Glossary – 100 “Data Analysis” Terms

Below is a glossary that includes 100 common “Data Analysis” terms and phrases in alphabetical order. Enjoy!

Term	Definition & Example
A/B Test	Comparing two variations to measure impact. Example: Two webpage layouts.
Actionable Insight	An insight that leads to a clear decision. Example: Improve onboarding experience.
Ad Hoc Analysis	One-off analysis for a specific question. Example: Investigating a sudden sales dip.
Aggregation	Summarizing data using functions like sum or average. Example: Total revenue by region.
Analytical Maturity	Organization’s capability to use data effectively. Example: Moving from descriptive to predictive analytics.
Bar Chart	A chart comparing categories. Example: Sales by region.
Baseline	A reference point for comparison. Example: Last year’s sales used as baseline.
Benchmark	A standard used to compare performance. Example: Industry average churn rate.
Bias	Systematic error in data or analysis. Example: Surveying only active users.
Business Question	A decision-focused question data aims to answer. Example: Which products drive profit?
Causation	A relationship where one variable causes another. Example: Price cuts causing sales growth.
Confidence Interval	Range likely containing a true value. Example: 95% CI for average sales.
Correlation	A statistical relationship between variables. Example: Sales and marketing spend.
Cumulative Total	A running total over time. Example: Year-to-date revenue.
Dashboard	A visual collection of key metrics. Example: Executive sales dashboard.
Data	Raw facts or measurements collected for analysis. Example: Sales transactions, sensor readings, survey responses.
Data Anomaly	Unexpected or unusual data pattern. Example: Sudden spike in user signups.
Data Cleaning	Correcting or removing inaccurate data. Example: Fixing misspelled country names.
Data Consistency	Uniform representation across datasets. Example: Same currency used everywhere.
Data Governance	Policies ensuring data quality, security, and usage. Example: Defined data ownership roles.
Data Imputation	Replacing missing values with estimated ones. Example: Filling null ages with the median.
Data Lineage	Tracking data origin and transformations. Example: Tracing metrics back to source systems.
Data Literacy	Ability to read, understand, and use data. Example: Interpreting charts correctly.
Data Model	The structure defining how data tables relate. Example: Star schema.
Data Pipeline	Automated flow of data from source to destination. Example: Daily ingestion job.
Data Profiling	Analyzing data characteristics. Example: Checking null percentages.
Data Quality	The accuracy, completeness, and reliability of data. Example: Valid dates and consistent formats.
Data Refresh	Updating data with the latest values. Example: Nightly refresh.
Data Refresh Frequency	How often data is updated. Example: Hourly vs. daily refresh.
Data Skewness	Degree of asymmetry in data distribution. Example: Income data skewed to the right.
Data Source	The origin of data. Example: SQL database, API.
Data Storytelling	Communicating insights using narrative and visuals. Example: Executive-ready presentation.
Data Transformation	Modifying data to improve usability or consistency. Example: Converting text dates to date data types.
Data Validation	Ensuring data meets rules and expectations. Example: No negative quantities.
Data Wrangling	Transforming raw data into a usable format. Example: Reshaping columns for analysis.
Dataset	A structured collection of related data. Example: A table of customer orders with dates, amounts, and regions.
Derived Metric	A metric calculated from other metrics. Example: Profit margin = Profit / Revenue.
Descriptive Analytics	Analysis that explains what happened. Example: Last quarter’s sales summary.
Diagnostic Analytics	Analysis that explains why something happened. Example: Revenue drop due to fewer customers.
Dice	Filtering data by multiple dimensions. Example: Sales for 2025 in the West region.
Dimension	A descriptive attribute used to slice data. Example: Date, region, product.
Dimension Table	A table containing descriptive attributes. Example: Product details.
Dimensionality	Number of features or variables in data. Example: High-dimensional customer data.
Distribution	How values are spread across a range. Example: Income distribution.
Drill Down	Navigating from summary to detail. Example: Yearly sales → monthly sales.
Drill Through	Jumping to a detailed view for a specific value. Example: Clicking a region to see store data.
ELT	Extract, Load, Transform approach. Example: Transforming data inside a warehouse.
ETL	Extract, Transform, Load process. Example: Loading CRM data into a warehouse.
Exploratory Data Analysis (EDA)	Initial investigation to understand data. Example: Visualizing distributions.
Fact Table	A table containing quantitative data. Example: Sales transactions.
Feature	An individual measurable property used in analysis. Example: Customer age used in churn analysis.
Feature Engineering	Creating new features from existing data. Example: Calculating customer tenure from signup date.
Filtering	Limiting data to a subset of interest. Example: Only orders from 2025.
Granularity	The level of detail in the data. Example: Daily sales vs. monthly sales.
Grouping	Organizing data into categories before aggregation. Example: Sales grouped by product category.
Histogram	A chart showing data distribution. Example: Frequency of order sizes.
Hypothesis	A testable assumption. Example: Discounts increase sales.
Incremental Load	Loading only new or changed data. Example: Yesterday’s transactions.
Insight	A meaningful finding that informs action. Example: High churn among new users.
KPI (Key Performance Indicator)	A critical metric tied to business objectives. Example: Monthly churn rate.
Kurtosis	Measure of how heavy the tails of a distribution are. Example: Detecting extreme outliers.
Latency	Delay between data generation and availability. Example: Real-time vs. daily data.
Line Chart	A chart showing trends over time. Example: Monthly revenue trend.
Mean	The arithmetic average. Example: Average order value.
Measure	A calculated numeric value, often aggregated. Example: SUM(Sales).
Median	The middle value in ordered data. Example: Median household income.
Metric	A quantifiable measure used to track performance. Example: Total sales, average order value.
Missing Values	Data points that are absent or null. Example: Blank customer age values.
Mode	The most frequent value. Example: Most common product category.
Multivariate Analysis	Analyzing multiple variables simultaneously. Example: Studying price, demand, and seasonality.
Normalization	Scaling data to a common range. Example: Normalizing values between 0 and 1.
Observation	A single record or row in a dataset. Example: One customer’s purchase history.
Outlier	A data point significantly different from others. Example: An unusually large transaction amount.
Percentile	Value below which a percentage of data falls. Example: 90th percentile response time.
Population	The full set of interest. Example: All customers.
Predictive Analytics	Analysis that forecasts future outcomes. Example: Predicting next month’s demand.
Prescriptive Analytics	Analysis that suggests actions. Example: Recommending price changes.
Quartile	Values dividing data into four parts. Example: Q1, Q2, Q3.
Report	A structured presentation of analysis results. Example: Monthly performance report.
Reproducibility	Ability to recreate analysis results consistently. Example: Using versioned datasets.
Rolling Average	An average calculated over a moving window. Example: 7-day rolling average of sales.
Root Cause Analysis	Identifying the underlying cause of an issue. Example: Revenue loss due to inventory shortages.
Sample	A subset of a population. Example: Survey respondents.
Sampling Bias	Bias introduced by non-random samples. Example: Feedback collected only from power users.
Scatter Plot	A chart showing relationships between two variables. Example: Ad spend vs. revenue.
Seasonality	Repeating patterns tied to time cycles. Example: Holiday sales spikes.
Semi-Structured Data	Data with flexible structure. Example: JSON files.
Sensitivity Analysis	Evaluating how outcomes change with inputs. Example: Impact of price changes on profit.
Slice	Filtering data by a single dimension. Example: Sales for 2025 only.
Snapshot	Data captured at a specific point in time. Example: End-of-month balances.
Snowflake Schema	A normalized version of a star schema. Example: Product broken into sub-tables.
Standard Deviation	Average distance from the mean. Example: Consistency of sales performance.
Standardization	Rescaling data to have mean 0 and standard deviation 1. Example: Preparing data for regression analysis.
Star Schema	A data model with facts surrounded by dimensions. Example: Sales fact with product and date dimensions.
Structured Data	Data with a fixed schema. Example: Relational tables.
Time Series	Data indexed by time. Example: Daily stock prices.
Trend	A general direction in data over time. Example: Increasing monthly revenue.
Unstructured Data	Data without a predefined schema. Example: Emails, images.
Variable	A characteristic or attribute that can take different values. Example: Age, revenue, product category.
Variance	Measure of data spread. Example: Variance in delivery times.