Analyze survey results with crosstabs, weighting, and significance
A sound quantitative analysis of survey data, with response-bias checks, weighting, crosstabs, and only the differences that are real.
The prompt
Help me analyze quantitative survey results correctly.
Survey goal and key questions: [what we want to learn]
Sample: [number of responses, how people were invited, response rate]
Population benchmarks: [known shares of the full population by key groups, e.g. region, tenure, plan - if available]
Data: [PASTE results or describe columns: question types (single choice, multi-select, Likert, NPS), respondent attributes]
Segments to compare: [e.g. new vs. long-time customers, regions]
Steps:
1. Check representativeness: compare the sample to population benchmarks and flag over- or under-represented groups. Recommend whether to weight and how (e.g. post-stratification or raking), and warn when weights get extreme.
2. Clean the data: speeders, straight-liners, duplicates, incomplete responses.
3. Summarize each key question correctly for its type: top-2-box for Likert, NPS calculation, multi-select shares that can sum past 100%.
4. Build crosstabs for the requested segments with base sizes shown. Flag cells with small bases (e.g. under 30) as directional only.
5. Test which differences are statistically meaningful, correcting for multiple comparisons, and report margins of error.
6. Summarize the findings that are both significant and large enough to matter.
Return:
- A data quality and representativeness summary.
- Crosstab tables with bases and significance flags.
- Top findings with confidence levels.
- Code outline in [Python / R / Excel] to reproduce it.
Use only the data I provide; do not invent numbers.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- what we want to learn
- number of responses, how people were invited, response rate
- e.g. new vs. long-time customers, regions
- Python / R / Excel
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Explain my Excel model to a non-technical executiveTurns a complex spreadsheet or model into a plain-English walkthrough an executive can follow, trust, and question.
- Run a fair lending review of loan pricing and approval dataA structured fair lending analysis plan and readout that tests for disparities in approvals, pricing, and exceptions.
- Analyze my fleet's CSA safety scores and plan how to lower themExplains which safety categories are driving high scores, which inspections and crashes matter most, and what to fix first.
- Find what drove my store's weekly sales resultBreaks a store's sales variance into traffic, conversion, ATV, and UPT, then gives specific actions for next week.