-
The F Curve Humility
That sloping F curve is a humility lesson. It asks, “How often would chance alone throw a number like yours?” If the tail is thin where you landed, you likely touched the signal. If it’s thick, you likely touched your own impatience. Curiosity beats certainty; run the test, then earn the claim.
-
Label Like a Human
“1/2/3” is future-you’s enemy. “High-Impact/Low-Impact/Control” is a gift. Statistics is heavy enough… don’t add memory taxes. Every label is a small act of kindness toward your own cognition.
-
Descriptives First, Always
If descriptives don’t match your sheet, nothing that follows counts. Think of descriptives as pre-flight. You don’t roll down the runway because you’re pretty sure the wing bolts are tight.
-
Within-Noise Hygiene
We romanticize “signal,” but craft lives in noise hygiene: consistent timing, instructions, counterbalancing, clean data entry. Reduce the rumble so small truths can speak up.
-
Meaning Over Mechanic
“Giving” is a mechanic; “impact” is a meaning. Designs that manipulate meaning move people… and numbers. Name the lever that hearts feel, not just the checkbox you can toggle.
-
Post-Hoc Integrity
If the ANOVA gate is closed, post-hocs are tour guides to nowhere. Peek for learning, sure… but don’t publish the postcard. Integrity scales your influence.
-
Effect Size as Story Weight
p tells you if; effect size hints at so what. Report both. A tiny, reliable blip is still a blip. A medium effect with meaning can change practice.
-
Choose Tests Like Tone
Every analysis has a voice. LSD is bold, Tukey measured, Bonferroni conservative. Your choice signals your posture toward risk and proof. Say it out loud before you click.