Transcript What is a p-value? - Professor Mo Geraghty

Presented by Mo Geraghty and Danny Tran
June 10, 2016


Q:Why do so many colleges and grad schools
teach p =0.05?
A: Because that’s still what the scientific
community and journal editors use.

Q:Why do so many people still use p = 0.05?
A:Because that’s what they were taught in college
or grad school.

ASA statement

- George Cobb, Professor Emeritus of Mathematics and Statistics
- Mt Holyhoke College








The p-value is not the probability that the null hypothesis is
true or the probability that the alternative hypothesis is false.
It is not connected to either.
The p-value is not the probability that a finding is "merely a
fluke."
The p-value is not the probability of falsely rejecting the null
hypothesis.
The p-value is not the probability that replicating the
experiment would yield the same conclusion.
The significance level, such as 0.05, is not determined by the
p-value.
The p-value does not indicate the size or importance of the
observed effect.
Misconceptions about p-value has its own Wikipedia page

Informally, a p-value is the probability under
a specified statistical model that a statistical
summary of the data (e.g., the sample mean
difference between two compared groups)
would be equal to or more extreme than its
observed value.



P-values can indicate how incompatible the
data are with a specified statistical model.
The smaller the p-value, the greater the statistical
incompatibility of the data with the null hypothesis,
if the underlying assumptions used to calculate the
p-value hold.
This incompatibility can be interpreted as casting
doubt on or providing evidence against the null
hypothesis or the underlying assumptions.


P-values do not measure the probability that
the studied hypothesis is true, or the
probability that the data were produced by
random chance alone.
The p-value is a statement about data in
relation to a specified hypothetical
explanation, and is not a statement about the
explanation itself.


p-value is not
P(Ho is true | getting data this extreme)
p-value is
P(getting data this extreme | Ho is true)




Suppose there is a 5% probability that a
research hypothesis (Ha) is true (prior).
You conduct the test with 90% power.
The p-value of the test is 0.04
Using Bayes’ Rule:
.05 .9 

P( Ha | data) 
 .54
.05.9   .95.04 



Scientific conclusions and business or policy
decisions should not be based only on whether a
p-value passes a specific threshold
A conclusion does not immediately become “true” on one side
of the divide and “false” on the other.
Researchers should bring many contextual factors into play to
derive scientific inferences, including the design of a study,
the quality of the measurements, the external evidence for
the phenomenon under study, and the validity of
assumptions that underlie the data analysis.




Proper inference requires full reporting and
transparency
p-values and related analyses should not be
reported selectively.
Cherry picking promising findings, also known by such
terms as data dredging, significance chasing,
significance questing, selective inference, and
“p-hacking,” leads to a spurious excess of statistically
significant results in the published literature and should
be vigorously avoided.
Example of p-hacking (from xkcd)




A p-value, or statistical significance, does not
measure the size of an effect or the importance
of a result.
Statistical significance is not equivalent to scientific,
human, or economic significance.
Smaller p-values do not necessarily imply the presence
of larger or more important effects, and larger p-values
do not imply a lack of importance or even lack of effect.
Some research journals no longer look at p-values, but
instead look at effect sizes.



By itself, a p-value does not provide a good
measure of evidence regarding a model or
hypothesis.
Researchers should recognize that a p-value
without context or other evidence provides limited
information.
A relatively large p-value does not imply evidence
in favor of the null hypothesis; many other
hypotheses may be equally or more consistent with
the observed data.




Methods that emphasize estimation over
testing, such as confidence, credibility, or
prediction intervals
Bayesian methods
Alternative measures of evidence, such as
likelihood ratios or Bayes Factors
Other approaches such as decision-theoretic
modeling and false discovery rates

Good statistical practice, as an essential
component of good scientific practice,
emphasizes:
◦
◦
◦
◦
◦
◦

principles of good study design and conduct
a variety of numerical and graphical summaries of data
understanding of the phenomenon under study
Interpretation of results in context
complete reporting
Proper logical and quantitative understanding of what
data summaries mean
No single index should substitute for scientific
reasoning.

http://amstat.tandfonline.com/doi/pdf/10.1080/00031305.2016.1154108
http://www.stat.columbia.edu/~gelman/research/published/pvalues3.pdf
http://jnci.oxfordjournals.org/content/99/4/332.full
http://fivethirtyeight.com/features/statisticians-found-one-thing-they-canagree-on-its-time-to-stop-misusing-p-values/
http://fivethirtyeight.com/features/not-even-scientists-can-easily-explain-pvalues/
http://www.vox.com/2016/5/9/11638808/john-oliver-science-studies-lastweek-tonight
http://freakonometrics.hypotheses.org/19817
http://www.bayesianphilosophy.com/the-myth-of-p-hacking/
https://bayesianbiologist.com/2011/08/21/p-value-fallacy-on-more-or-less/
https://xkcd.com/1478/