Suppression of Small Classes & Information Loss
This lesson is part of the course
In this lesson
You suppress the records in classes below k = 3, measure how much of the data that costs and check whether it biases the statistic the researchers care about.
Buy the course once for $9.99 to unlock every lesson and lab, the final exam and the certificate – lifetime access, no subscription.
Lessons in this course
- Direct Identifiers, Quasi-Identifiers & Sensitive Attributes Locked
- Pseudonymisation: Lookup Keys, Salted IDs & Masking Locked
- Generalisation: Age Bands & ZIP Prefixes Locked
- k-Anonymity: Equivalence Classes with COUNTIFS Locked
- Suppression of Small Classes & Information Loss Locked
- l-Diversity: When Everyone in a Class Shares the Secret Locked
- Re-identification Risk: 1/k, Average & Maximum Risk Locked
- Data Minimisation & Retention: Which Rows Must Go? Locked