Which term describes data issues where extreme values distort results?

Which term describes data issues where extreme values distort results?

• A. Outliers
• B. Informative Missingness
• C. EDA
• D. Imputation

Answer: (A)

Extreme values that lie far from the rest of the data are called outliers. They can distort results because they pull summary statistics away from where most observations cluster. For instance, a single unusually high value can raise the mean, while a few extreme points can inflate the variance or alter the strength and direction of relationships in a model. This is why recognizing and addressing outliers matters: they may be genuine rare events, data entry errors, or indicate a need for a different modeling approach (like robust methods or data transformations) to avoid misleading conclusions. Informative missingness describes a situation where the fact that data are missing provides information about the value that would have been observed, rather than about extreme values themselves. Exploratory Data Analysis is a set of techniques for exploring data and uncovering patterns, not a term for data distortions caused by extremes. Imputation is the act of filling in missing values, which is another data handling step rather than the specific issue of extreme values distorting results.

Extreme values that lie far from the rest of the data are called outliers. They can distort results because they pull summary statistics away from where most observations cluster. For instance, a single unusually high value can raise the mean, while a few extreme points can inflate the variance or alter the strength and direction of relationships in a model. This is why recognizing and addressing outliers matters: they may be genuine rare events, data entry errors, or indicate a need for a different modeling approach (like robust methods or data transformations) to avoid misleading conclusions.

Informative missingness describes a situation where the fact that data are missing provides information about the value that would have been observed, rather than about extreme values themselves. Exploratory Data Analysis is a set of techniques for exploring data and uncovering patterns, not a term for data distortions caused by extremes. Imputation is the act of filling in missing values, which is another data handling step rather than the specific issue of extreme values distorting results.