Whole Wheat Bread Lab
What moves together in 116 whole wheat bread 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 116 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: 4 rise together at rho 0.20 or more, 1 moves in opposite directions at −0.20 or less, and 5 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 116 recipes (p of 0.05 or more).
All 15 pairs as a table
| Pair | Rho | Strength | p |
|---|---|---|---|
| Sweetener and fat | 0.56 | moderate | under 0.001 |
| Sweetener and yeast | 0.49 | moderate | under 0.001 |
| Fat and yeast | 0.36 | weak | under 0.001 |
| Salt and yeast | −0.27 | weak | 0.003 |
| Liquid and salt | 0.24 | weak | 0.010 |
| Whole wheat share and fat | 0.15 | very weak | 0.12 |
| Liquid and fat | −0.14 | very weak | 0.13 |
| Whole wheat share and liquid | −0.14 | very weak | 0.14 |
| Fat and salt | −0.14 | very weak | 0.14 |
| Sweetener and salt | −0.11 | very weak | 0.23 |
| Liquid and yeast | −0.10 | negligible | 0.31 |
| Whole wheat share and yeast | 0.06 | negligible | 0.53 |
| Whole wheat share and salt | −0.04 | negligible | 0.64 |
| Liquid and sweetener | −0.04 | negligible | 0.69 |
| Whole wheat share and sweetener | −0.03 | negligible | 0.76 |
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.
Recipes with more sweetener tend to use more fat
rho 0.56 across 116 recipes · moderate · p under 0.001
The third of recipes with the most sweetener use a median of 7.6% fat; the third with the least sweetener, 0%.
Recipes with more sweetener tend to use more yeast
rho 0.49 across 116 recipes · moderate · p under 0.001
The third of recipes with the most sweetener use a median of 1.6% yeast; the third with the least sweetener, 0.8%.
Recipes with more salt tend to use less yeast
rho −0.27 across 116 recipes · weak · p 0.003
The third of recipes with the most salt use a median of 1.1% yeast; the third with the least salt, 1.5%.
Also strong, and left out above because both of its ingredients already appear: fat and yeast (rho 0.36).
What moves on its own
- Whole wheat share. Nearly independent of the rest: its strongest correlation with any other ingredient is 0.15, with fat. A recipe's amount of whole wheat share says almost nothing about its other amounts.
The pairs closest to unrelated: whole wheat share and sweetener (−0.03), liquid and sweetener (−0.04), whole wheat share and salt (−0.04) and whole wheat share and yeast (0.06).
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 whole wheat share 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.