Free CFA Quantitative Methods Practice Questions & Answers
1,200 exam-style Quantitative Methods questions. Pick your answer, hit Check answer, and see the worked solution — free to start, no signup.
100% free · No login to start
Question 301
A feature with extremely high variance may:
Select an option first.
Correct answer: A — Dominate distance‑based models
Explanation: Why A is right: High‑variance features can overshadow others in models like KNN. Why others are wrong: B: Not always removed. C/D: Not implied.
Question 302
A feature that is strongly correlated with many other features may:
Select an option first.
Correct answer: A — Indicate multicollinearity
Explanation: Why A is right: Strong correlations across features signal redundancy. Why others are wrong: B/C/D: Not implied.
Question 303
A feature with many identical values and few unique values is:
Select an option first.
Correct answer: A — Low‑cardinality
Explanation: Why A is right: Few unique values = low cardinality. Why others are wrong: B: Opposite. C: Sparsity refers to zeros. D: Could be categorical.
Question 304
A feature with many unique categories (e.g., thousands) is:
Select an option first.
Correct answer: A — High‑cardinality
Explanation: Why A is right: Many unique values = high cardinality. Why others are wrong: B: Opposite. C/D: Not implied.
Question 305
A feature that is highly skewed and contains outliers may benefit from:
Select an option first.
Correct answer: A — Log or square‑root transformation
Explanation: Why A is right: Transformations reduce skew and stabilize variance. Why others are wrong: B/C/D: Not appropriate.
Get the full CFA question bank — free
Drop your email and we'll send you fresh CFA practice questions, fully worked solutions and exam-deadline reminders. No spam — unsubscribe in one click.
A feature that is highly correlated with time (e.g., trending upward) may require:
Select an option first.
Correct answer: A — Detrending
Explanation: Why A is right: Detrending removes time‑based drift. Why others are wrong: B/C/D: Not relevant.
Question 307
A feature that is measured on a very different scale from others may require:
Select an option first.
Correct answer: A — Scaling
Explanation: Why A is right: Scaling ensures features contribute proportionally. Why others are wrong: B/C/D: Not related.
Question 308
A feature that shows a strong nonlinear relationship with the target may benefit from:
Select an option first.
Correct answer: A — Polynomial transformation
Explanation: Why A is right: Polynomial terms help capture nonlinear patterns. Why others are wrong: B: Used for categorical variables. C: Used for text. D: Not relevant.
Question 309
A feature with many identical values and only a few distinct values is:
Select an option first.
Correct answer: A — Low‑cardinality
Explanation: Why A is right: Few unique values = low cardinality. Why others are wrong: B: Opposite. C/D: Not implied.
Question 310
A feature that is highly correlated with the target but also highly correlated with time may require:
Select an option first.
Correct answer: A — Detrending
Explanation: Why A is right: Detrending removes time‑based drift that can mislead models. Why others are wrong: B/C/D: Not appropriate.
Question 311
A feature that contains extreme outliers may be handled by:
Select an option first.
Correct answer: A — Winsorization
Explanation: Why A is right: Winsorization caps extreme values to reduce their influence. Why others are wrong: B/C/D: Not related.
Question 312
A feature that is strongly correlated with the target but also perfectly correlated with another feature is:
Select an option first.
Correct answer: A — Redundant
Explanation: Why A is right: Perfect correlation means one feature adds no new information. Why others are wrong: B: Not always harmful, but redundant. C/D: Correlation doesn’t imply type.
Question 313
A feature that varies widely in scale compared to others may distort:
Select an option first.
Correct answer: A — Distance‑based models
Explanation: Why A is right: Models like KNN and SVM rely on distance; unscaled features dominate. Why others are wrong: B/C/D: Not affected by scale.
Question 314
A feature that is highly skewed and contains many zeros may benefit from:
Select an option first.
Correct answer: A — Log(1 + x) transformation
Explanation: Why A is right: Log(1 + x) handles zeros and reduces skew. Why others are wrong: B/C/D: Not appropriate.
Question 315
A feature that is strongly correlated with the target but also strongly correlated with noise variables may:
Select an option first.
Correct answer: A — Mislead the model
Explanation: Why A is right: Correlation with noise can create false patterns. Why others are wrong: B: It may hurt accuracy. C: Not always removed. D: Not implied.
Question 316
A feature that is extremely sparse (mostly zeros) may be:
Select an option first.
Correct answer: A — Useful if it captures rare but important events
Explanation: Why A is right: Sparse features can be valuable if the rare events they represent matter. Why others are wrong: B/C: Not always true. D: Sparsity doesn’t imply type.
Question 317
K‑means clustering requires the user to specify:
Select an option first.
Correct answer: A — The number of clusters
Explanation: Why A is right: K‑means requires choosing k, the number of clusters. Why others are wrong: B: Distance metric is usually fixed (Euclidean). C/D: Used in hierarchical clustering.
Question 318
A key limitation of K‑means is that it:
Select an option first.
Correct answer: A — Assumes spherical clusters
Explanation: Why A is right: K‑means assumes clusters are roughly spherical and similar in size. Why others are wrong: B: K‑means requires numeric data. C: It scales well. D: It does require initialization.
Question 319
The K‑means algorithm updates clusters by:
Select an option first.
Correct answer: A — Reassigning points to the nearest centroid
Explanation: Why A is right: K‑means iteratively assigns points to the closest centroid. Why others are wrong: B/C/D: Not part of the algorithm.
Question 320
A centroid in K‑means represents:
Select an option first.
Correct answer: A — The mean of all points in a cluster
Explanation: Why A is right: K‑means uses the mean to define cluster centers. Why others are wrong: B/C/D: Not used in K‑means.
Question 321
Hierarchical clustering differs from K‑means because it:
Select an option first.
Correct answer: A — Does not require specifying the number of clusters upfront
Explanation: Why A is right: Hierarchical clustering builds a full tree first; clusters can be chosen later. Why others are wrong: B: No centroids used. C: Can use various distance metrics. D: Dendrograms visualize results.
Question 322
Agglomerative clustering starts with:
Select an option first.
Correct answer: B — Each observation as its own cluster
Explanation: Why B is right: Agglomerative = bottom‑up, starting with individual points. Why others are wrong: A: That’s divisive clustering. C: K‑means uses random centroids. D: Not required.
Question 323
Divisive clustering starts with:
Select an option first.
Correct answer: B — One large cluster
Explanation: Why B is right: Divisive = top‑down, starting with one cluster and splitting. Why others are wrong: A: Agglomerative. C/D: Not required.
Question 324
A dendrogram is used to:
Select an option first.
Correct answer: A — Visualize hierarchical clustering
Explanation: Why A is right: Dendrograms show how clusters merge or split. Why others are wrong: B/C/D: Not dendrogram uses.
Question 325
In a dendrogram, the height at which two branches merge represents:
Select an option first.
Correct answer: A — The distance between clusters
Explanation: Why A is right: Height corresponds to dissimilarity. Why others are wrong: B/C/D: Not represented by height.
Question 326
A shorter branch height in a dendrogram indicates:
Select an option first.
Correct answer: A — More similar clusters
Explanation: Why A is right: Short height = low distance = high similarity. Why others are wrong: B: Opposite. C/D: Not related.
Question 327
A distance matrix in clustering contains:
Select an option first.
Correct answer: A — Pairwise distances between observations
Explanation: Why A is right: Clustering relies on distances between points. Why others are wrong: B/C/D: Not distance matrices.
Question 328
Euclidean distance is most appropriate when:
Select an option first.
Correct answer: A — Features are numeric and scaled
Explanation: Why A is right: Euclidean distance assumes numeric, comparable scales. Why others are wrong: B: Use Hamming or other metrics. C: Requires vectorization. D: Not meaningful.
Question 329
A key limitation of hierarchical clustering is that it:
Select an option first.
Correct answer: A — Cannot be undone once clusters merge
Explanation: Why A is right: Hierarchical clustering is greedy; merges cannot be reversed. Why others are wrong: B: No k needed. C: Dendrograms exist. D: Works with any distance metric.
Question 330
The “elbow method” is used to:
Select an option first.
Correct answer: A — Choose the number of clusters in K‑means
Explanation: Why A is right: The elbow point indicates diminishing returns in reducing within‑cluster variance. Why others are wrong: B/C/D: Not related.
Every question on this page stays free and open either way.
Add Your Testimonial
Privacy Preference
We use cookies to enhance your browsing experience, serve personalized content, and analyze our traffic. By clicking "Accept All", you consent to our use of cookies on this platform.
Before you go, can we ask you one thing?
We are just getting started, and knowing what is holding you back would help us a lot. It takes about 20 seconds.
Overall rating
★★★★★
How likely are you to recommend us to a friend? (0 to 10)What is stopping you from creating a free account?
🎉
Thank you
We read every response. This is exactly how we make PCC better for you.
CCarr
Free assistant · no signup
Carr only reads what is public on PCC, plus your own practice progress.