Fundamentals·Glossary term

Experiment

Experiment A/B testing Reference guide

Experiment is a concept used in experimentation fundamentals.

Quick definition: An experiment is a systematic investigation in which an intervention is deliberately assigned or introduced and its effect on a defined outcome is measured. In product experimentation, the strongest design is usually a randomized controlled experiment: eligible units receive control or treatment, outcomes are collected concurrently, and the difference is analyzed under a prespecified plan.

What is an experiment?

An experiment is a structured test of a hypothesis. Unlike an observational analysis, where a team studies what happened naturally, an experiment deliberately changes a condition and measures the consequence. That intervention may be a new interface, recommendation model, pricing rule, onboarding flow, campaign message, or operational policy.

The central question is causal:

What would have happened to the same units without the intervention?

That alternative outcome is the counterfactual and cannot be observed for the same unit at the same time. A control group provides a concurrent estimate of it. GrowthBook defines a controlled experiment as a comparison between what happened under treatment and a credible estimate of what would have happened without it [1].

Experiment vs. related methods

MethodIs treatment assigned?Concurrent control?Main use
Randomized controlled experimentYes, randomlyYesEstimate causal effect
A/B testYes, usually randomlyYesDigital controlled experiment
Before-and-afterSometimesNoDescribe change over time
Observational studyNoNot necessarilyStudy naturally occurring differences
Quasi-experimentNot fully randomOftenEstimate effects when randomization is infeasible
Usability studyMay show a prototypeNot necessarilyUnderstand interaction problems and “why”

“Experiment” is the broad concept. “A/B test” is one common online implementation, not a completely separate scientific method.

The components of a trustworthy experiment

1. A decision or research question

Start with the decision, not the tool. Examples include: should the new checkout ship, does the ranking model improve completed sessions, or does the pricing page reduce qualified-lead conversion?

2. A minimal viable hypothesis

A useful hypothesis names the intervention, expected outcome, mechanism, and population:

If we show transparent delivery dates on product pages,
then completed purchases will increase,
because uncertainty about fulfilment will fall for first-time shoppers.

A hypothesis should be falsifiable. “Make the experience better” is an aspiration, not an experiment hypothesis.

3. Experimental units and population

Define who or what can receive the intervention: users, accounts, sessions, requests, stores, regions, listings, or organizations. Choose a randomization unit that matches how the treatment spreads and how outcomes are shared. User-level assignment usually provides a consistent cross-session experience; account or cluster assignment may be necessary when members interact.

4. Control and treatment

The control is the baseline condition. The treatment is the intervention. Document the difference precisely: code version, content, eligibility, exposure event, rollout, dependencies, and expected mechanism.

5. Outcomes and evaluation criteria

Choose one primary outcome for the main decision. Add secondary metrics for explanation, guardrails for potential harm, and diagnostic metrics for experiment trustworthiness. Mature organizations may define an Overall Evaluation Criterion (OEC) that expresses the business objective across multiple outcomes, but it must be designed before launch rather than assembled from whichever metric moved.

6. Assignment and instrumentation

Randomization balances confounding influences in expectation. Instrumentation records assignment, exposure, user actions, outcomes, errors, latency, and relevant timestamps. Without reliable exposure and outcome logs, the statistical analysis is only as good as the missing or asymmetric data allows.

7. An analysis and decision rule

Predefine baseline, MDE, power, alpha or Bayesian threshold, duration, primary comparison, stopping rules, treatment of missing data, and rollout criteria. The statistical result is the final link in a chain; it cannot repair weak experimental design.

The experiment lifecycle

Research on the online controlled experiment lifecycle groups the work into three broad phases: ideation, design and execution, and analysis and learning [2]. A useful operational version is:

PhaseKey workOutput
IdeationProblem discovery, evidence review, hypothesis, expected mechanismDecision brief and minimal viable hypothesis
DesignPopulation, unit, variants, metrics, power, duration, risksPre-registered experiment plan
Build and QAImplement assignment, treatment, logging, dashboards, alertsValidated experiment ready to launch
Ramp and executeExpose traffic gradually, monitor guardrails and qualityClean observations under planned conditions
AnalyzeCheck SRM, data quality, primary metric, uncertainty, segmentsScorecard and decision
LearnRecord result, mechanism, limitations, follow-up, rolloutInstitutional memory and next hypothesis

The final phase is often neglected. A result that is not documented cannot improve future prioritization, metric definitions, or experiment design.

How to design an experiment

  1. Frame the problem: identify the user or business friction and supporting evidence.
  2. Define the decision: specify what will happen after positive, negative, or inconclusive evidence.
  3. Write the hypothesis: state change, expected effect, mechanism, and population.
  4. Select the unit: use user, account, request, region, or cluster according to treatment spillover.
  5. Choose metrics: primary, secondary, guardrail, and diagnostic.
  6. Plan power: estimate baseline, MDE, sample, allocation, and duration.
  7. Implement and QA: validate assignment, identity, exposure, events, rendering, and performance.
  8. Run and monitor: ramp risk-sensitive changes and stop only under the planned rules or critical guardrails.
  9. Analyze: inspect validity before interpreting impact.
  10. Ship and learn: roll out, roll back, or design a follow-up experiment.

Randomization and causal inference

Randomization gives each eligible unit a known chance of receiving each condition. It tends to balance observed and unobserved characteristics across arms within the limits of sample size. The observed difference then estimates an average treatment effect under the assumptions of the design.

Estimated effect = average outcome in Treatment − average outcome in Control

That estimate is only meaningful if treatment assignment is credible, users remain in their assigned experience, outcomes are measured consistently, and treatment does not contaminate control. If users influence one another, share inventory, or compete for a fixed resource, interference can violate the simple individual-level model. In such cases, consider cluster, geo, time-based, or other specialized designs. The controlled-experiments literature explicitly identifies leakage and interference as threats to validity [3].

Metrics and the Overall Evaluation Criterion

Metric classQuestion it answersExample
Success / primaryDid the intervention achieve its main objective?Activated accounts per eligible user
Driver / secondaryWhat mechanism moved?Form completion, feature adoption
GuardrailDid we harm something we refuse to trade away?Errors, latency, cancellations
Trust / diagnosticCan we trust the comparison?SRM, exposure rate, missing events

Metrics should be normalized to the experimental unit where appropriate. For example, revenue per user is generally more interpretable than total revenue when arm sizes differ. Do not turn every metric into a winner criterion; multiple unplanned tests increase false discoveries and make decisions ambiguous.

Threats to experiment validity

ThreatWhat it looks likeMitigation
Sample Ratio MismatchObserved allocation differs from planCheck assignment counts; investigate before reading impact
PeekingStopping when a p-value turns favorableFix horizon or use valid sequential inference
CarryoverPrevious treatment affects later outcomesStable user assignment, washout, or specialized design
InterferenceTreatment users affect control usersCluster, geo, resource, or time-based randomization
NoveltyShort-lived reaction to a new experienceRun through adoption cycles; use long-term holdouts
Instrumentation asymmetryEvents or denominators differ by armQA raw logs and invariant metrics
Selection after treatmentAnalyzing only users behaviorally triggered by treatmentPrefer intent-to-treat or pre-treatment eligibility

Experiment vs. analytics

Analytics describes what users did and where patterns occur. An experiment deliberately changes a condition to estimate what the change caused. Both are necessary:

  • Analytics can identify a funnel drop, segment, or anomaly worth investigating.
  • Qualitative research can explain user intent, confusion, and unmet needs.
  • An experiment can estimate whether a proposed intervention changes behavior.
  • Post-experiment analysis can reveal mechanisms and new hypotheses—but subgroup discoveries should be treated as exploratory unless designed in advance.

An experiment does not answer every product question. It measures outcomes, not the full reason behind them; GrowthBook recommends combining experiments with interviews, surveys, session research, and usability work [4].

Expert experiment checklist

  • The decision and problem are explicit.
  • The hypothesis is falsifiable and mechanism-based.
  • Population, eligibility, and randomization unit are defined.
  • Control and treatment are documented precisely.
  • Primary, secondary, guardrail, and diagnostic metrics are separated.
  • Baseline, MDE, power, sample, and duration are planned.
  • Assignment is random, persistent, and auditable.
  • Exposure and outcomes are logged symmetrically.
  • SRM, latency, errors, and missing events are monitored.
  • Interference, carryover, novelty, and seasonality are considered.
  • Stopping, multiple-testing, and missing-data rules are written before launch.
  • Result, limitations, and follow-up are recorded in a searchable repository.

FAQ

What is an experiment in product analytics?

It is a deliberate intervention assigned to a defined population and evaluated against a measurable outcome, usually with a concurrent control. An A/B test is the most common online form.

Does every experiment need a control group?

For a strong causal comparison, a concurrent control is usually the default. Some designs use historical controls, switchbacks, geo controls, or quasi-experimental methods when a conventional control is impossible—but each carries additional assumptions.

What is the difference between an experiment and an A/B test?

Experiment is the broad methodological term. A/B test is a common digital experiment with two variants, typically control A and treatment B.

Can experiments prove causation?

Randomization supports causal inference by reducing confounding, but only when assignment, exposure, measurement, interference, and analysis are valid.

What makes an experiment trustworthy?

A credible control, appropriate randomization unit, clear hypothesis, reliable instrumentation, adequate sample, predefined outcomes and stopping rules, quality diagnostics, and a documented decision.

Summary

An experiment is not simply “trying a new version.” It is a disciplined learning system: define a counterfactual, intervene deliberately, randomize appropriately, measure outcomes, test trustworthiness, analyze uncertainty, and institutionalize what was learned. The best experimentation programs optimize not only pages or features, but the quality and speed of organizational learning.

Sources

  1. GrowthBook: What is a controlled experiment?
  2. The Online Controlled Experiment Lifecycle
  3. Kohavi, Tang & Xu: Trustworthy Online Controlled Experiments
  4. Google Research: Overlapping Experiment Infrastructure
  5. Analytics ToolKit: Online Controlled Experiment
  6. Practical Guide to Controlled Experiments on the Web
  7. Randomized Experiments and Causal Inference