Distill
Prep
Python
GenAI
GenAI Frameworks
NLP
Deep Learning
Machine Learning
ML Libraries
Statistics
SQL
MLOps
Cloud
System Design
Pricing
Blog
Learn
Practice
Test
Live Engine
Select Topic
Easy
(32)
Medium
(27)
Hard
(25)
easy
Practice
[T10 · PCA] Before applying PCA, a data scientist must standardize the features (zero mean, unit variance). Why is this step essential?
A
PCA requires non-negative values — standardization ensures all values are positive
B
PCA finds directions of maximum variance — features with larger absolute scale (e.g., income in dollars vs age in years) dominate the variance; standardization ensures each feature contributes equally to the covariance matrix before PCA finds its principal directions
C
Standardization is optional — PCA is scale-invariant
D
Standardization is only needed when features have different units; same-unit features don't need it
Confirm Answer
Previous
Back
Next