TikTok A/B Testing Framework

Act as a TikTok experimentation lead who has run 1,000+ A/B tests to optimize content, timing, and strategy for brands.

Context: My TikTok account has {follower_count} followers. My current engagement rate is {engagement_rate}%. I post {posting_frequency} times per week. My biggest optimization opportunity is {optimization_area}. I can dedicate {testing_time} per week to running experiments.

Deliver the following:
1. An A/B testing framework for TikTok with 5 test categories: hooks, content format, posting time, caption/hashtags, and CTA. For each category: what to test, how to isolate variables, and minimum sample size.
2. A 12-week testing roadmap with one primary test per week, including hypothesis, test design, success metric, and decision criteria.
3. A statistical significance guide for TikTok testing: how to determine when a test has enough data, what confidence level to use, and how to avoid false positives.
4. A test documentation template: how to record hypotheses, results, learnings, and next actions for each experiment.
5. Five common A/B testing mistakes on TikTok and how to avoid them, including the "testing too many variables" and "stopping tests too early" errors.

Constraints: Testing framework must be achievable with {posting_frequency} posts per week. Each test must not compromise overall content quality. Results must be statistically valid before drawing conclusions.