Agent Skills: Statistics Skill

Statistical analysis methods, hypothesis testing, and probability for data analytics

statistical-analysishypothesis-testingprobabilitydata-analytics
analyticsID: pluginagentmarketplace/custom-plugin-data-analyst/statistics

Skill Files

Browse the full folder contents for statistics.

Download Skill

Loading file tree…

skills/statistics/SKILL.md

Skill Metadata

Name
statistics
Description
Statistical analysis methods, hypothesis testing, and probability for data analytics

Statistics Skill

Overview

Master statistical concepts and methods essential for data analysis, from descriptive statistics to advanced inferential techniques.

Core Topics

Descriptive Statistics

  • Measures of central tendency (mean, median, mode)
  • Measures of dispersion (variance, standard deviation, IQR)
  • Data distributions and skewness
  • Percentiles and quartiles

Inferential Statistics

  • Sampling methods and sample size determination
  • Confidence intervals
  • Hypothesis testing (t-tests, chi-square, ANOVA)
  • P-values and statistical significance

Probability

  • Basic probability rules
  • Probability distributions (normal, binomial, Poisson)
  • Bayes' theorem
  • Expected value and variance

Regression Analysis

  • Linear regression
  • Multiple regression
  • Logistic regression
  • Model validation and diagnostics

Learning Objectives

  • Apply descriptive statistics to summarize data
  • Conduct hypothesis tests for business decisions
  • Build and interpret regression models
  • Communicate statistical findings effectively

Error Handling

| Error Type | Cause | Recovery | |------------|-------|----------| | Sample too small | Insufficient data | Increase sample or use bootstrap | | Assumption violated | Data doesn't fit test | Use non-parametric alternative | | Multicollinearity | Correlated predictors | Remove or combine variables | | Outliers | Extreme values | Investigate or use robust methods | | P-hacking | Multiple testing | Apply Bonferroni correction |

Related Skills

  • programming (for implementing statistical models)
  • visualization (for presenting statistical insights)
  • advanced (for machine learning)