MMMM Studio
  1. 01 Map
  2. 02 Check
  3. 03 Expect
  4. 04 Fit
  5. 05 Test
  6. 06 Plan

Step two · before any modelling

Can this data answer the question at all?

A fit takes minutes and hands back confident-looking numbers whether or not the design could ever have identified them. So we ask whether it could first, and it costs a second. Nothing here has been modelled — this is arithmetic on your file.

The verdict

Go

Your data can answer the question. Nothing here stops the model from running, and nothing will make a channel's number meaningless.

3 things to carry forward, all about how wide the answers will be, not whether you get them: Paid Search, TV — Broadcast and Out of Home.

How this verdict is decided

NO-GOsomething is broken that isn't about one named channel — or every channel is blocked
CAUTIONone or two named channels are blocked, and the rest are fine
GOnothing blocked — cautions on named channels travel with those channels instead

There is no score to improve and no percentage to argue with. A caution about one channel never demotes the whole dataset, because it has somewhere better to live: that channel’s own row, and its trust grade after the fit.

Set my expectations →

Takes about two minutes, and it is the step that catches impossible assumptions before they become results.

Five questions we ask of every dataset

History
Is there enough data to work out this many things at once?

208 rows · 6.1× headroom

34 things to estimate

Separability
Can the channels be told apart from each other, and from ordinary demand?

6.80 · line at 5.00

Paid Search

Variation
Does each channel's spend move enough for its effect to be visible?

2 channels flagged

TV — Broadcast and Out of Home

Demand control
Is there a column for the demand that prompted the spend? Whether it is a good one can't be established from this data — only that it is there.

Present

a demand control is mapped

Sales series
Is the sales line itself clean enough to model?

No extreme weeks

nothing the outlier check flagged

Three things to know, each with what to do about it

Worth watchingElevated variance inflation6.804 measured · 5.00 threshold

Paid Search has VIF 6.8 after transformation.

What to do: Worth watching rather than fixing. If this channel also shows low contraction on the Evidence tab, treat its individual number as unreliable.

Worth watchingTV — Broadcast is off air most weeks0.615 measured · 0.50 threshold

It runs in 38% of weeks, in bursts rather than at the start or end of the window. The effect is identified from the handful of on/off transitions rather than from the whole period, so its interval comes back wide even when the fit itself is sound.

What to do: Nothing to fix in the data — this is a media plan, not a defect. Expect a wide range on this channel and weight it accordingly; a lift test on a single burst would pin it faster than more history would.

Out of Home is off air most weeks0.524 measured · 0.50 thresholdOpen

It runs in 44% of weeks, in bursts rather than at the start or end of the window. The effect is identified from the handful of on/off transitions rather than from the whole period, so its interval comes back wide even when the fit itself is sound.

What to do: Nothing to fix in the data — this is a media plan, not a defect. Expect a wide range on this channel and weight it accordingly; a lift test on a single burst would pin it faster than more history would.

What we will do about it

Findings change the model, not your numbers. We never impute, winsorise or drop a row — every entry here alters how the fit is estimated, and states what that costs you.

Your data clears every check that would make us alter the model, so this will be a plain fit of the specification you chose.

How much each channel's spend moves about

Ups and downs are what let the model see what a channel does. Spend the same amount every week and there is nothing to learn from — the return comes back as whatever we assumed going in, however large the budget.

ChannelSpend shareVariationOverlap costWeeks with nothing spent
TV — Broadcast28.0%1.371.262% of weeks had no spend
Video — CTV15.7%0.603.2spent every week
Paid Social19.4%0.333.0spent every week
Paid Search16.9%0.426.8spent every week
Programmatic Display11.4%0.321.9spent every week
Out of Home8.6%1.171.256% of weeks had no spend

How closely your channels move together

Read a cell as: when this channel went up, did that one go up too? 1.00 means always, 0.00 means never. Anything above 0.80 and your data cannot tell the two apart. Measured after allowing for advertising that keeps working once it stops running and for the tenth million doing less than the first — checking raw spend instead is the usual reason a tool declares your data fine and then fails to separate anything.

TV — Broadcast1.000.060.180.190.040.08
Video — CTV0.061.000.170.120.220.11
Paid Social0.180.171.000.780.51-0.04
Paid Search0.190.120.781.000.580.09
Programmatic Display0.040.220.510.581.00-0.02
Out of Home0.080.11-0.040.09-0.021.00
TV — BroadcastVideo — CTVPaid SocialPaid SearchProgrammatic DisplayOut of Home
How do I read this?