Study 3 Descriptive Analytics and Exploratory Analysis with 12 free online flashcards. Review key terms, definitions, and concepts with this interactive flashcard deck.
What can exploratory data analysis reveal—and what can it not prove?
Exploratory data analysis uses summaries and visuals to reveal patterns, unusual observations, and useful questions. It does not by itself establish causes or prove that a pattern will continue.
Why identify a dataset’s unit of observation before summarizing it?
The unit of observation is what each row represents, such as a transaction, customer, or store-day. Establishing it helps prevent invalid totals and comparisons.
Why shouldn’t missing values automatically be replaced with zero?
Do not automatically replace missing values with zero: “not recorded” and “none” have different meanings.
How is the mean calculated, and what can pull it toward the tail?
The mean is the sum of all values divided by the number of observations. Because it uses every value, unusually high or low values can pull it toward the tail.
What is the median, and why can it represent a typical value better than the mean?
The median is the middle value after sorting the observations. It is less affected by extreme values than the mean.
What does the interquartile range measure?
The interquartile range is the difference between the third and first quartiles: IQR=Q3−Q1. It describes the spread of the middle half of the data.
What does standard deviation summarize, and what can make it sensitive?
Standard deviation summarizes how far values tend to lie from the mean. It uses the same units as the data and can be sensitive to extreme values.
What should accompany a category proportion to make it informative?
Counts give the number of observations in a category; proportions give their share of the total. Report the denominator and time period so the share is interpretable.
What is a histogram useful for exploring?
A histogram groups numeric observations into intervals. Inspect it for center, spread, skew, multiple peaks, or possible outliers.
Which display helps reveal trends and recurring patterns over time?
A line chart helps explore how a measure changes over time, including trends, recurring patterns, abrupt changes, and gaps.
What can side-by-side box plots reveal when comparing groups?
Side-by-side box plots compactly compare group medians, middle-half spread, overlap, and unusual values.
What can a scatter plot show, and what does an association not establish?
A scatter plot can show the direction, form, and strength of an association between two numeric measures. Association alone does not establish cause and effect.