Related Data Science Links
Learn Pca Data Science Tutorial, validate concepts with Pca Data Science MCQ Questions, and prepare interviews through Pca Data Science Interview Questions and Answers.
PCA Q&A
1What is PCA?
Answer: Dimensionality reduction technique using orthogonal principal components.
2PCA objective?
Answer: Preserve maximum variance in fewer components.
3Why center data before PCA?
Answer: PCA depends on covariance around zero-mean features.
4Need standardization?
Answer: Yes when features are on different scales.
5What are eigenvectors/eigenvalues?
Answer: Eigenvectors define component directions; eigenvalues indicate explained variance.
6Explained variance ratio?
Answer: Portion of total variance captured by each component.
7How choose components?
Answer: Use cumulative explained variance and validation metrics.
8PCA limitation?
Answer: Linear method; may miss nonlinear structures.
9PCA for visualization?
Answer: Yes, often to 2D/3D for exploratory plots.
10One-line summary?
Answer: PCA compresses features while retaining major variation patterns.