==============================================================================
LOG-DAY MODEL + COHEN'S f + POWER -- naive_a2_d0_13   [metric: success RATE]
==============================================================================
model: behavior ~ stim + log(day) + stim:log(day) + (1|rat)   (behavior = success RATE)
log(day) uses 1-indexed training day (our day 0 = paper "Day 1")
observed groups: stim n=3, control n=7   nrep=120, alpha=0.05

--- fitted on real data ---
stim x log(day) interaction: F(1,118)=8.542  p(resid)=0.00416  p(Satt)=0.00418 (df=115)
  honest per-animal random slope (log-day): F(1,5.1)=7.00  p=0.04487
Cohen's f (interaction, partial eta^2=0.019) = 0.141  (small-medium; f: .10 small, .25 medium, .40 large)

--- power simulation (log-day ground truth: stim:logday=+0.07789, ratSD=0.04775, resSD=0.09872) ---

 true stim:log(day) = +0.07789 (100% of observed)
  N/group  | per-animal power | LME power
  ------------------------------------------
  3        |  0.38            |  0.80  <- observed
  5        |  0.84            |  0.93
  8        |  1.00            |  1.00
  12       |  1.00            |  1.00
  16       |  1.00            |  1.00
  24       |  1.00            |  1.00

 true stim:log(day) = +0.03895 (50% of observed)
  N/group  | per-animal power | LME power
  ------------------------------------------
  3        |  0.13            |  0.31  <- observed
  5        |  0.31            |  0.38
  8        |  0.59            |  0.63
  12       |  0.75            |  0.78
  16       |  0.92            |  0.92
  24       |  0.95            |  0.95

Read per-animal as the honest power; LME matches the paper's power code (optimistic).
