Analytics & Measurement

The territory

30 core terms mapped for this field, ranked by how often builders reach for them. Each one is a future entry. Want to bust one? One entry, one file, one pull request.

• event trackinglogging named user actions with attached properties"record when someone clicks the thing" · "log what people do"
• conversion funnelordered steps measured for drop-off between each stage"where people fall off" · "the step-by-step drop chart"
• conversion ratepercentage of eligible users completing a desired action"how many actually sign up" · "what percent convert"
• user vs. session vs. pageviewperson, visit, and viewed page counted as different units"is that people or visits" · "why are visits higher than users"
• cohort analysisgrouping users by signup period, comparing behavior over time"compare people who joined in March vs April" · "the triangle chart"
• retention curvepercent of users still active N days after signup"how many come back" · "the curve that flattens or doesn't"
• North Star metricsingle number best proxying delivered customer value"the one number that matters" · "our main metric"
• attribution modelrules assigning conversion credit across touchpoints"which ad gets the credit" · "what actually caused the sale"
• UTM parametersURL query tags identifying traffic source, medium, campaign"the ?source= stuff on links" · "campaign tags in the link"
• session replayrecorded playback of a real user's screen and cursor"watch someone use my site" · "screen recording of visitors"
• heatmapcolor overlay showing where users click, move, or scroll"the red-blob click map" · "where people look"
• A/B testrandomized comparison of two variants on one metric"try two versions and see which wins" · "split test"
• statistical significanceconfidence the observed difference isn't random noise"is this result real or luck" · "enough data yet"
• event taxonomynaming and property scheme keeping events consistent"rules for naming my events" · "stop the mess of event names"
• product analyticsbehavior-level analytics inside the product, not just pages"analytics for in-app actions" · "not just pageviews"
• dimension vs. metriccategorical breakdowns versus numeric measurements used in reports"the labels vs the numbers" · "rows vs values in a report"
• activation eventfirst meaningful action proving a new user got value"when they actually start using it" · "the aha moment" · "activation"
• time to value (TTV)elapsed time from signup to first real benefit"how long before it's useful" · "time until they get something out of it"
• churn rateshare of users or revenue lost in a period"people leaving" · "how many cancel"
• funnel step conversion ratepercent advancing from one funnel stage to next"how many made it to the next step"
• identity resolution / user stitchinglinking anonymous visits to a known user after login"connect the visitor to their account later"
• dashboardfixed panel of saved charts tracking core metrics"the screen with all the numbers"
• segmentsaved filter defining a reusable subset of users"just the paying users" · "a saved group"
• DAU/WAU/MAUactive-user counts per day, week, month"how many people use it daily" · "active users"
• lifecycle stagelabeling users as new, active, dormant, resurrected, churned"which stage a user is in" · "new vs dormant users"
• user properties vs. event propertiestraits attached to a person vs. to a single action"person info vs action info" · "what goes on the user record"
• bounce rate vs. engagement ratesingle-action visits vs. meaningfully engaged visits"people who leave right away" · "bounce rate vs engaged sessions"
• first-party analyticstracking from your own domain, without third-party cookies"privacy-friendly analytics" · "cookieless analytics"
• tracking plandocumented spec of every event and its properties"the spreadsheet of what we track" · "event schema"
• guardrail metricsecondary metric watched so a win doesn't break something"make sure we didn't hurt something else"

Deeper in the field

• conversion event tracked action designated as a desired outcome
• acquisition channel traffic grouping such as organic, paid, direct, or referral
• source / medium labels identifying traffic origin and delivery method
• multi-touch attribution (MTA) splitting credit across all touchpoints, not just last click
• last-click / first-touch attribution crediting the final or initial touchpoint entirely
• attribution window period after a touchpoint during which conversions receive credit
• cross-domain tracking preserving user and session identity across related domains
• data layer structured browser data supplying consistent values to analytics tools
• tag management system tool for deploying analytics tags without code releases
• server-side tracking sending events from backend, bypassing browser blockers
• CDP (customer data platform) central hub collecting and routing events to tools
• event deduplication preventing double-counted or spammed events
• control group unchanged comparison group estimating a variant's causal effect
• holdout group users deliberately excluded to measure baseline
• incrementality test holdout comparison proving a channel caused lift
• experiment sample-size calculation users needed to detect a given effect reliably
• peeking problem inflated false positives from checking test results early
• novelty effect temporary metric lift because a change is simply new
• survivorship bias conclusions skewed by only measuring users who stayed
• vanity metric impressive number that does not guide a meaningful decision
• stickiness ratio DAU-to-MAU or DAU-to-WAU ratio indicating habitual use
• power user curve (L30) frequency distribution separating casual from heavy users
• funnel analysis vs. path analysis fixed-step vs. free-path exploration of user routes
• funnel leakage disproportionate drop at one specific step
• funnel window time limit within which steps must occur to count
• consent mode / privacy-preserving measurement modeling metrics when users decline tracking
• data freshness / latency delay between an action and its appearance in reports
• metric definition drift same metric name computed differently in two tools
• anomaly detection / alerting automatic flags when a metric deviates from expected