Rationally Wellby Hinge Testlab
Methodology

Rigor you can inspect, and a number that tells you how far to trust it.

We measure each customer against their own starting point, report the full picture, and label every read with how firmly it can be leaned on. Here is how the measurement works, and what it establishes.

Each customer is their own baseline

Compare each customer only to themselves.

The method begins with a simple, demanding idea: compare each customer only to themselves. Before the product has had time to do anything, we capture where that person starts. Every later check-in is read against that personal starting point, so the change we report is change within that individual, not an average pulled from a crowd of strangers who began in different places. Comparing a person to themselves removes the largest source of noise in most consumer measurement, the fact that no two people start alike.

Took Stillwell Nightly · Night wakingsExample
Your nights, with versus without
On nights with it38 nights
0.6per night, average
0your range 0 – 34
On nights without9 nights
1.7per night, average
0your range 0 – 44
The same measures, the same way, every time

Consistency is the rigor.

Rigor lives in consistency. Each customer answers the same structured measures, in the same form, at each check-in, beginning with a clean baseline taken before first use. That consistency is what lets a change be read as a change, rather than an artifact of asking different questions at different moments.

Every read carries a confidence level

No number arrives bare.

Each read is reported with a stated confidence level that reflects how many customers it draws on, how consistent the signal is, and how much time has passed. An early, thin read is labeled as exactly that. A firm one is too. As more customers move through their first weeks, confidence rises and the picture settles. You are never asked to trust a number more than the data behind it earns.

We report the whole distribution

The honest curve is the product.

The full response curveExample
no change strong response non-responders kept in
Rungs of rigor

Choose the rung your claim needs.

Measurement comes in rungs, and you choose the one your claim needs.

This rung

Within-person baseline read

Reads how your customers respond against their own baseline: their reported experience, the timing, the subgroups, the patterns. It establishes how your customers responded and what they reported feeling, measured honestly and labeled by confidence.

Experience and perception
Higher rung

Claims-Ready

When a claim needs to separate your product's effect from everything else at work in real life, that calls for a higher rung. The Claims-Ready rung adds an independent review board and a control group, the design built for study-grade claims. Same honest posture, more rigorous instrument, for when the claim you want to make asks for it.

Study-grade claims
We show our work

Rigor you can inspect.

The measures, the method, and the way confidence is assigned are documented and open to inspection. Before you stand behind a number, you can see how it was produced. Rigor you cannot inspect is just a claim. Rigor you can is the reason to trust the read.

Two voices, kept separate

Your claims, our measurement.

Your product claims stay in your voice. The measurement stays in ours. That separation is what lets the read work as honest evidence rather than as marketing the brand wrote about itself. See the two voices side by side.

See the method run

See the method on your own product.

Start with a responder snapshot, and watch the measurement run on a slice of your real customers.