==============================================================================
LOG-DAY MODEL + COHEN'S f + POWER -- right_only_d6_10   [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=4, control n=2   nrep=120, alpha=0.05

--- fitted on real data ---
stim x log(day) interaction: F(1,26)=0.485  p(resid)=0.4924  p(Satt)=0.4929 (df=24)
  honest per-animal random slope (log-day): F(1,6.0)=0.24  p=0.644
Cohen's f (interaction, partial eta^2=0.009) = 0.094  (small; f: .10 small, .25 medium, .40 large)

--- power simulation (log-day ground truth: stim:logday=+0.09523, ratSD=0.03826, resSD=0.05641) ---

 true stim:log(day) = +0.09523 (100% of observed)
  N/group  | per-animal power | LME power
  ------------------------------------------
  3        |  0.04            |  0.10
  5        |  0.15            |  0.19
  8        |  0.17            |  0.23
  12       |  0.20            |  0.27
  16       |  0.40            |  0.38
  24       |  0.54            |  0.54

 true stim:log(day) = +0.04761 (50% of observed)
  N/group  | per-animal power | LME power
  ------------------------------------------
  3        |  0.06            |  0.11
  5        |  0.09            |  0.09
  8        |  0.06            |  0.07
  12       |  0.12            |  0.12
  16       |  0.14            |  0.14
  24       |  0.22            |  0.22

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