survey, and that it keeps school conditions the same for both groups. Those are real strengths.
My concern is with who ends up in each group. Students do not carry bottles at random. The ones who carry them are likely to be students whose families already value water, who are more health-conscious, or who play sports and need to stay hydrated. Those same students probably drink fewer sugary drinks to begin with. If carriers report less sugary drink intake than non-carriers, we cannot tell how much of the difference the bottle caused and how much was already there. Shadish et al. (2002) call this the selection threat: differences between groups that existed before the treatment and that could explain the outcome on their own. A comparison of self-selected users with non-users is especially exposed to it, because the choice to use the program is likely related to the outcome.
There is a second problem. The program aims to change behavior across a whole school, through stations everyone can use and a promotion everyone sees. Non-carriers in a program school are still exposed to stations and promotion, so comparing them with carriers measures the effect of carrying a bottle rather than the effect of the program. Rossi et al. (2019) advise matching the comparison to the level at which a program is delivered, which here is the school.
What would sidestep both problems? The program is being phased in, and 40 schools are on a waiting list for next year. Comparing whole program schools with waiting-list schools, before and after installation, compares groups that did not choose themselves into treatment. Because both sets of schools wanted the program, they may be similar in motivation, and measuring each school before and after removes stable differences between them. Wing et al. (2018) describe this difference-in-differences approach as well suited to policies rolled out over time, as long as program and comparison schools were on similar paths beforehand, which the purchase data from previous years could check.
Would that design still let you use your bottle counts? They could serve as an implementation measure, showing how much of the program reached students in each school, rather than defining the comparison groups.
References
Rossi, P. H., Lipsey, M. W., & Henry, G. T. (2019). Evaluation: A systematic approach (8th ed.). SAGE.
Shadish, W. R., Cook, T. D., & Campbell, D. T. (2002). Experimental and quasi-experimental designs for generalized causal inference. Houghton Mifflin.
Wing, C., Simon, K., & Bello-Gomez, R. A. (2018). Designing difference in difference studies: Best practices for public health policy research. Annual Review of Public Health, 39, 453-469. https://doi.org/10.1146/annurev-publhealth-040617-013507
Reading the PHLT 8044 Week 5 instructions
In the fifth thread, students answer a classmate's proposed evaluation design. Faculty expect the reply to identify what the design leaves unresolved, ideally one specific mechanism of bias explained clearly, rather than a list of every possible threat. Naming the threat in the terms of a standard source, such as Shadish, Cook and Campbell's validity typology, shows command of the concept. Strong replies also credit what the design does well and offer an alternative that addresses the problem, preferably one that uses information the classmate already planned to collect. Matching the comparison to the level at which a program is delivered is a common point. A source should support the critique, and the tone should be collegial. Replies of three to four hundred words are typical.
How the PHLT 8044 Week 5 example is put together
The reply restates the proposal and credits its easy data collection and shared school conditions. A paragraph explains that bottle carriers are likely to differ from non-carriers in family habits, health consciousness and sports participation, and that these same traits predict lower sugary drink intake, then names the selection threat. A second paragraph explains that non-carriers in program schools are still exposed to the program, so the comparison measures carrying rather than the program, and cites advice to match the comparison to the delivery level. A third proposes comparing program and waiting-list schools before and after installation, explains why both groups' application to the program helps, and cites difference-in-differences guidance on the parallel trends check. The reply closes by suggesting the classmate's bottle counts serve as an implementation measure.
Where the marks sit in the PHLT 8044 Week 5 rubric
Graders reward a reply that names one mechanism of bias precisely and explains why it matters for this design. A generic warning about confounding, or a list of threats without explanation, earns less. Credit goes to recognizing the second problem, that the comparison measures a component rather than the program, because it shows understanding of how the program is delivered. Offering a feasible alternative design, and keeping a useful part of the classmate's plan, demonstrates constructive engagement. Sources should be cited accurately and tied to specific points. Tone matters: the reply should credit the proposal's strengths and frame the critique as a way to make the evaluation more convincing. A clear structure, concession, problem, alternative, makes the reply easy for the classmate to use.
Common PHLT 8044 Week 5 mistakes, and how to avoid them
Design critiques often list threats without explaining any of them. Choose the one most likely to bias this particular comparison, explain how it would work in the classmate's data, and name it in standard terms. Check whether the comparison matches how the program is delivered. Offer an alternative design the program could actually carry out, and find a role for the classmate's own data in it. Credit what works before raising problems. Replies to other design proposals in your thread can follow the same order.
Get a PHLT 8044 Week 5 example written to your instructions
Include the classmate's design post along with the Week 5 prompt and rubric; the reply answers the comparison they actually proposed. It is turned around in 24-48h, nothing owed on a first request. Classmates are never named, and the reply refers to their design in terms that fit only that post.
More PHLT 8044 papers and PhD in Public Health samples
- PHLT 8044 Week 1: Monitoring Versus Evaluation Post
- PHLT 8044 Week 2: Water Program Evaluability Study
- PHLT 8044 Week 3: Water Access Program Logic Model
- PHLT 8044 Week 4: Water Program Evaluation Questions
- PHLT 8044 Week 6: Difference-in-Differences Memo
- PHLT 8044 Week 7: Indicators and Credibility Plan
- PHLT 8044 Week 8: Data Collection Schedule Plan
- PHLT 8044 Week 9: Preregistered Analysis Plan
- PHLT 8044 Week 10: First-Year Findings Memo
- PHLT 8044 Week 11: Second-Year Evaluation Plan
- PHLT 8042 Week 5: A1c Registry Justification Memo
- PHLT 8040 Week 5: Tools of Government Peer Replies
- PHLT 8034 Week 5: Formaldehyde Dose Reasoning
- PHLT 8032 Week 5: Chart Rationale Paper
PHLT 8044 Week 5 questions, answered
Suppose the classmate already compares whole schools?
In that case the reply turns to what a school comparison leaves unresolved, such as whether waiting-list schools differ from participating ones in ways that also affect decay, or whether schools changed hands between waves. With the actual post in hand, the reply targets the comparison it makes rather than this one.
Where can I find a free PHLT 8044 Week 5 sample paper?
This page reproduces the complete Week 5 reply, identifying selection bias in a comparison of bottle carriers with non-carriers and proposing a school-level difference-in-differences design.
Is comparing carriers with non-carriers always wrong?
Not always, but it answers a narrower question than intended. It can describe how carriers differ from non-carriers, yet it cannot isolate the program's effect because students choose whether to carry bottles.
What is the selection threat?
The possibility that groups differed before the program in ways that could explain the outcome on their own. When people choose whether to use a program, that choice is often related to the outcome.
Why compare whole schools rather than students?
The program is delivered to whole schools through stations and promotion, so every student in a program school is exposed. Comparing schools matches the comparison to the level at which the program works.