Pvalue and power

P value

types of P value

1. one sided P value :rarely used, and we should avoid this P value.
2. two sided P value: the most common

a P value is composed of three parts

1. the probability random change would result in the observation
2. the probability of observing something else that is equally rare
3. the probability of observing something rarer or more extreme

P-hacking

P-hacking means the misuse and abuse of analysis techniques and results in being fooled by false positives.
makes the false positives small : adjust P value.

Power

Power is the probability that we will correctlly reject the Null hypothesis.

Power analysis

we are going to do a power analysis to determine the Sample size for the next time we do this expriment.
Power is effected by several things, there are two main factors:

1. How much overlap there is between the two distributions we want identify with our study.
2. The sample Size: the number of measurements we collect from each group.
   the more overlaps , need more Sample Size in order to have** Power=0.8**