Mind Hacks has an article trying to explain why the placebo effect has been growing stronger over the last few years — a great reminder that sometimes historical data gets tainted as recording and testing procedures change over time.
For example, we know that better designed and higher quality studies show smaller drug effects. This includes things as simple as randomization. If your method for randomly allocating people to groups is more susceptible to bias, it’s more likely to produced biased results. Better randomization improves the placebo effect, again, nothing to do with expectancy or belief.
Yet another example of how we can’t take statistics for granted, we have to put them in the context of how the underlying data was collected.