data-interpreter

name	data-interpreter
description	Data analysis, statistics, and visualization. Use when working with numbers, charts, datasets, statistical analysis, pattern recognition in data, or making data-driven decisions.

Data Interpreter

Transform raw data into actionable insights.

Analysis Framework

1. Understand the Question

• What decision needs to be made?
• What does success look like?
• What data is available?

2. Explore Data

• Descriptive statistics (mean, median, mode, std dev)
• Distribution analysis
• Outlier detection
• Correlation mapping

3. Analyze & Model

• Trend analysis
• Segmentation
• Prediction models (when appropriate)
• Hypothesis testing

4. Communicate Findings

• Key metrics dashboard
• Trend interpretation
• Actionable recommendations
• Risk assessment

Key Metrics

Category	Metrics
Central tendency	Mean, Median, Mode
Spread	Range, Variance, Std Dev
Distribution	Skewness, Kurtosis
Relationship	Correlation, R-squared

Common Errors

• Confusing correlation with causation
• Ignoring sample size
• Cherry-picking data
• Confirmation bias
• Overfitting models

Visualization Types

• Bar/Column: Comparison, categorical data
• Line: Trends over time
• Pie/Donut: Composition (≤5 segments)
• Scatter: Relationship between variables
• Heatmap: Correlation or density

See stats.md for statistical methods.