A teacher in my highschool (~16 years ago) “demonstrated” that lossless and mp3 are indistinguishable by playing the same song in different formats… On 10€ pc speakers

’ A p-value of 0.05 was considered statistically significant because that’s what everyone does and we don’t question tradition.’

I’m currently doing the same experiment over and over again to hopefully soon reach significance. This hits to close to home