Manipulation of statistics such that the desired outcome assumes "statistical significance", usually for the benefit of the
study's sponsors. Usually done by ex post facto
choice of significance labels and simple reporting of results as being conclusive regardless of calculated p-value. This depends on the public's general lack of understanding of statistical measures and press non-reportage of details.
Also the basis of nutrition
research.
Study: "Soy protein was shown to reduce
cancer rates in rats with a p <1.0" (effectively random data)
Next day's headline: "Soy Cures
Cancer"
Sales soar 1000%
p-hacking = Profit.