P-hacking 
https://blogs.plos.org/scicomm/2015/05/19/p-hacking-megan-head-on-why-its-not-good-for-science/
 is when researchers play with the data, often using complex statistical 
models, to arrive at results that look like they're not random.
  
 "There's nothing wrong with having a lot of data and looking at it carefully," 
Althouse says. "The problem is p-hacking."
 To understand p-hacking, you need to understand p-values. P-values 
https://galton.uchicago.edu/~thisted/Distribute/pvalue.pdf are how researchers 
measure the likelihood that a result in an experiment did not happen due to 
random chance. They're the odds, for example, that your new diet is what caused 
you to lose weight, as opposed to natural background fluctuations in myriad 
bodily functions.
 Nonetheless, Malina says, "We believe that the overwhelming majority of 
scientists are committed to rigorous and transparent work of the highest 
caliber."
 

 
https://www.npr.org/sections/thesalt/2018/09/26/651849441/cornell-food-researchers-downfall-raises-larger-questions-for-science
 
https://www.npr.org/sections/thesalt/2018/09/26/651849441/cornell-food-researchers-downfall-raises-larger-questions-for-science
 


 from Megan Head:
 a) P-hacking is when researchers analyse their results in multiple ways or 
multiple times until they get their desired result
 b) this is an issue because it can make us think that an effect or 
relationship is more important than it really is
 c) these could lead to policies or recommendations based on false results. For 
instance if their have been a lot of studies showing that a particular drug has 
no effects on a particular disease if the data were p-hacked it might actually 
look like the drug helps to prevent the disease, when in fact it doesn’t, then 
doctors would be prescribing medicines that don’t actually work.
 d) trust research that has been replicated lots of times more than one off 
studies.
 
https://blogs.plos.org/scicomm/2015/05/19/p-hacking-megan-head-on-why-its-not-good-for-science/
 
https://blogs.plos.org/scicomm/2015/05/19/p-hacking-megan-head-on-why-its-not-good-for-science/
 

 

Reply via email to