Chapter 24 — Applied research methods
Lesson map
Lesson 24 published. Map, example, EX070.
flowchart TD
N0["Learning outcomes"]
N1["24.1 Framing a question"]
N2["24.2 Simple design"]
N3["Lab — Crossover comparison of reminder types"]
N4["24.3 Ethics and data"]
N5["Synthesis"]
N0 --> N1 --> N2 --> N3 --> N4 --> N5
N5 --> EX["Worked example"]
EX --> Q["Exercise EX070"]
Logical drawing
flowchart LR
N0["Learning outcomes"]
N1["24.1 Framing a question"]
N2["24.2 Simple design"]
N3["Lab — Crossover comparison of reminder types"]
N4["24.3 Ethics and data"]
N5["Synthesis"]
N0 --> N1 --> N2 --> N3 --> N4 --> N5 --> Q["EX070"]
[Learning outcomes]
|
v
[24.1 Framing a question]
|
v
[24.2 Simple design]
|
v
[Lab — Crossover comparison of reminder types]
|
v
[24.3 Ethics and data]
|
v
[Synthesis]
|
v
[Worked example] --> [Exercise EX070]
Learning outcomes
You will (1) frame a small applied research question; (2) choose a simple design suited to a workplace; (3) handle ethics and data responsibly.
24.1 Framing a question
Lucas notices that some clinics send their monthly reminder by email while others mention it in the morning huddle. He frames a question: does a spoken reminder in the huddle lead to more reports in the following week than an email reminder? The question is narrow, practical and answerable with existing data. Marta encourages him to state in advance what difference would matter to managers, so that the result guides a real decision about how to send reminders. The managers suggest a threshold.
24.2 Simple design
Lucas designs a crossover: in month one, half the clinics use spoken reminders and half email; in month two, they swap. Each clinic serves as its own comparison, which reduces the effect of differences between clinics. He counts reports in the week after each reminder. The lab compares totals. He notes that crossover designs assume the first reminder does not affect the second month too strongly, which he checks by looking at the week before each reminder. No carry-over pattern is found.
Lab — Crossover comparison of reminder types
# Crossover: reports in the week after each reminder type (synthetic, 16 clinics).
m1 = {"spoken": 30, "email": 18}; m2 = {"spoken": 28, "email": 21}
print("spoken total", m1["spoken"] + m2["spoken"], "email total", m1["email"] + m2["email"])
Run with python3 lab_cross.py. Verified output:
spoken total 58 email total 39
24.3 Ethics and data
The study uses existing aggregate report counts and normal reminders, so no extra burden falls on staff. Lucas informs clinic managers and staff that reminder styles are being compared and that no individual data are used. The practice manager and Marta approve the plan. Data are kept in a restricted folder and deleted after the report. Applied research in workplaces must be as respectful as academic research, even when it seems minor, because staff trust is easily lost. Managers agree to take part.
Worked example
Lucas frames a reminder question, runs a two-month crossover across clinics and handles ethics transparently.
Synthetic case. Data are synthetic.
Errors and limits
Carry-over effects. Few clinics.
Exercises
- EX070 — Research question. What did Lucas ask? Rubric: 3 = whether spoken huddle reminders lead to more reports than email;; 2 = reminders;; 1 = vague;; 0 = none.
- EX071 — Crossover benefit. Why use a crossover design? Rubric: 3 = each clinic serves as its own comparison;; 2 = self-comparison;; 1 = vague;; 0 = none.
- EX072 — Lab totals. What totals did the lab compare? Rubric: 3 = spoken 58 versus email 39 reports;; 2 = spoken higher;; 1 = vague;; 0 = none.
Synthesis
Small workplace studies can answer practical questions with simple, ethical designs.
Continue studying — chapter 24 of 30
← Chapter 23 (draft) · Course chapter index · Chapter 25 (draft) →