InvestorsHub Logo
Followers 38
Posts 1440
Boards Moderated 0
Alias Born 03/07/2004

Re: pphmtoolong post# 211172

Sunday, 03/15/2015 4:35:08 PM

Sunday, March 15, 2015 4:35:08 PM

Post# of 346283
PPHMtoolong, stat/sig or statistical significance is everything.
Without it data is "anecdotal", or someone's impression that a set of observations is real. The following is grossly simplified: To get into the "stat/sig ballpark" usually require that, after doing some simple math on a data set, it can be establish that if the test were performed 100 times the observed data could only happen by chance in 5 or fewer test runs out of 100 identical trials. Test data with a p value of .01, is much more reliable because only once in one hundred similar test runs would the observed data set be expected to occur by chance. Obviously the lower the p value, the more certain is a real difference between test data and "chance" occurence. What about p=.08? Not good enough even though the data set may actually be valid. The number of observations (patients) is factored in.
Once you've taken courses in statistics your point of view becomes almost intolerable to more romantic/dreamer folks...
Volume:
Day Range:
Bid:
Ask:
Last Trade Time:
Total Trades:
  • 1D
  • 1M
  • 3M
  • 6M
  • 1Y
  • 5Y
Recent CDMO News