Dimensionality Reduction for High Correlation and Non-Normal Data
A data scientist is analyzing a dataset with 100 features and 10,000 observations. The target variable is binary (0/1). Initial exploratory data analysis reveals that many features have missing values, high correlation with each other, and non-normal distributions. The data scientist wants to identify the most important features for predicting the target while reducing dimensionality. Which TWO actions should the data scientist take? (Choose two.)
Quick Answer
The answer is to compute mutual information between each feature and the target, and apply Principal Component Analysis (PCA). Mutual information is the correct choice for identifying important features because it captures any non-linear relationship between a feature and the binary target, making it robust to non-normal distributions and high correlation. PCA then handles the high correlation by transforming the correlated features into uncorrelated principal components, reducing dimensionality without requiring normality. On the AWS Certified Machine Learning Specialty MLS-C01 exam, this question tests your ability to distinguish between correlation-sensitive methods like PCA and normality-dependent techniques like Pearson correlation; a common trap is choosing Pearson correlation, which assumes linearity and normality. Remember the memory tip: “PCA for correlation, mutual info for non-linear and non-normal”—pair them to handle both challenges effectively.
⚠ Common exam trap
The MLS-C01 exam often tests the misconception that correlation-based methods (like Pearson or chi-squared) are sufficient for feature selection in high-dimensional, non-normal data, when in fact they fail due to assumptions about linearity and distribution.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Apply Principal Component Analysis (PCA) to reduce dimensionality.
B is correct because Principal Component Analysis (PCA) is a dimensionality reduction technique that transforms correlated features into a set of linearly uncorrelated principal components, effectively handling high correlation and reducing the feature space. It does not require normality assumptions and can work with missing values after imputation, making it suitable for this dataset.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use chi-squared test to rank features by p-value.
Why it's wrong here
Chi-squared test is for categorical features, not continuous.
- ✓
Apply Principal Component Analysis (PCA) to reduce dimensionality.
Why this is correct
PCA reduces dimensionality by creating uncorrelated components, handling multicollinearity.
- ✗
Perform a t-test for each feature to compare means between classes.
Why it's wrong here
t-test is for two-group comparison, not suitable for ranking multiple features.
- ✗
Calculate Pearson correlation coefficients between features and target.
Why it's wrong here
Pearson correlation assumes linearity and normality, which are violated.
- ✓
Compute mutual information between each feature and the target.
Why this is correct
Mutual information captures non-linear dependencies and works with non-normal data.
Go deeper
Related to this question
About these practice questions
This MLS-C01 question is part of Courseiva's 1,672-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
Same concept, more angles
1 more way this is tested on MLS-C01
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A data scientist is analyzing a dataset with 1,000 features. They suspect many features are redundant and want to reduce dimensionality before training a model. Which technique is most appropriate for identifying the most important features?
easy- A.Apply principal component analysis (PCA) and select the top components
- ✓ B.Use L1 regularization (Lasso) to shrink coefficients to zero
- C.Train a random forest and remove features with low importance
- D.Compute the correlation matrix and remove features with high correlation
Why B: L1 regularization (Lasso) is the most appropriate technique for identifying the most important features because it performs feature selection by shrinking the coefficients of less important features to zero, effectively selecting a subset of original features. This directly identifies which features are most relevant. PCA, while a dimensionality reduction technique, creates new components that are linear combinations of original features and does not identify the importance of original features. Random forest feature importance and correlation matrix methods can identify redundant features but are less direct for selecting the most important subset.
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This MLS-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the MLS-C01 exam.