Maternal Smoking & Birth Weight
Birth weight, gestation, and maternal health for 1,174 mother-baby pairs from the Child Health and Development Studies — the classic causality-vs-correlation dataset.
Each row is one mother-baby pair from the Child Health and Development Studies (Oakland, CA, 1960s): birth weight, gestational days, maternal age, height, pregnancy weight, and whether the mother smoked.
We use it to practice comparing distributions across groups and to have the “does association mean causation?” argument with real stakes — it’s the canonical example from Berkeley’s Data 8 curriculum, which DS-100 adapts.
Used in
Citing this dataset
Course style guide rule: cite the dataset name, provider, and the date you accessed it — e.g. "Maternal Smoking & Birth Weight. Course data catalog, courses.langd0n.com. Accessed [date]." If the entry names an upstream source (a city portal, a public agency), cite that too.