DA0-002 Data Acquisition and Preparation Practice Question
A data analyst is working with a dataset that contains a 'salary' column with extreme outliers. Before performing a linear regression analysis, the analyst wants to reduce the impact of these outliers. Which technique should be applied?
⚠ Common exam trap
The trap here is thinking that standardization or normalization reduces outlier impact, when in fact they only change the scale and do not address the extreme values themselves.
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
✓
Winsorizing
Winsorizing is the correct technique because it caps extreme values at a specified percentile, reducing their influence while retaining all data points. For linear regression, outliers can disproportionately affect the slope and intercept, so limiting their impact is crucial. Winsorizing is preferable to deletion when sample size is limited, and it preserves the order of values, making it a robust choice for this scenario.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
One-hot encoding
Why it's wrong here
One-hot encoding is used to convert categorical variables into binary vectors. It is not applicable to a continuous 'salary' column. Applying it would create numerous binary columns, which is nonsensical for numerical data and does not address outliers. Therefore, it fails to solve the problem.
- ✗
Standardization
Why it's wrong here
Standardization rescales data to have a mean of 0 and a standard deviation of 1. While it changes the scale, it does not reduce the impact of outliers; in fact, outliers remain outliers in the transformed space and can still skew regression coefficients. Thus, it does not mitigate the issue.
- ✗
Binning
Why it's wrong here
Binning converts continuous data into categorical bins, such as low, medium, high salary ranges. This loses the granularity of the salary values and is not appropriate for linear regression, which requires numerical input. Binning would distort the relationship and is not a technique for outlier mitigation in regression.
- ✓
Winsorizing
Why this is correct
Winsorizing replaces extreme values with the nearest non-extreme value, typically at a specified percentile (e.g., 5th and 95th). This reduces the influence of outliers without removing them, preserving the sample size. It is suitable for linear regression as it limits the leverage of extreme points while maintaining the data distribution's shape.
Go deeper
Related to this question
About these practice questions
This DA0-002 question is part of Courseiva's 1,004-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 →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official CompTIA exam blueprint
This DA0-002 practice question is part of Courseiva's free CompTIA 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 DA0-002 exam.