Statistics for data science
Undergraduate · Data science
Syllabus focus
Topics typically covered
Standard syllabus
Probability and sampling
- Random variables and common distributions used in DS
- Expectation, variance, and independence intuition
- Sampling distributions and the CLT in practice
- Bootstrap resampling for uncertainty (intro)
- Bias vs variance in estimators
- Simulation for understanding random processes
Inference
- Point estimates and confidence intervals
- Hypothesis tests for means and proportions
- p-values, Type I/II errors, and power (intro)
- Multiple comparisons awareness
- Nonparametric alternatives survey
- Connecting tests to business or science questions
Regression for DS
- Simple and multiple linear regression
- Residual diagnostics and influence
- Categorical predictors and interactions (intro)
- Logistic regression for binary outcomes (intro)
- Model selection pitfalls and overfitting
- Interpreting coefficients for stakeholders
STEM / applied
Computational stats
- Implementing summaries and tests in Python or R
- Monte Carlo experiments for intuition
- Visualizing sampling variability
- A/B test design basics and peeking risks
- Reporting effect sizes with intervals
- Reproducible statistical notebooks
Data-science bridges
- From EDA to confirmatory analysis
- Feature noise and measurement error awareness
- Causal language caution vs predictive goals
- Survey of GLMs beyond logistic (optional)
- Critiquing published analyses
- Capstone: statistical report on a real dataset
Notes
May overlap Math Intro Statistics / Regression; tutoring emphasizes DS tooling and predictive vs explanatory framing used in the course.