Bad luck could be, not just getting that 5% result which 95% accuracy implies, but some non-obvious difference in the volunteers (different genetics?), in the tea. or in the milk.
It isn’t that odd. There are a lot of things that could easily change the results. Exact temperature of tea (if one protocol involved hotter or colder water), temperature of milk, type of milk, type of tea (one of the protocols uses black tea, and another uses green tea). Note also that the studies are using different metrics as well.
It does seem odd to get such divergent results.
Bad luck could be, not just getting that 5% result which 95% accuracy implies, but some non-obvious difference in the volunteers (different genetics?), in the tea. or in the milk.
It isn’t that odd. There are a lot of things that could easily change the results. Exact temperature of tea (if one protocol involved hotter or colder water), temperature of milk, type of milk, type of tea (one of the protocols uses black tea, and another uses green tea). Note also that the studies are using different metrics as well.
Nitpick: the second study included both black and green tea.
However, your general point stands, and I’ll add that there are different sorts of both black and green teas.