Open Prompts
Submit a prompt
Analysis

Run A Statistical Hypothesis Test

Describe the research question, the two groups being compared with their sample sizes, the outcome variable, and the significance level, and this prompt runs a complete hypothesis test end to end. - States the null and alternative hypotheses in plain language - Checks the chosen test's assumptions (normality, variance, independence) - Selects and justifies the right test, reporting the statistic, p-value - Reports a confidence interval alongside the p-value - Computes an effect size and comments on practical significance - Delivers the full Python/R workflow as code

Prompt
I need to determine whether {research_question}.

Context:
- Dataset: {groups_description}
- Sample sizes: Group A = {group_a_size}, Group B = {group_b_size}
- Variable being compared: {outcome_variable}
- Significance level: {significance_level}

Carry out:
1. State the null and alternative hypotheses in everyday language
2. Verify the assumptions the chosen test requires (normality, equal variance, independence)
3. Choose and justify the right statistical test (t-test, Mann-Whitney, chi-square, ANOVA, etc.)
4. Run it and report the test statistic, p-value, and confidence interval
5. Compute an effect size (Cohen's d, odds ratio, or another suitable measure)
6. Explain the outcome in plain language: "There is/isn't sufficient evidence that..."
7. Comment on practical significance (is the effect large enough to matter, even if it's statistically significant?)

Provide the Python/R code for the whole workflow, from loading the data to the conclusion.
Download .md

Variables

Related prompts

Analysis

Analyze A/B Test Results Rigorously

A statistics-first review of an A/B test that goes past a single p-value before you ship the result. - Inputs: control and treatment group results, primary metric, test duration, and optional segments - Checks: post-hoc power, statistical significance with confidence interval, absolute and relative effect size - Flags: novelty-effect risk, sample ratio mismatch, peeking problems, and multiple-comparison issues - Output: a ship/kill/keep-testing call with the reasoning behind it

Analysis

Analyze Dataset Correlations And Risks

Goes past a raw correlation matrix to flag the relationships in a dataset that actually matter before modeling starts. - Inputs: key variables of interest plus dataset columns, types, and row count - Analysis: correlation matrix, non-obvious pairings, multicollinearity risk, categorical-to-numeric associations, and time-lagged correlations - Warns: spurious correlations that look causal but aren't - Output: plain-language findings plus runnable Python code

Analysis

Analyze Industry Trends And Predictions

Scans an industry over a chosen timeframe and data sources to surface major trend shifts, emerging patterns, and disruption signals, then covers technology impacts, consumer-behavior changes, and regulatory shifts before producing evidence-backed predictions for the next two to five years. Useful for strategy and planning teams who need a forward-looking read rather than a snapshot of current competitors.