Data-Driven-Decision-Making Exam Study Guide: The Ultimate 2026 Practice Test

A z-score standardizes a value by expressing how many standard deviations it lies from the mean. A fundamental assumption of z-score analysis in data-driven decision making is that the data can be transformed to a standard normal distribution with a mean of zero and a standard deviation of one.

This transformation allows analysts to compare values from different distributions on a common scale and to calculate probabilities using the standard normal table. The formula for a z-score subtracts the mean from the observed value and divides by the standard deviation, resulting in this standardized distribution.

Outliers are not eliminated by default in z-score calculations; instead, z-scores are often used to identify outliers. A standard deviation of 2 is incorrect and would not represent a standardized distribution.

Therefore, the correct answer is A, reflecting the core assumption underlying z-score usage.

Big data includes both structured and unstructured data. Structured data are organized in predefined formats such as rows and columns in databases, spreadsheets, or transaction systems. Unstructured data include forms such as emails, videos, social media content, images, audio files, sensor outputs, and free-text documents that do not fit neatly into traditional tabular formats. One of the defining features of big data is not just its size, but also its variety. This variety means organizations must work with multiple data types and sources to generate useful insights. The other options do not define what big data includes. Spreadsheets may handle small portions of data, but they do not define the concept itself. Powerful extraction tools may be used in big data environments, but they are tools rather than components of the data. Inferential statistics are analytical methods, not the data itself. Therefore, the best answer is that big data includes both structured and unstructured data.

Starting an analysis with flawed data significantly undermines the effectiveness of data-driven decision making. One major consequence is that more time is spent managing data than analyzing data. Analysts must devote substantial effort to cleaning, validating, and correcting errors before meaningful analysis can occur, delaying insights and increasing costs.

Another critical result is that missing data tend to skew the results of the analysis. Incomplete data can distort averages, trends, and statistical relationships, leading to biased conclusions and unreliable decisions. This is especially problematic in predictive and inferential analytics, where assumptions about data completeness are essential.

Using spreadsheets or placing data in charts does not inherently result from flawed data, nor does it resolve data quality issues. While visualization can help identify errors, it is not a direct outcome of starting with flawed data.

Data-driven decision making emphasizes that poor-quality input leads to poor-quality output. Ensuring data accuracy and completeness before analysis is essential for producing valid insights. Therefore, the correct answers are B and D.