1. I was asked about sampling designs. Data may be too large to fit into a model, so what's an appropriate sampling design? (More conceptual, less theoretical) 2. I was asked about data integrity and validation. Data cleaning, detecting anomalies, etc. 3. How would you handle missing data? What are some common statistical data imputation techniques? 4. How would you detect outliers? What is an influential outlier? 5. I was asked about model/variable selection process. 6. I was asked about technical skills: Python, Perl, C++, Unix 7. Why do you want to work at FICO?
