Data Literacy and Data Science
What this domain tests
Data Literacy and Data Science checks whether you can read data critically: identify data types, judge quality, choose summary statistics and select a visualization that does not mislead. Expect short calculations and interpretation.
Core rules and concepts
- Data are raw records; information is data processed into meaning.
- Structured data fit rows and columns; unstructured data include free text, images and audio.
- Measurement scales matter: nominal labels have no order; ordinal data are ordered but gaps are not equal; interval data have equal gaps but no true zero; ratio data have a true zero.
- The data lifecycle runs from collection and cleaning through analysis, visualization, storage and reuse.
- Quality dimensions include accuracy, completeness, consistency, timeliness and validity.
- Mean, median and mode describe centre; range and standard deviation describe spread.
- Choose charts by task: bars for categories, histograms for distributions, line charts for trends, scatter plots for relationships.
Worked example
Five test scores are 40, 42, 45, 47 and 100. The mean is (40+42+45+47+100)/5 = 274/5 = 54.8. The median is 45 because it is the middle value when sorted. The 100 is an outlier that pulls the mean upward, so the median represents a typical score better. Reporting only the mean would overstate typical performance.
Traps that cost marks
Do not use a mean for skewed data without comment. Do not treat ordinal labels as equal intervals. Do not infer causation from correlation. Do not ignore truncated axes or a cleaned dataset that silently dropped failures.