|
KMID : 0371319940460020155
|
|
Journal of the Korean Surgical Society
1994 Volume.46 No. 2 p.155 ~ p.162
|
|
|
How Should We Present the Result of Statistical Analysis?: The meaning of P-value
|
|
|
|
|
Abstract
|
|
|
Most medical researchers believe that it would be fruitless be fruitless to submit for publication any paper that lacks statistical tests of "significance". They have preoccupied the significance tests(statistical hypothesis test) whether the
"P-value"
is less than 0.05; results are considered "significant" or "not significant" according to whether or not the "P-value" is less than or greater than 005. But since they could give rise to many misleading conclusions, the notion of "statistical
significance" cold be expunged from the dictionary of the medical researcher with no less. Used to assess confounding, it is simply incorrect; used to test statistically the association between cause and effect, it is often misleading and never
descriptive of the magnitude of effect or the precision of measurement. In conclusion, the use of confidence intervals rather than P-values or "statistical significance" yield a remarkable improvement in clarity of interpretation for everyone and
prevents overt misinterpretation by unwary readers or investigators.
|
|
|
KEYWORD
|
|
|
|
|
|
FullTexts / Linksout information
|
|
|
|
|
Listed journal information
|
|
  
|