incrementality-and-experimentation

Name: incrementality-and-experimentation
Availability: InStock
Author: scumunna

Design advertising incrementality tests with statistical power and sample size calculations.

1|Updated Jun 24, 2026

Search Tags:#experiment design #statistical analysis #advertising #incrementality testing #brand lift

Ready to run

npx skills add https://github.com/scumunna/programmatic-skills --skill incrementality-and-experimentation

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: incrementality-and-experimentation
Source: https://github.com/scumunna/programmatic-skills/tree/main/skills/incrementality-and-experimentation
Command: npx skills add https://github.com/scumunna/programmatic-skills --skill incrementality-and-experimentation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill empowers you to design and interpret incrementality tests with statistical rigor, validating the true impact of advertising campaigns.

Core Features & Use Cases

Incrementality Test Design: Tailored approaches for different test methods (e.g., user-level holdout, geo lift, brand lift survey).
Statistical Rigor: Enforcing minimum detectable effect, statistical power, significance levels, and sample size.
Use Case: Plan a geo lift test to measure the effectiveness of a new video ad campaign across multiple markets, ensuring results are statistically sound and meaningful.

Quick Start

Design a lift test to measure campaign A's impact against control, considering statistical rigor, minimum detectable effect, and platform constraints.

Frequently Asked Questions about incrementality-and-experimentation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I design an incrementality test to measure true advertising impact?▼

An incrementality test measures the causal effect of advertising by comparing exposed and control groups. You design it by selecting a methodology like geo lift or user-level holdout, then calculating statistical power, significance levels, and sample size to validate the true impact.

What is the difference between geo lift and user-level holdout testing?▼

Geo lift testing measures advertising impact by holding out entire geographic markets as control groups, while user-level holdout isolates specific individuals. Both evaluate the causal effect of campaigns but differ in their granular approach to controlling exposure.

How do I calculate sample size and statistical power for a marketing lift test?▼

To calculate sample size and statistical power for a lift test, establish your minimum detectable effect and significance levels. These statistical calculations ensure your advertising test results are mathematically sound and meaningful beyond observed data.

When should I use brand lift surveys instead of marketing mix modeling?▼

Use brand lift surveys when you need direct user-level feedback on brand perception, whereas marketing mix modeling evaluates overall campaign effectiveness using historical data. Both methodologies measure advertising incrementality but rely on distinct causal effect evaluation approaches.

Can I interpret confidence intervals to evaluate campaign effectiveness?▼

Yes, interpreting confidence intervals is essential to evaluate campaign effectiveness and validate advertising impact. It helps determine the statistical significance of your incrementality test results within the defined minimum detectable effect.