Question

    Which data cleaning technique is most appropriate for handling missing data when missing values are randomly distributed across a dataset?

    A Removing rows with missing data Correct Answer Incorrect Answer
    B Replacing missing values with the mean or median Correct Answer Incorrect Answer
    C Dropping columns with missing values Correct Answer Incorrect Answer
    D Using placeholder values (like zero or -1) for missing data Correct Answer Incorrect Answer
    E Ignoring the missing values altogether Correct Answer Incorrect Answer

    Solution

    When missing data points are randomly distributed, imputing values using the mean (for continuous data) or median (for skewed distributions) can be an effective technique. This approach maintains the dataset’s overall structure and helps reduce potential bias introduced by missing values. By substituting missing values with central tendencies, analysts can preserve statistical relationships without significantly distorting the data, ensuring a more accurate analysis. Option A is incorrect as removing rows may lead to a significant data loss, especially if many rows contain missing values. Option C is incorrect because dropping columns with missing values reduces feature dimensions, potentially discarding useful information. Option D is incorrect as placeholder values can introduce bias or mislead analysis, especially if the placeholder value skews the distribution. Option E is incorrect because ignoring missing values leaves gaps, making it difficult to perform accurate analysis.

    Practice Next