Top 100 Vocabulary for Adults | Data & Analytics Professionals
Data and analytics vocabulary is the language of turning observations into decisions. Professionals must distinguish signal from noise, correlation from causation, measurement from meaning, and a beautiful dashboard from an analysis that actually changes what someone should do.
This profession-specific flagship belongs to the eduKate Adult Vocabulary for Professionals system. It complements Scientists & Researchers, AI & Machine Learning Professionals and Decision-Making & Judgement.
The Four Banks
Data & Measurement: data, dataset, record, field, variable, observation, measure, metric, dimension, categorical, numerical, continuous, discrete, missing value, outlier, duplicate, schema, source, lineage, metadata, grain, aggregation, sampling, population, denominator.
Statistics & Inference: mean, median, variance, standard deviation, distribution, percentile, probability, confidence interval, hypothesis, null hypothesis, significance, p-value, effect size, correlation, causation, confounder, bias, randomisation, control group, treatment group, regression, prediction, residual, uncertainty, inference.
Analysis & Visualisation: analysis, segmentation, cohort, funnel, conversion, retention, churn, trend, seasonality, benchmark, baseline, anomaly, diagnostic analysis, descriptive analysis, predictive analysis, prescriptive analysis, dashboard, chart, visualisation, filter, drill-down, comparison, narrative, insight, recommendation.
Data Operations & Decision Support: pipeline, ETL, ELT, warehouse, lake, transformation, query, SQL, join, model, refresh, latency, data quality, validation, reconciliation, governance, access, privacy, documentation, reproducibility, experiment, A/B test, decision support, stakeholder, actionability.
Top 100 Data & Analytics Vocabulary: Working Meanings
| # | Word | Professional meaning |
|---|---|---|
| 1 | Data | Recorded observations used for analysis or decision-making. |
| 2 | Dataset | A structured collection of related data. |
| 3 | Record | One row or unit of observed information. |
| 4 | Field | A defined attribute within a record. |
| 5 | Variable | A characteristic that can take different values. |
| 6 | Observation | One measured or recorded instance. |
| 7 | Measure | A quantified representation of a concept or outcome. |
| 8 | Metric | A defined quantitative measure used to track performance or behaviour. |
| 9 | Dimension | A categorical attribute used to group or slice measures. |
| 10 | Categorical | Representing membership in defined groups or labels. |
| 11 | Numerical | Representing quantities with numbers. |
| 12 | Continuous | A variable capable of taking any value within a range. |
| 13 | Discrete | A variable taking separate countable values. |
| 14 | Missing value | An expected data point that is absent or unknown. |
| 15 | Outlier | An observation unusually distant from the rest of the data. |
| 16 | Duplicate | A repeated record representing the same underlying entity or event. |
| 17 | Schema | The defined structure and relationships of stored data. |
| 18 | Source | The system or process from which data originates. |
| 19 | Lineage | The documented path showing where data came from and how it changed. |
| 20 | Metadata | Information describing data, such as definition, source or format. |
| 21 | Grain | The level of detail represented by one row or observation. |
| 22 | Aggregation | Combining detailed observations into summaries. |
| 23 | Sampling | Selecting a subset of a population for analysis. |
| 24 | Population | The full group about which an analysis seeks to make conclusions. |
| 25 | Denominator | The base quantity used in calculating rates or proportions. |
| 26 | Mean | The arithmetic average of values. |
| 27 | Median | The middle value when observations are ordered. |
| 28 | Variance | A measure of spread around the mean. |
| 29 | Standard deviation | A measure describing typical distance from the mean. |
| 30 | Distribution | The pattern of values across a dataset. |
| 31 | Percentile | A value below which a specified percentage of observations falls. |
| 32 | Probability | A numerical representation of likelihood. |
| 33 | Confidence interval | An interval estimate describing uncertainty around a parameter under specified assumptions. |
| 34 | Hypothesis | A testable proposition about a relationship or effect. |
| 35 | Null hypothesis | A default hypothesis commonly representing no effect or difference. |
| 36 | Significance | A statistical judgement about compatibility of data with a null model under specified assumptions. |
| 37 | P-value | The probability, under a specified null model, of observing data at least as extreme as the result obtained. |
| 38 | Effect size | The magnitude of a difference or relationship. |
| 39 | Correlation | A statistical relationship between variables. |
| 40 | Causation | A relationship in which one factor contributes to producing another outcome. |
| 41 | Confounder | A variable associated with both exposure and outcome that can distort an observed relationship. |
| 42 | Bias | A systematic distortion in measurement, sampling or analysis. |
| 43 | Randomisation | Assignment by chance to reduce systematic differences between groups. |
| 44 | Control group | A comparison group not receiving the intervention of interest. |
| 45 | Treatment group | A group receiving the intervention being evaluated. |
| 46 | Regression | A statistical method modelling relationships between variables. |
| 47 | Prediction | An estimate of an unknown or future value. |
| 48 | Residual | The difference between observed and model-predicted values. |
| 49 | Uncertainty | Incomplete knowledge about estimates or conclusions. |
| 50 | Inference | Drawing conclusions beyond directly observed data. |
| 51 | Analysis | Structured examination of data to answer a question. |
| 52 | Segmentation | Dividing a population into meaningful groups. |
| 53 | Cohort | A group sharing a defined starting event or characteristic. |
| 54 | Funnel | A sequence of stages through which users or events progress. |
| 55 | Conversion | Movement from one desired stage to another. |
| 56 | Retention | Continued participation or use over time. |
| 57 | Churn | Loss of users, customers or recurring activity. |
| 58 | Trend | A general direction of change over time. |
| 59 | Seasonality | Recurring variation associated with time cycles. |
| 60 | Benchmark | A reference point used for comparison. |
| 61 | Baseline | The starting condition used to assess change. |
| 62 | Anomaly | An observation or pattern that differs materially from expectation. |
| 63 | Diagnostic analysis | Analysis focused on why an outcome occurred. |
| 64 | Descriptive analysis | Analysis summarising what happened. |
| 65 | Predictive analysis | Analysis estimating what is likely to happen. |
| 66 | Prescriptive analysis | Analysis suggesting actions under stated objectives and constraints. |
| 67 | Dashboard | A visual display of selected measures and status. |
| 68 | Chart | A graphical representation of data. |
| 69 | Visualisation | Use of visual form to make data patterns understandable. |
| 70 | Filter | A condition restricting which data is included. |
| 71 | Drill-down | Movement from summary data to finer levels of detail. |
| 72 | Comparison | Assessment of differences across groups, periods or benchmarks. |
| 73 | Narrative | A structured explanation connecting findings into meaning. |
| 74 | Insight | A useful interpretation that changes understanding of the problem. |
| 75 | Recommendation | A proposed action supported by analysis and context. |
| 76 | Pipeline | A sequence of automated data-processing stages. |
| 77 | ETL | Extract, transform, load: moving and preparing data before storage in a target system. |
| 78 | ELT | Extract, load, transform: loading data before transformation in the target environment. |
| 79 | Warehouse | A structured analytical data store designed for reporting and analysis. |
| 80 | Lake | A storage environment holding large volumes of raw or semi-structured data. |
| 81 | Transformation | Changing data structure, format or values for analysis. |
| 82 | Query | A request to retrieve or manipulate data. |
| 83 | SQL | A language commonly used to query relational databases. |
| 84 | Join | An operation combining records from datasets based on related fields. |
| 85 | Model | A structured representation used to describe, estimate or predict. |
| 86 | Refresh | Updating analytical data with newer source information. |
| 87 | Latency | The delay between real-world events and data becoming available. |
| 88 | Data quality | The degree to which data is accurate, complete, timely and fit for purpose. |
| 89 | Validation | Checking that data or analysis satisfies intended requirements. |
| 90 | Reconciliation | Comparison of sources or totals to identify discrepancies. |
| 91 | Governance | The structure of ownership, standards and accountability for data. |
| 92 | Access | Permission to retrieve or use data. |
| 93 | Privacy | Appropriate collection, use and protection of personal information. |
| 94 | Documentation | Recorded definitions, assumptions, methods and lineage. |
| 95 | Reproducibility | The ability to obtain consistent analytical results using documented methods and data. |
| 96 | Experiment | A structured test designed to estimate the effect of an intervention. |
| 97 | A/B test | A controlled experiment comparing two variants. |
| 98 | Decision support | Analysis designed to improve a specific decision. |
| 99 | Stakeholder | A person or group using, influencing or affected by analysis. |
| 100 | Actionability | The degree to which an analysis can support a concrete decision or action. |
A Metric Is a Model of Reality
Every metric compresses a richer world. “Active user,” “conversion,” “quality,” and “retention” depend on definitions. Good analysts inspect the definition before interpreting the number.
Scenario: Revenue Rose After a Campaign
That sequence does not prove causation. Check seasonality, customer mix, pricing, other campaigns, market changes and whether a suitable comparison group exists. The business question is not merely whether two things moved together, but how much incremental effect the intervention produced.
Seven-Day Data & Analytics Vocabulary Plan
| Day | Practice |
|---|---|
| 1 | Define metric, dimension, grain and denominator. |
| 2 | Separate mean, median, variance and distribution. |
| 3 | Practise correlation, confounding and causation distinctions. |
| 4 | Build one funnel or cohort analysis. |
| 5 | Audit a dashboard for definitions and actionability. |
| 6 | Recall 75+ analytics terms by function. |
| 7 | Write a one-page analytical brief with evidence, uncertainty and recommendation. |
Continue the Digital Profession Wing
- Cybersecurity Professionals
- AI & Machine Learning Professionals
- Product Management Professionals
- Decision-Making & Judgement
Conclusion
Data and analytics vocabulary turns numbers into disciplined questions. It helps professionals see where the measurement came from, what uncertainty remains, what comparison is valid and whether the result is useful enough to change a decision.