Comparison group

Similar accounts, same tier, segment and access state, that did not receive the effort in the same period. Their change carries the season, the market and the product change; subtracting it leaves what is associated with the effort. It removes noise, not the selection of who got the effort.

DefinitionSimilar accounts, same tier, segment and access state, that did not receive the effort in the same period. Their change carries the season, the market and the product change; subtracting it leaves what is associated with the effort. It removes noise, not the selection of who got the effort.

Always beside the own change

Own change alone credits the market to the effort.

Not a holdout

A holdout is random and measures cause. A comparison group is observational and measures association.

How it is used

Accounts of the same tier, segment and status that did not receive the effort in the same period. The outcome for the treated accounts is read against the outcome for this group, not against their own past alone.

Example

Accounts called monthly grew 6 percent. Similar accounts not called grew 1 percent over the same months. The difference of 5 points is the most that can be attributed to the calls.

Where it goes wrong

Before and after on the treated accounts only. The market rose 4 percent, and the programme is credited with all 6.

Articles that use this term

AI and self-service analytics

Association and cause: what the company's own data can say, and the sentence that says it

Why every effect measured from a company's own history, samples and prescriptions, onboarding milestones and renewals, first-touch latency and first-year revenue, delayed installs and non-renewal, is an association and not a cause, the selection that makes it so, the comparison group that removes most of the noise, the sentence that reports it honestly, associated with rather than caused, why it is still enough to direct effort, and the two claims that are never made from it.

16 Sept 20263 min read Forecast and pipeline · Pharma

Pull-through after a formulary win: did the prescriptions follow the access?

How a pharmaceutical commercial team measures whether a formulary or payer win turned into prescriptions, from the access file, the prescription data and the call log: the accounts whose access opened on a date, their prescriptions before and after against accounts whose access did not change, the calls made to them in the weeks after the win, the territories where access opened and nobody called, and the honest statement of what the difference is and is not.

16 Sept 20262 min read Territory, capacity and quota planning · Pharma

Sample-to-script correlation per territory: what the samples actually moved

How a pharmaceutical commercial team relates sample drops to prescription change per account and per territory, from the sample log and prescription data: the account's own baseline, the change in the weeks after sampling against accounts of the same tier not sampled, the territories where sampling moves nothing, and the honest wording that keeps a correlation from being reported as a cause.

16 Sept 20262 min read Coverage and territory · Pharma

Ten questions a pharma commercial head asks, and the table that answers each

The ten questions a pharmaceutical commercial head puts to the field and market access teams, what is reach and frequency among accounts that can prescribe, which calls went to blocked accounts, did the formulary win pull through, which territories are balanced on writable potential, which samples moved anything, which accounts have open access and no call, what did the cycle plan say against what happened, where did access change this month, which reps are off plan, and what changed, each with the table from the call log, the access file and the prescription data, and the answer to send back.

16 Sept 20263 min read