OK, challenge accepted, or as the Emperor would say:
View attachment 34607
First off, are you aware that you have duplicate people in your list? I just finished reading through the entire User Experiences thread and put things into Excel. The criteria I use:
-Claire B not included. She was a trial participant.
-Only those at or near the end of treatment are in this list. Results fluctuate too much to include anyone else.
-Wishy-washy results that sound too much like Neuromod's video testimonials get filed under "Placebo".
THAT is where the what-color-is-this-dress subjectivity is going to be.
BTW, I hesitate to mention this but we do have one disimprover followed by suicide. I'm not going to indict Neuromod but Allan's experience is still a matter of record.
So in my accounting, 19 total participants.
Disimprover: 3
No Change: 5
Placebo (wishy washy/mild/inconclusive): 8
Improver (aka statistically significant): 3
Final tally: 3 / 19 =
15.7%
Verdict: Results do NOT match Neuromod's claims.
Even if you include everyone in the placebo group it rises to
57.8% which is close to but still shy of their figures, but it helps explain their criteria which seems to chalk up every weak/wishy-washy outcome as a win.
Sample size is still much too small. Averages always fluctuate a lot with small sample sizes. I'd like to see well over 100 complete their treatment before drawing any conclusions, which I doubt we'll get before April.
View attachment 34608