CompTIA Data+: key terms

Flashcards for this exam CompTIA Data+ guide Class dates

• Accessible VisualizationDesigning charts that people with disabilities, including color-vision deficiency and screen-reader users, can perceive and understand.Intermediate
• Accumulating Snapshot Fact TableA fact table with one row per process instance, such as an order, that is updated as the process passes milestones.Advanced
• ACIDThe four properties of reliable transactions: Atomicity, Consistency, Isolation and Durability.Foundational
• Additive MeasureA fact that can be summed meaningfully across every dimension, such as sales amount or quantity.Intermediate
• Aggregate FunctionA function that computes one value from a set of rows, such as SUM, AVG, COUNT, MIN, MAX, STDDEV or LISTAGG.Foundational
• ALTER TABLE StatementThe DDL statement that changes an existing table's structure, such as adding, dropping or modifying columns and constraints.Foundational
• Alternative Hypothesis (H1)The claim that there is an effect or difference, accepted when the null hypothesis is rejected.Foundational
• Analysis of Variance (ANOVA)A test of whether the means of three or more groups differ, by comparing between-group variance with within-group variance (the F-statistic).Intermediate
• Anti JoinA join pattern that returns rows from one table that have no match in another.Intermediate
• Apache ParquetAn open-source columnar file format with efficient compression, encoding and predicate pushdown, widely used for analytics.Intermediate
• Append QueriesA Power Query operation that stacks rows from two or more queries with the same columns, like SQL UNION ALL.Foundational
• Atomic ValueA value that cannot be meaningfully divided further for the purposes of the data model.Foundational
• AtomicityThe ACID property that a transaction completes entirely or not at all.Foundational
• AttributeA property that describes an entity, implemented as a column in a table.Foundational
• Bar ChartA chart that compares values across categories using rectangular bars whose lengths are proportional to the values.Foundational
• Batch ProcessingProcessing accumulated data in discrete scheduled jobs, such as hourly or nightly loads.Foundational
• BETWEEN OperatorA predicate that tests whether a value lies within an inclusive range: x BETWEEN a AND b means x >= a AND x <= b.Foundational
• Big DataDatasets too large, fast or varied for traditional single-server databases to store and process efficiently.Foundational
• Box PlotA chart showing a distribution's median, quartiles (the box), whiskers and outliers; also called a box-and-whisker plot.Foundational
• Bullet ChartA compact bar chart, designed by Stephen Few, that shows a measure against a target and qualitative ranges.Advanced
• Business Intelligence (BI)The technologies and practices for collecting, integrating, analyzing and presenting business data to support decision-making.Foundational
• Cardinality (Data Modeling)The number of instances of one entity that can relate to instances of another: one-to-one, one-to-many or many-to-many.Foundational
• Cartesian ProductThe set of all possible row pairings between two tables, produced by a cross join or a missing join condition.Intermediate
• CASE ExpressionSQL's conditional expression, which returns a value based on the first WHEN condition that is true.Foundational
• CAST FunctionThe ANSI SQL function that explicitly converts a value to another data type: CAST(expression AS type).Foundational
• Categorical Color PaletteA set of distinct hues for unordered categories, without implying magnitude or order.Intermediate
• Categorical DataQualitative data that place observations into groups (nominal or ordinal) rather than measuring quantities.Foundational
• Central Limit Theorem (CLT)The theorem that the distribution of sample means approaches a normal distribution as sample size grows, regardless of the population's shape.Intermediate
• Chart SelectionMatching the chart to the task: bar to compare, line for trends, histogram or box plot for distributions, scatter for relationships.Foundational
• ChartjunkUnnecessary or distracting decoration in charts, such as 3-D effects, heavy patterns or clip art, that doesn't convey data.Foundational
• Chasm TrapAn error that occurs when two fact tables are joined through a shared dimension, multiplying rows and overstating measures from both.Advanced
• Chi-Square Test (χ²)A test for categorical data: goodness of fit (observed vs expected frequencies) or independence (association between two categorical variables).Intermediate
• Choropleth MapA map that shades geographic regions by a data value.Intermediate
• Cluster SamplingDividing the population into clusters (such as schools or stores), randomly selecting whole clusters, and sampling everyone (or a sample) within them.Intermediate
• COALESCE FunctionA function that returns the first non-NULL argument in its list.Foundational
• Coefficient of Variation (CV)The standard deviation divided by the mean, often given as a percentage, used to compare variability across datasets with different scales.Intermediate
• Cohort AnalysisGrouping users by a shared starting event or period, such as signup month, and tracking their behavior over time.Intermediate
• ColumnA named attribute of a table with a defined data type that every row stores a value (or NULL) for; also called a field.Foundational
• Column AliasA temporary name given to a column or expression in a query's result using AS.Foundational
• Columnar StorageStoring each column's values together on disk rather than storing whole rows, which speeds analytic scans and improves compression.Intermediate
• COMMIT StatementThe TCL command that makes all changes in the current transaction permanent and visible to other sessions.Foundational
• Common Table Expression (CTE)A named temporary result set defined with WITH that can be referenced in the statement that follows.Intermediate
• Composite KeyA key made of two or more columns that together uniquely identify a row.Intermediate
• Conceptual Data ModelA high-level model that shows the main business entities and their relationships, without attributes or technical detail.Foundational
• Confidence Interval (CI)A range computed from sample data that, under repeated sampling, would contain the true population parameter a stated percentage of the time.Intermediate
• Conformed DimensionA dimension shared with consistent keys, attributes and meaning across multiple fact tables or data marts.Intermediate
• Confounding VariableA variable that influences both the supposed cause and the effect, creating a spurious association.Intermediate
• Consistency (ACID)The ACID property that a transaction takes the database from one valid state to another, respecting all constraints and rules.Foundational
• Continuous DataQuantitative data that can take any value within a range, such as height, time or temperature.Foundational
• Convenience SamplingA non-probability method that samples whoever is easiest to reach.Foundational
• Correlated SubqueryA subquery that references columns from the outer query and is logically evaluated once per outer row.Intermediate
• Correlation CoefficientPearson's r: a value from -1 to +1 measuring the strength and direction of a linear relationship between two numeric variables.Intermediate
• Correlation vs CausationThe principle that a statistical association between two variables does not prove that one causes the other.Foundational
• COUNT FunctionAn aggregate that counts rows: COUNT(*) counts every row, COUNT(col) counts non-null values, COUNT(DISTINCT col) counts unique non-null values.Foundational
• CREATE TABLE StatementThe DDL statement that defines a new table with its columns, data types and constraints.Foundational
• CRISP-DMCross-Industry Standard Process for Data Mining: six iterative phases from business understanding through data prep, modeling, evaluation and deployment.Intermediate
• CROSS JOINA join with no condition that returns every combination of rows from both tables (the Cartesian product).Intermediate
• Crow's Foot NotationAn ERD notation that uses symbols at line ends to show cardinality: a three-pronged 'crow's foot' for many, a bar for one and a circle for zero.Intermediate
• Dashboard (Data Visualization)A visual display of the most important information needed to achieve objectives, arranged on a single screen for at-a-glance monitoring.Foundational
• Data AccuracyThe data quality dimension measuring how well data values reflect the real-world entities or events they describe.Foundational
• Data Analysis ProcessA structured analytics workflow; the Google Data Analytics certificate's six phases are Ask, Prepare, Process, Analyze, Share and Act.Foundational
• Data AnomaliesInsert, update and delete anomalies: integrity problems caused by redundant data in unnormalized tables.Intermediate
• Data ArchivingMoving data that is no longer actively used to lower-cost, long-term storage while keeping it retrievable for compliance or reference.Foundational
• Data CleansingDetecting and correcting or removing inaccurate, incomplete, duplicate or improperly formatted data.Foundational
• Data CompletenessThe data quality dimension measuring whether all required data values and records are present.Foundational
• Data ConsistencyThe data quality dimension measuring whether the same data agrees across records, systems and time.Foundational
• Data Control Language (DCL)The SQL commands that manage permissions: GRANT, REVOKE and, in SQL Server, DENY.Foundational
• Data Definition Language (DDL)The SQL commands that define and change database structure: CREATE, ALTER, DROP, TRUNCATE and RENAME.Foundational
• Data DemocratizationMaking data accessible to non-technical users across an organization, with appropriate governance.Foundational
• Data DictionaryA repository of metadata describing each table, column, data type, constraint and meaning in a database.Foundational
• Data FederationRunning a single query across multiple independent databases and returning combined results.Intermediate
• Data FreshnessHow recently data was updated relative to expectations, usually monitored as the time since the last successful load.Intermediate
• Data GovernanceThe framework of policies, roles, standards, processes and controls that ensures data is managed as an asset: secure, high quality, compliant and usable.Foundational
• Data IngestionThe process of importing data from sources into a storage or processing platform, in batches or as a stream.Foundational
• Data LakeA central repository that stores large volumes of raw data in any format (structured, semi-structured or unstructured) cheaply, usually in object storage.Foundational
• Data Lifecycle Management (DLM)Managing data from creation and storage through use, sharing, archiving and secure deletion according to policy.Intermediate
• Data LiteracyThe ability to read, work with, analyze and communicate with data.Foundational
• Data Manipulation Language (SQL) (DML)The SQL commands that add, change or remove rows: INSERT, UPDATE, DELETE and MERGE (and, in some classifications, SELECT).Foundational
• Data MartA subset of a data warehouse focused on one business area or department, such as sales or finance.Foundational
• Data ParsingBreaking a string or semi-structured value into components, such as splitting a full address into street, city and postal code.Foundational
• Data PipelineAn automated series of steps that moves data from sources through transformations to destinations.Foundational
• Data ProfilingExamining data to summarize its structure, content, completeness, distributions, patterns and anomalies before using it.Foundational
• Data ProvenanceThe documented origin and history of data, including where it came from, who created or changed it, and how.Intermediate
• Data Quality (DQ)The degree to which data is fit for its intended use, judged on dimensions such as accuracy, completeness, consistency, timeliness, validity and uniqueness.Foundational
• Data Quality DimensionsMeasurable aspects of data quality: accuracy, completeness, consistency, timeliness, validity and uniqueness.Foundational
• Data Query Language (DQL)The SQL sublanguage for retrieving data, consisting essentially of the SELECT statement.Foundational
• Data SiloData isolated within one department or system and not accessible or integrated with the rest of the organization.Foundational
• Data StandardizationConverting data into a consistent format and set of codes, such as ISO dates, country codes, units and naming conventions.Foundational
• Data StorytellingCommunicating insights by combining data, visuals and narrative tailored to an audience to drive understanding and action.Foundational
• Data SwampA data lake that has become unusable because of missing metadata, governance and quality controls.Foundational
• Data TimelinessThe data quality dimension measuring whether data is available and current enough for its intended use.Foundational
• Data TransformationConverting data from one structure, format or value set to another, by filtering, joining, aggregating, pivoting, deriving or recoding.Foundational
• Data UniquenessThe data quality dimension measuring whether each real-world entity is recorded only once.Foundational
• Data ValidityThe data quality dimension measuring whether values conform to defined formats, types, ranges and business rules.Foundational
• Data VirtualizationQuerying data in place across multiple sources through a unified layer, without physically copying it.Intermediate
• Data VisualizationRepresenting data graphically so that patterns, trends, comparisons and outliers can be understood quickly.Foundational
• Data Warehouse (DW)A central repository of integrated, cleaned, historical data from multiple sources, structured for analytics and reporting.Foundational
• Data WranglingThe overall process of discovering, structuring, cleaning, enriching and validating raw data into an analysis-ready form; also called data munging.Foundational
• Data-Ink RatioEdward Tufte's principle that the share of a graphic's ink devoted to data should be maximized and non-data ink minimized.Intermediate
• Database IndexA data structure that speeds up row lookups on one or more columns at the cost of extra storage and slower writes.Foundational
• Database NormalizationThe process of organizing tables to reduce redundancy and prevent update anomalies by applying normal forms.Foundational
• Database SchemaThe structure of a database (its tables, columns, types, keys and relationships), or a named namespace that groups database objects.Foundational
• Database TableThe core relational storage object: a named set of rows sharing the same columns; formally called a relation.Foundational
• Database TransactionA logical unit of work of one or more operations that must succeed or fail as a whole.Foundational
• Date DimensionA dimension with one row per calendar date and attributes such as year, quarter, month, weekday, fiscal period and holiday flag.Foundational
• Degenerate DimensionA dimension key, such as an order or invoice number, stored in the fact table with no separate dimension table.Advanced
• DELETE StatementThe DML statement that removes rows that match a condition from a table, logging each row.Foundational
• Delimited Text FileA plain-text file, such as CSV or TSV, in which fields are separated by a delimiter and records by line breaks.Foundational
• DenormalizationIntentionally adding redundancy, for example by merging tables or duplicating columns, to speed reads and simplify queries.Intermediate
• Derived TableA subquery in the FROM clause that acts as a temporary inline table, which must have an alias.Intermediate
• Descriptive AnalyticsAnalytics that answers 'what happened?' by summarizing historical data through reports, dashboards and KPIs.Foundational
• Descriptive StatisticsStatistics that summarize and describe the features of a dataset, such as its center, spread and shape, without generalizing beyond it.Foundational
• Diagnostic AnalyticsAnalytics that answers 'why did it happen?' through drill-down, correlation, segmentation and root-cause analysis.Foundational
• Dimension TableA table of descriptive attributes (who, what, where, when) used to filter, group and label facts.Foundational
• Dimensional ModelingA data modeling technique that organizes analytic data into facts (measurable events) and dimensions (descriptive context).Intermediate
• Discrete DataQuantitative data that take countable values, usually integers, such as number of orders or defects.Foundational
• DISTINCT KeywordA SELECT modifier that removes duplicate rows from the result.Foundational
• Diverging Color PaletteA two-hue color scale with a neutral midpoint, used for data that deviates above and below a meaningful center such as zero or a target.Intermediate
• Document DatabaseA NoSQL database that stores self-describing documents (JSON or BSON) whose structure can vary from document to document.Foundational
• Drill-DownNavigating from summarized data to a more detailed level along a hierarchy, such as Year to Quarter to Month.Foundational
• Drill-ThroughNavigating from a summary value to a separate detail page or report, filtered to the selected context.Intermediate
• DROP StatementThe DDL command that permanently removes a database object, such as a table, view, index or schema, together with its data.Foundational
• Duplicate Record DetectionIdentifying records that represent the same entity, through exact key matches or fuzzy matching of attributes.Intermediate
• DurabilityThe ACID property that committed changes persist even after a crash or power loss.Foundational
• Empirical RuleThe 68-95-99.7 rule: in a normal distribution about 68%, 95% and 99.7% of values lie within 1, 2 and 3 standard deviations of the mean.Foundational
• Enterprise Data Warehouse (EDW)An organization-wide data warehouse that integrates data across all business areas to serve as a single source for analytics.Intermediate
• EntityA person, place, thing, event or concept about which data is stored; it usually becomes a table.Foundational
• Entity ResolutionDetermining when records from one or many sources refer to the same real-world entity and linking or merging them.Advanced
• Entity-Relationship Diagram (ERD)A diagram that shows entities, their attributes and the relationships between them, used to design databases.Foundational
• EXCEPT OperatorA set operator that returns distinct rows from the first query that are not in the second; Oracle calls it MINUS.Intermediate
• EXISTS OperatorA predicate that returns true if a subquery returns at least one row.Intermediate
• Exploratory Data Analysis (EDA)An open-ended investigation of a dataset with summary statistics and visualizations to understand structure, spot anomalies and form hypotheses.Foundational
• Extract, Load, Transform (ELT)A pattern that loads raw data into the target platform first and transforms it there using the platform's own compute.Foundational
• Extract, Transform, Load (ETL)A data integration process that extracts data from sources, transforms it in a separate engine, then loads it into a target such as a warehouse.Foundational
• Fact TableThe central table in a star schema that stores numeric measurements of business events plus foreign keys to dimensions.Foundational
• Factless Fact TableA fact table with dimension keys but no numeric measures, recording that an event or coverage relationship occurred.Advanced
• Fan TrapA modeling or join error in which joining tables at different grains duplicates rows and inflates aggregated totals.Advanced
• First Normal Form (1NF)A table is in 1NF when every column holds atomic (single) values, there are no repeating groups, and each row is unique.Foundational
• Five Vs of Big DataThe characteristics of big data: Volume, Velocity, Variety, Veracity and Value.Foundational
• Five-Number SummaryA distribution summary consisting of the minimum, Q1, median, Q3 and maximum.Foundational
• Foreign Key (FK)A column in one table that references the primary or unique key of another table, enforcing a relationship between them.Foundational
• Full LoadReloading an entire dataset each run, typically by truncating and repopulating the target.Foundational
• FULL OUTER JOINA join that returns all rows from both tables, matching where possible and filling NULLs on whichever side has no match.Intermediate
• Funnel AnalysisMeasuring how users progress through sequential steps toward a goal and where they drop off.Intermediate
• Funnel ChartA chart of stages in a sequential process showing decreasing values, used for conversion pipelines.Foundational
• Galaxy SchemaA model with multiple fact tables that share conformed dimension tables; also called a fact constellation.Intermediate
• GrainThe level of detail one row of a fact table represents, such as one line item per order or one balance per account per day.Intermediate
• GROUP BY ClauseThe clause that groups rows sharing the same values so that aggregate functions return one row per group.Foundational
• Half-Open Date RangeA date filter written as >= start AND < end, which includes the start and excludes the end so datetime values are captured correctly.Intermediate
• HAVING ClauseThe clause that filters groups after GROUP BY, typically using aggregate conditions.Foundational
• Heat MapA matrix visualization in which cell color intensity encodes values, revealing patterns across two dimensions.Foundational
• Hypothesis TestingA statistical procedure for deciding whether sample evidence is strong enough to reject a null hypothesis about a population.Intermediate
• IN OperatorA predicate that tests whether a value matches any value in a list or subquery.Foundational
• Incremental LoadLoading only data that is new or changed since the last run, instead of reloading everything.Intermediate
• Inferential StatisticsUsing sample data to draw conclusions or make predictions about a larger population, with quantified uncertainty.Foundational
• Inmon MethodologyBill Inmon's top-down approach that builds a normalized (3NF) enterprise data warehouse first, then derives dimensional data marts.Intermediate
• INNER JOINA join that returns only rows with matching values in both tables.Foundational
• INSERT StatementThe DML statement that adds new rows to a table, from literal values or from a SELECT.Foundational
• Interquartile Range (IQR)The spread of the middle 50% of data: the third quartile minus the first quartile (Q3 - Q1).Foundational
• INTERSECT OperatorA set operator that returns only the distinct rows present in both query results.Intermediate
• Isolation (ACID)The ACID property that concurrent transactions do not see each other's intermediate, uncommitted changes.Foundational
• JSON DocumentA self-describing record in JavaScript Object Notation made of key-value pairs, arrays and nested objects.Foundational
• Junction TableAn associative table that resolves a many-to-many relationship by holding foreign keys to both related tables.Intermediate
• Junk DimensionA dimension that combines miscellaneous low-cardinality flags and indicators into one table to avoid cluttering the fact table.Advanced
• Key-Value StoreA NoSQL database that stores data as unique keys mapped to opaque values, optimized for fast lookups by key.Foundational
• Kimball MethodologyRalph Kimball's bottom-up approach that builds a data warehouse from dimensional star schemas linked by conformed dimensions.Intermediate
• KPI CardA visual that displays a key metric's current value, often against a target and with trend or status indicators.Foundational
• LAG and LEAD FunctionsWindow functions that return a value from a previous row (LAG) or a following row (LEAD) within a partition.Intermediate
• Late-Arriving DataRecords that arrive after the window or batch for their event time has already been processed.Advanced
• LEFT OUTER JOINA join that returns every row from the left table plus matching rows from the right, with NULLs where no match exists.Foundational
• Levels of MeasurementThe four scales of data: nominal (labels), ordinal (ordered categories), interval (equal spacing, no true zero) and ratio (equal spacing with a true zero).Foundational
• LIKE OperatorA predicate that matches strings against a pattern using wildcards: % for any sequence and _ for a single character.Foundational
• LIMIT ClauseA clause that restricts how many rows a query returns; the syntax varies (LIMIT, TOP, FETCH FIRST n ROWS ONLY).Foundational
• Line ChartA chart that connects data points with lines to show trends over a continuous dimension, usually time.Foundational
• Logical Data ModelA detailed, technology-independent model that defines entities, attributes, keys, relationships and normalization.Intermediate
• Many-to-Many Relationship (Database) (M:N)A relationship where many rows in one table relate to many rows in another; it is resolved with a junction table.Intermediate
• Margin of Error (MOE)Half the width of a confidence interval: the critical value multiplied by the standard error.Foundational
• Master DataCore, relatively stable business entities shared across processes, such as customers, products, employees and locations.Foundational
• MeanThe arithmetic average: the sum of values divided by the number of values.Foundational
• Measures of Central TendencySingle values that describe the center of a distribution: mean, median and mode.Foundational
• MedianThe middle value of ordered data, or the average of the two middle values when the count is even.Foundational
• Merge QueriesA Power Query operation that joins two queries horizontally on matching columns, like a SQL join.Foundational
• MetadataData about data: technical (schemas, types), business (definitions, owners) and operational (load times, lineage, usage) information.Foundational
• Misleading VisualizationA chart that distorts the data's message through truncated or inconsistent axes, inappropriate scales, cherry-picked ranges or area distortion.Foundational
• ModeThe most frequently occurring value in a dataset; there may be none, one (unimodal) or several (multimodal).Foundational
• Moving AverageThe average of the most recent n periods, recalculated each period to smooth short-term fluctuations and reveal trends.Foundational
• Multiple Linear RegressionA regression model that predicts a numeric outcome from two or more predictors: y = β0 + β1x1 + ... + βkxk + ε.Intermediate
• Natural KeyA key made from real-world business data that is already unique, such as an ISBN, VIN or email address; also called a business key.Intermediate
• Non-Additive MeasureA fact that cannot be summed across any dimension, such as percentages, ratios or unit prices.Intermediate
• Normal DistributionA symmetric, bell-shaped continuous probability distribution fully described by its mean and standard deviation.Foundational
• NoSQL DatabaseA non-relational database that stores data as key-value pairs, documents, wide columns or graphs, usually with a flexible schema.Foundational
• NOT EXISTSA predicate that is true when a correlated subquery returns no rows; the NULL-safe way to write an anti join.Intermediate
• NOT NULL ConstraintA constraint requiring that a column always contains a value.Foundational
• NULLA marker meaning a value is missing or unknown; it is not zero, an empty string or false.Foundational
• Null Hypothesis (H0)The default assumption of no effect, no difference or no relationship, which a test tries to find evidence against.Foundational
• OLAP CubeA multidimensional data structure that precomputes measures across dimensions for fast slicing and aggregation.Intermediate
• One-to-Many Relationship (1:N)A relationship where one row in a parent table can relate to many rows in a child table, but each child relates to one parent.Foundational
• One-to-One Relationship (1:1)A relationship where each row in one table matches at most one row in another.Intermediate
• Online Analytical Processing (OLAP)Systems optimized for complex, read-heavy queries that aggregate large volumes of historical data for analysis.Foundational
• Online Transaction Processing (OLTP)Systems that handle many short, concurrent read and write transactions, such as orders, payments and bookings.Foundational
• Operational Data Store (ODS)An integrated, near-real-time store of current operational data from several systems, used for operational reporting.Intermediate
• ORDER BY ClauseThe clause that sorts the final result set by one or more expressions, ascending (default) or descending.Foundational
• Ordinal DataCategorical data with a meaningful order but unequal or unknown spacing between categories.Foundational
• Orphan RecordA child row whose foreign key points to a parent row that does not exist.Foundational
• OutlierAn observation that lies unusually far from the other values in a dataset.Foundational
• P-ValueThe probability, assuming the null hypothesis is true, of observing results at least as extreme as those in the sample.Intermediate
• Partial DependencyA dependency in which a non-key attribute depends on only part of a composite primary key.Intermediate
• PercentileThe value below which a given percentage of observations fall; the 90th percentile exceeds 90% of the values.Foundational
• Periodic Snapshot Fact TableA fact table that records the state of something at regular intervals, such as daily inventory or monthly account balances.Advanced
• Physical Data ModelThe implementation-specific model with actual tables, columns, data types, indexes, partitions and constraints for a chosen DBMS.Intermediate
• Pie ChartA circular chart divided into slices showing each category's proportion of a whole.Foundational
• Population and SampleThe population is the entire group of interest; a sample is the subset actually observed and measured.Foundational
• Power QueryMicrosoft's data connection and transformation engine, used in Power BI, Excel, Dataflows and Fabric, with a GUI that records steps as M code.Foundational
• Pre-Attentive AttributesVisual properties such as color, size, position, length and orientation that the brain processes almost instantly, before conscious attention.Intermediate
• Predictive AnalyticsAnalytics that answers 'what is likely to happen?' using statistical models and machine learning on historical data.Foundational
• Prescriptive AnalyticsAnalytics that answers 'what should we do?' by recommending actions using optimization, simulation and decision models.Intermediate
• Primary Key (PK)A column or set of columns whose values uniquely identify each row in a table; it cannot contain NULLs.Foundational
• Probability DistributionA function describing the likelihood of each possible value of a random variable.Foundational
• QuartileValues that split ordered data into four equal parts: Q1 (25th percentile), Q2 (the median) and Q3 (75th percentile).Foundational
• RangeThe difference between the maximum and minimum values, the simplest measure of spread.Foundational
• RANK and DENSE_RANKRanking window functions: RANK gives tied rows the same rank and leaves gaps; DENSE_RANK gives ties the same rank without gaps.Intermediate
• Reference DataStandardized code sets and classifications used to categorize other data, such as country codes, currency codes and status values.Foundational
• Referential IntegrityThe guarantee that every foreign key value matches an existing key in the referenced table, so no orphaned rows exist.Foundational
• Relational DatabaseA database that stores data in tables of rows and columns, linked through keys, and queried with SQL.Foundational
• Relational Database Management System (RDBMS)Software that creates, manages and queries relational databases, enforcing schemas, constraints, security and transactions.Foundational
• ResidualThe difference between an observed value and the value predicted by a model (y - ŷ).Intermediate
• RIGHT OUTER JOINA join that returns every row from the right table plus matching rows from the left, with NULLs where no match exists.Foundational
• Role-Playing DimensionA single physical dimension referenced several times by a fact table in different roles, such as Date as Order Date and Ship Date.Intermediate
• Roll-UpAggregating data to a higher, less detailed level of a hierarchy, such as City to Country; the opposite of drill-down.Foundational
• ROLLBACK StatementThe TCL command that undoes all uncommitted changes in the current transaction, or back to a savepoint.Foundational
• RowA single record in a table, holding one value (or NULL) for each column; called a tuple in relational theory.Foundational
• ROW_NUMBER FunctionA window function that assigns a unique sequential integer to rows within each partition according to the ORDER BY.Intermediate
• Running TotalA cumulative sum that adds each row's value to the total of all preceding rows in a defined order.Foundational
• Sampling BiasSystematic error that occurs when some members of a population are more likely to be sampled than others, so the sample misrepresents the population.Foundational
• Scatter PlotA chart that plots two numeric variables as points to reveal relationships, clusters and outliers.Foundational
• SCD Type 1A slowly changing dimension method that overwrites the old attribute value, keeping no history.Intermediate
• SCD Type 2A slowly changing dimension method that inserts a new row for each change, with effective dates and a current-row flag, preserving full history.Intermediate
• SCD Type 3A slowly changing dimension method that adds a column to store the previous value alongside the current one, keeping limited history.Advanced
• Schema-on-ReadApplying structure to data when it is queried, rather than enforcing a schema when it is written.Intermediate
• Schema-on-WriteValidating and structuring data to a predefined schema when it is loaded, rejecting non-conforming records.Intermediate
• SeasonalityRegular, calendar-related patterns that repeat over fixed periods, such as daily, weekly or yearly cycles.Foundational
• Second Normal Form (2NF)A table is in 2NF when it is in 1NF and every non-key column depends on the whole primary key, not part of it.Intermediate
• SELECT StatementThe SQL statement that retrieves rows and columns from one or more tables or views.Foundational
• Selection BiasBias introduced when the way subjects or data are selected relates to the outcome being studied.Intermediate
• Self JoinA join of a table to itself, using two aliases, to compare rows within the same table.Intermediate
• Self-Service BIEnabling business users to create their own reports and analyses from governed data without relying on IT for each request.Foundational
• Semi-Additive MeasureA fact that can be summed across some dimensions but not across time, such as account balances or inventory levels.Advanced
• Semi-Structured DataData with self-describing tags or keys but no rigid tabular schema, such as JSON, XML, Avro or Parquet with nested fields.Foundational
• Sequential Color PaletteA single-hue (or light-to-dark) color scale for ordered numeric data running from low to high.Intermediate
• Significance Level (α)The threshold probability α for rejecting the null hypothesis, commonly 0.05, which equals the accepted Type I error rate.Foundational
• Simple Random Sampling (SRS)A sampling method in which every member of the population has an equal chance of being selected.Foundational
• Simpson's ParadoxA phenomenon in which a trend in several groups reverses or disappears when the groups are combined.Advanced
• Single Source of Truth (SSOT)The practice of having one authoritative source for each data element or metric so that everyone uses consistent numbers.Foundational
• SkewnessA measure of a distribution's asymmetry: right (positive) skew has a long right tail, left (negative) skew a long left tail.Intermediate
• Slice and DiceOLAP operations: slicing fixes one dimension to a single value, and dicing selects a sub-cube using values from several dimensions.Foundational
• Slowly Changing Dimension (SCD)Techniques for handling changes to dimension attributes over time, such as a customer moving city.Intermediate
• Small MultiplesA grid of small charts with the same scale and axes, each showing a different subset of the data, for easy comparison.Intermediate
• Snowflake SchemaA dimensional model whose dimension tables are normalized into multiple related tables, such as Product to Subcategory to Category.Intermediate
• SparklineA small, word-sized line chart without axes that shows the trend shape alongside a number or in a table.Intermediate
• SQL Data TypesThe categories of values a column can hold: numeric (INT, DECIMAL, FLOAT), character (CHAR, VARCHAR), date/time, Boolean, binary and semi-structured.Foundational
• SQL Logical Query Processing OrderThe order in which SQL logically evaluates clauses: FROM/JOIN, WHERE, GROUP BY, HAVING, SELECT, DISTINCT, ORDER BY, then LIMIT/TOP.Intermediate
• Stacked Bar ChartA bar chart in which each bar is divided into segments showing the parts that make up the total.Foundational
• Staging Area (Data Warehousing)An intermediate storage location where extracted data lands before being cleansed, transformed and loaded into target tables.Foundational
• Standard Deviation (SD)The square root of variance, describing typical distance from the mean in the data's own units.Foundational
• Standard Error (SE)The standard deviation of a sampling distribution, usually of the mean: SE = s / √n.Intermediate
• Star SchemaA dimensional model with a central fact table joined directly to denormalized dimension tables, forming a star shape.Foundational
• Stream ProcessingContinuously processing data records as they arrive to produce near-real-time results.Intermediate
• Structured DataData organized into a fixed schema of rows and columns, such as relational tables or spreadsheets.Foundational
• Structured Query Language (SQL)The standard declarative language for defining, querying and manipulating data in relational databases.Foundational
• Student's t-TestA test comparing means (one sample against a value, or two independent groups) when the population standard deviation is unknown, using the t-distribution.Intermediate
• SubqueryA query nested inside another statement, used as a value, a list, or a derived table.Foundational
• Surrogate KeyA system-generated identifier with no business meaning, such as an auto-increment integer or GUID, used as a primary key.Intermediate
• Survivorship BiasDrawing conclusions only from entities that 'survived' a selection process while ignoring those that failed or dropped out.Intermediate
• Systematic SamplingSelecting every kth item from an ordered list after a random start.Intermediate
• Table AliasA short temporary name for a table in a query, used to qualify columns and required for self joins.Foundational
• Third Normal Form (3NF)A table is in 3NF when it is in 2NF and no non-key column depends on another non-key column (no transitive dependencies).Intermediate
• Tidy DataHadley Wickham's data structure principle: each variable is a column, each observation is a row and each type of observational unit is a table.Intermediate
• Time SeriesA sequence of observations recorded at successive points in time, often at regular intervals.Intermediate
• Top-N QueryA query that returns the N highest or lowest rows overall or per group.Intermediate
• Transaction Control Language (TCL)The SQL commands that manage transactions: BEGIN/START TRANSACTION, COMMIT, ROLLBACK and SAVEPOINT.Foundational
• Transaction Fact TableA fact table with one row per discrete event at the most atomic grain, such as each sale or each click.Intermediate
• Transitive DependencyAn indirect dependency in which a non-key attribute depends on another non-key attribute rather than directly on the key.Intermediate
• TreemapA chart that displays hierarchical part-to-whole data as nested rectangles sized by value.Intermediate
• TRUNCATE StatementA statement that quickly removes all rows from a table while keeping its structure, typically with minimal logging.Intermediate
• Truncated AxisA y-axis that does not start at zero, exaggerating differences; misleading for bar charts but sometimes acceptable for line charts if clearly labeled.Foundational
• Type I ErrorRejecting a true null hypothesis: a false positive, with probability α.Intermediate
• Type II ErrorFailing to reject a false null hypothesis: a false negative, with probability β.Intermediate
• UNION ALLA set operator that stacks the results of two queries and keeps all rows, including duplicates.Foundational
• UNION OperatorA set operator that combines the results of two queries into one set and removes duplicate rows.Foundational
• Unpivot ColumnsA Power Query transformation that turns selected columns into attribute-value row pairs, converting wide data to long format.Intermediate
• Unstructured DataData with no predefined model, such as documents, emails, images, audio and video.Foundational
• UPDATE StatementThe DML statement that modifies existing column values in rows that match a condition.Foundational
• VarianceThe average squared deviation from the mean, measuring how spread out data are; units are the square of the data's units.Intermediate
• ViewA named stored query that behaves like a virtual table; it stores no data and runs its query when referenced.Foundational
• Waterfall ChartA chart showing how an initial value is increased and decreased by sequential positive and negative contributions to reach a final value.Intermediate
• Weighted AverageAn average in which each value is multiplied by a weight reflecting its importance or frequency, divided by the sum of the weights.Foundational
• WHERE ClauseThe clause that filters individual rows before grouping, keeping only those where the condition is true.Foundational
• Wide vs Long DataTwo layouts for the same data: wide has one column per variable value (such as per month); long (tidy) has one row per observation.Intermediate
• Window FunctionA function that computes a value across a set of rows related to the current row, defined with OVER(), without collapsing them.Intermediate
• Z-ScoreThe number of standard deviations a value lies from the mean: z = (x - μ) / σ.Intermediate