Changes

{{cquote|Because with HARKing a hypothesis is made after the results are known the chance of falsely rejecting a null-hypothesis increases, this means an increase of type I errors.}}

{{cquote|Because with HARKing a hypothesis is made after the results are known the chance of falsely rejecting a null-hypothesis increases, this means an increase of type I errors.}}

But not all Hypothesizing After Results are Known is bad.  This situations in which HARKing is harmful are mostly in the fields of medicine and social science.  In those fields, the correct practice is to form an hypothesis, design and conduct an experiment, analyze the results according to good statistical practice, and then draw conclusions about the hypothesis.

But not all Hypothesizing After Results are Known is bad.  This situations in which HARKing is harmful are mostly in the fields of medicine and social science.  In those fields, the correct practice is to form an hypothesis, design and conduct an experiment, analyze the results according to good statistical practice, and then, from those results, draw conclusions about the hypothesis.

But in other fields it needn't be done that way.  For example, the discovery of radioactivity (and hence all of nuclear physics) arose from formulating a theory (by Becquerel, Curie, Rutherford, and many others) to explain the unexpectedly observed phenomenon of energy radiation from Uranium.

But in other fields it needn't be done that way.  For example, the discovery of radioactivity (and hence all of nuclear physics) arose from formulating a theory (by Becquerel, Curie, Rutherford, and many others) to explain the unexpectedly observed phenomenon of energy radiation from Uranium.