Scones Lab660 recipes

Scones Lab

What moves together in 660 scone recipes

When a recipe uses more of one ingredient, does it tend to use more or less of another? For every pair of the 6 ingredient ratios (grams per 100 g of flour), this page ranks all 660 recipes on each and measures how closely the two rankings agree: Spearman's rho, from −1 (the more of one, always the less of the other) through 0 (unrelated) to 1 (always rise together).

15 pairs in all: 3 rise together at rho 0.20 or more, 1 moves in opposite directions at −0.20 or less, and 6 are close to unrelated (between −0.10 and 0.10). This describes recipes as they are published; it does not say what changing one amount would do to a bake.

Every pair at once

Read a cell by its row and column. Caramel cells rise together, slate cells move in opposite directions, and the deeper the color the stronger the relationship. Pale cells with grey numbers are not distinguishable from no relationship with 660 recipes (p of 0.05 or more).

Butter and liquid: rho −0.10, very weak−0.10Butter and sugar: rho 0.52, moderate0.52Liquid and sugar: rho −0.18, very weak−0.18Butter and egg: rho 0.15, very weak0.15Liquid and egg: rho −0.31, weak−0.31Sugar and egg: rho 0.17, very weak0.17Butter and leavening: rho 0.04, negligible, not distinguishable from zero0.04Liquid and leavening: rho 0.07, negligible, not distinguishable from zero0.07Sugar and leavening: rho −0.01, negligible, not distinguishable from zero−0.01Egg and leavening: rho 0.09, negligible0.09Butter and salt: rho 0.39, weak0.39Liquid and salt: rho 0.04, negligible, not distinguishable from zero0.04Sugar and salt: rho 0.34, weak0.34Egg and salt: rho 0.13, very weak0.13Leavening and salt: rho 0.02, negligible, not distinguishable from zero0.02LiquidSugarEggLeaveningSaltButterLiquidSugarEggLeavening
All 15 pairs as a table
Spearman correlation for every pair of ratios, strongest first
PairRhoStrengthp
Butter and sugar0.52moderateunder 0.001
Butter and salt0.39weakunder 0.001
Sugar and salt0.34weakunder 0.001
Liquid and egg−0.31weakunder 0.001
Liquid and sugar−0.18very weakunder 0.001
Sugar and egg0.17very weakunder 0.001
Butter and egg0.15very weakunder 0.001
Egg and salt0.13very weakunder 0.001
Butter and liquid−0.10very weak0.008
Egg and leavening0.09negligible0.025
Liquid and leavening0.07negligible0.074
Butter and leavening0.04negligible0.37
Liquid and salt0.04negligible0.37
Leavening and salt0.02negligible0.67
Sugar and leavening−0.01negligible0.71

The three clearest relationships

The strongest pairs that reach rho 0.20 either way with a p-value under 0.01. Each dot is a recipe; the line joins the median of the second ingredient within each fifth of recipes ranked by the first.

  1. Recipes with more butter tend to use more sugar

    rho 0.52 across 660 recipes · moderate · p under 0.001

    The third of recipes with the most butter use a median of 27% sugar; the third with the least butter, 11%.

    0%20%40%60%80%0%20%40%60%Butter, % of flour →↑ Sugar, % of flour
  2. Recipes with more butter tend to use more salt

    rho 0.39 across 660 recipes · weak · p under 0.001

    The third of recipes with the most butter use a median of 1.2% salt; the third with the least butter, 0.2%.

    0%20%40%60%80%0%1%2%3%4%Butter, % of flour →↑ Salt, % of flour
  3. Recipes with more liquid tend to use less egg

    rho −0.31 across 660 recipes · weak · p under 0.001

    The third of recipes with the most liquid use a median of 0% egg; the third with the least liquid, 19%.

    0%50%100%150%0%20%40%60%Liquid, % of flour →↑ Egg, % of flour

Also strong, and left out above because both of its ingredients already appear: sugar and salt (rho 0.34).

What moves on its own

  • Leavening. Nearly independent of the rest: its strongest correlation with any other ingredient is 0.09, with egg. A recipe's amount of leavening says almost nothing about its other amounts.

The pairs closest to unrelated: sugar and leavening (−0.01), leavening and salt (0.02), butter and leavening (0.04) and liquid and salt (0.04).

How the numbers are made

Spearman's rho is the ordinary correlation of the two rankings, so it measures whether one amount tends to rise with the other, in a straight line or not, and a single extreme recipe moves it little. A recipe with none of an ingredient ranks lowest on it. An ingredient fewer than 12 recipes use is left out of the matrix.

The p-value is the chance of a rho at least this far from zero if the two amounts were unrelated. With 15 pairs tested, about 0.8 would pass 0.05 by chance alone even if no ingredient were related to another, which is why the relationships explained above must pass 0.01 and reach 0.20.

Every number is divided by the same flour weight, so a recipe light on flour reads high on every ingredient at once. That nudges every correlation toward positive: part of a positive rho can be flour, not the two ingredients. A negative one holds despite it.

A correlation describes the recipes as published. “Recipes with more butter tend to use…” is a statement about what bakers write down together, not a rule that adding one forces the other. Plot any two ingredients to see the recipes behind a number.