Analyze Video View Distribution: Mode, Median, Mean Comparison
Overview
This question evaluates competency in statistical summarization (mode, median, mean), elementary probability, and causal reasoning/experimental design for a Data Scientist role within the Statistics & Math domain, requiring both conceptual understanding of distributional behavior and practical application in probability and hypothesis testing.
Meta
Aug 4, 2025, 10:55 AM
Data Scientist
Onsite
Statistics & Math
52
0
Scenario
You are analyzing user engagement on a short‑video sharing product. You have a distribution of “video views per user,” and you observe that average watch length has increased while average share count per video has decreased.
Assume, unless stated otherwise, that share events are independent across videos and that each watched video has the same probability of being shared.
Tasks
- Describe and compare the mode, median, and mean for the distribution of video views per user. Explain what you would expect for a short‑video app and what each measure tells you.
- Each video a user watches has a 10% chance of being shared. What is the probability that at least one of ten watched videos is shared? State your assumptions.
- Given the observation that average watch length increased while average share count per video decreased, propose plausible hypotheses and outline how you would test them (metrics to cut, experimental/causal methods, and validation/guardrails).
Solution
Login required
Show