Simpson's paradox … and how to avoid it

By H. J. Norton, G. Divine. 2015

24 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Kristina Lerman
2. Nazanin Alipourfard
3. Peter G. Fennell
4. Fred Morstatter
5. Ninareh Mehrabi
6. Aram Galstyan

In Statistics and Probability

1. Kristina Lerman
2. Nazanin Alipourfard
3. Peter G. Fennell
4. Aram Galstyan
5. Fred Morstatter
6. Nripsuta Ani Saxena
7. Ninareh Mehrabi

Citations in the corpus

• Using Simpson's Paradox to Discover Interesting Patterns in Behavioral Data (2018, methodology): “Simpson’s paradox (Blyth 1972; Norton and Divine 2015) often confounds analysis of heterogeneous data, especially social and behavioral data.”
• Can you Trust the Trend?: Discovering Simpson's Paradoxes in Social Data (2018, methodology): “to user behavior on Stack Exchange. We also illustrate the di‡erence between our method and linear models that model the outcome variable as a function of bothXp andXc. Forsuchmultivariatelinearmodels[17],wecan•tamodel fp;c„α + βXp + βcXc”to the disaggregated data, and compare the sign of the coe†ci”