ICDL Data Analytics (ICDL) flashcards
ICDL Data Analytics · Build recall with a focused review session.
32 cards. Read the term and the definition here. The deck at the top of this page is optional.
- Descriptive analytics
- The analytics type that summarizes historical data to answer what happened, using measures such as totals, averages, trends, and dashboard summaries.
- Predictive analytics
- The analytics type that uses historical patterns and statistical models to estimate future outcomes, such as forecasts or likelihood scores.
- Prescriptive analytics
- The analytics type that recommends actions by combining predictions with rules or optimization, answering what should be done next.
- Nominal data
- A categorical data type whose values are unordered labels with no ranking, such as colors, departments, or country names.
- Ordinal data
- A categorical data type whose values have a meaningful order but unequal or undefined intervals, such as satisfaction ratings from low to high.
- Ratio data
- A numeric data type with equal intervals and a true zero, permitting meaningful ratios such as ratios of weight, revenue, or age.
- Median vs mean
- The median is the middle value and resists outliers, while the mean averages all values and shifts strongly when extreme values are present.
- Standard deviation
- A measure of average dispersion of values around the mean; a larger value indicates data points spread more widely from the center.
- Correlation coefficient
- A value from -1 to +1 describing the strength and direction of a linear relationship; zero indicates no linear relationship.
- Bar chart use
- A chart type that compares quantities across discrete categories using bars whose lengths are proportional to the values.
- Line chart use
- A chart type that displays trends of a continuous variable over time by connecting data points in chronological order.
- Scatter plot use
- A chart type that plots one variable against another to reveal relationships, clusters, and outliers between two numeric variables.
- Histogram purpose
- A chart that groups continuous numeric data into bins to show the distribution shape, such as normal, skewed, or bimodal.
- Pivot table function
- A tool that summarizes large datasets by arranging fields into rows, columns, values, and filters, aggregating without altering the source data.
- Sorting versus filtering
- Sorting reorders records by a field, while filtering hides rows that fail criteria without deleting them from the dataset.
- Outlier detection rule
- A value is flagged as an outlier if it lies beyond 1.5 times the interquartile range from the quartiles, or beyond three standard deviations.
- Misleading truncated axis
- Starting a value axis above zero exaggerates differences between bars or lines, distorting the perceived magnitude of change.
- Primary key
- A field or combination of fields that uniquely identifies each row in a relational table and cannot contain duplicate values.
- Foreign key
- A field in one table that references the primary key of another table, establishing a relationship and enforcing referential integrity.
- WHERE versus HAVING
- WHERE filters individual rows before grouping, while HAVING filters aggregated groups after GROUP BY is applied.
- SQL aggregate functions
- Functions such as SUM, COUNT, AVG, MIN, and MAX that collapse multiple rows into a single summary value per group.
- Data cleaning steps
- The process of removing duplicates, standardizing formats, handling missing values, correcting invalid entries, and validating value ranges.
- Dashboard design principle
- Place the most important KPI prominently, limit metrics per view, label axes and units, and display the data refresh date.
- Audit trail
- A recorded log of data changes showing who modified what and when, supporting traceability, accountability, and error investigation.
- Data normalization
- Organizing tables to reduce redundancy and inconsistency by separating data into related tables linked by keys.
- SMART goals
- A goal-setting rule requiring objectives to be specific, measurable, achievable, relevant, and time-bound for clear evaluation.
- KPI definition
- A key performance indicator is a measurable, time-bound metric tied to a strategic objective and actionable by its owner.
- A/B testing
- An experiment comparing a control group with a variant; statistical significance, often p below 0.05, shows the difference is unlikely due to chance.
- Confirmation bias
- A cognitive bias in which people favor information confirming existing beliefs, leading to selective use of data in decisions.
- Leading versus lagging indicators
- Leading indicators predict future outcomes and permit early action, while lagging indicators confirm results already achieved.
- Return on investment
- A profitability measure calculated as benefit minus cost, divided by cost, then multiplied by 100 to give a percentage.
- Data storytelling structure
- A sequence for communicating findings: state the question, present the evidence, interpret the result, and recommend a specific action.