🔬 Research
Survey Analysis Prompt: Results Tables and Open-End Themes
Paste survey counts and comments to get checked results tables, segment comparisons with base sizes, coded open-end themes with quotes, and a short readout.
0Reviews
Prompt
Act as a survey research analyst who turns pasted survey results into a short, honest readout. You compute every percentage from the counts I give you, show the base for every number, code open-ended comments into themes with real quotes, and flag where the data is too thin to support a claim. Inputs: - What the survey was for and the decision it should inform: [SurveyGoal] - Questions and answer options, in order: [QuestionList] - Response counts per option for each closed question: [ResponseCounts] - Counts split by segment, if I have them: [SegmentCounts] - Open-ended comments, pasted verbatim: [OpenEnds] - Who will read the readout and how long it can be: [Audience] - Base size below which a segment result is only directional (default 30): [MinBase] Generate: 1. Data check: total n per question, whether option counts add up, missing or skipped answers, and anything that looks off. Stop and ask if totals do not reconcile. 2. Results tables: for each closed question, count and percentage per option (one decimal), with the base n above the table. 3. Segment comparison: for each SegmentCounts split, percentages within each segment, the base for each, and a "directional only" flag when a base is under MinBase. Describe differences in plain words; do not claim statistical significance unless I ask for a test and the counts allow it. 4. Open-end themes: a short codebook (theme, rule for what counts), the number of comments per theme, and 1 or 2 verbatim quotes each. Comments can carry more than one theme; say if any do. 5. Key findings: 3 to 5 findings, each tied to a number or theme count from the steps above, written for Audience. 6. Caveats and next questions: who answered versus who did not, what the survey cannot tell us, and 2 or 3 follow-up questions for SurveyGoal. Rules: - Never invent responses, quotes, percentages, or benchmarks from other surveys. - Keep percentages tied to their base; say "of 50 lap swimmers", not just "48%". - If I paste personal details in comments, leave them out of the quotes.
Instructions
Paste counts exactly as your survey tool exports them, plus open comments as plain text. Remove names, emails, and other personal details first. For tests of significance, ask separately and give the raw counts per segment.
Generated Output
This image was generated using the prompt above.
Examples
Example Input
SurveyGoal: Riverside Community Pool board wants to decide whether to change weekday opening hours before membership renewals in January. QuestionList: Q1 "How satisfied are you with current opening hours?" (Very satisfied, Satisfied, Neutral, Dissatisfied, Very dissatisfied). Q2 "Do you plan to renew your membership?" (Yes, No, Not sure). Q3 open: "What one change would improve your membership?" ResponseCounts: Q1: Very satisfied 30, Satisfied 42, Neutral 24, Dissatisfied 18, Very dissatisfied 6. Q2: Yes 84, No 12, Not sure 24. SegmentCounts: Q1 by member type. Families (n=70): Very satisfied or Satisfied 48, Neutral 14, Dissatisfied or Very dissatisfied 8. Lap swimmers (n=50): Very satisfied or Satisfied 24, Neutral 10, Dissatisfied or Very dissatisfied 16. OpenEnds (10 comments): "Open lap lanes before 6am, I swim before work" / "Cleaner changing rooms please" / "More lesson slots for kids, waitlist is long" / "Lap lanes at 5:30 would be great" / "The showers are often dirty by evening" / "Earlier opening on weekdays" / "Parking lot is full on Saturdays" / "Lockers and floors in the women's changing room need attention" / "Swim lessons fill up in minutes" / "Lap swim before 6 would make me renew" Audience: 5 volunteer board members, one page, read before Tuesday's meeting. MinBase: 30
Example Output
1. DATA CHECK Q1: 30 + 42 + 24 + 18 + 6 = 120. Q2: 84 + 12 + 24 = 120. Segments: 70 families + 50 lap swimmers = 120, and segment counts add back to Q1 totals (satisfied 48 + 24 = 72 = 30 + 42; dissatisfied 8 + 16 = 24 = 18 + 6). Q3: 10 comments, so 110 of 120 respondents left it blank. No reconciliation issues. 2. RESULTS TABLES Q1 Satisfaction with opening hours (base: 120) Very satisfied 30 (25.0%) | Satisfied 42 (35.0%) | Neutral 24 (20.0%) | Dissatisfied 18 (15.0%) | Very dissatisfied 6 (5.0%) Satisfied overall: 72 (60.0%). Dissatisfied overall: 24 (20.0%). Q2 Plan to renew (base: 120) Yes 84 (70.0%) | No 12 (10.0%) | Not sure 24 (20.0%) 3. SEGMENT COMPARISON, Q1 Families (base 70): satisfied 48 (68.6%), neutral 14 (20.0%), dissatisfied 8 (11.4%) Lap swimmers (base 50): satisfied 24 (48.0%), neutral 10 (20.0%), dissatisfied 16 (32.0%) Both bases are above 30. Lap swimmers are less satisfied with hours: 16 of 50 dissatisfied versus 8 of 70 families. No significance test was run. 4. OPEN-END THEMES (10 comments, one theme each) Early lap hours (comment asks for lap swimming or opening before about 6am): 4. "Lap swim before 6 would make me renew." "Lap lanes at 5:30 would be great." Changing room cleanliness: 3. "The showers are often dirty by evening." Swim lesson capacity: 2. "Swim lessons fill up in minutes." Weekend parking: 1. "Parking lot is full on Saturdays." 5. KEY FINDINGS (for the board) - 60.0% of 120 members are satisfied with opening hours; 20.0% are not. - Dissatisfaction sits mostly with lap swimmers: 32.0% of 50, against 11.4% of 70 families. - Early lap swimming is the most common request, in 4 of 10 comments, and one ties it to renewing. - 20.0% of members are not sure they will renew, so the January decision matters. - Changing room cleanliness came up in 3 comments; it is not an hours issue but worth a separate look. 6. CAVEATS AND NEXT QUESTIONS - Only 10 of 120 people wrote a comment, so theme counts show what was raised, not how common it is across members. - We know who answered, not who skipped the survey; members unhappy enough to leave may be missing. - Renewal plans are intentions, not renewals. Next: Would lap swimmers use a 5:30am weekday lap session, and on which days? Would families accept fewer lanes in the first hour if it meant early lap time? Is the "Not sure" group mostly lap swimmers? (Needs Q2 split by member type.)