PSYC1001 Lecture Notes - Lecture 19: False Dilemma, False Alarm, Decision Rule
2 Jul 2018
School
Department
Course
Professor
23/04/2018 Practical Significance and Statistical Power
Critical cut error is 5% aka p=0.050
Normal decision rule (reject is p<0.050)
Conservative decision rule (reject if p<0.0001)
Liberal decision rule (reject if p<0.2)
The decision for statistics The null is true The null is false
Retain the null Correct (1-α) Error (Type 2) (β)
Reject the null Error (Type 1) (α) Correct/Power (1- β)
The general decision in ‘signal detection’ Nothing is there Something is there
I see nothing Correct rejection Miss
I see something False alarm Hit
The variability of the effect you are looking for (more variability = lower power)
The size of the effect you are looking for (larger effect = more power)
Sample size (larger sample size = more power)
Sample size is the one factor we have most control over – usually it is what we use to control
the power of a study - not always easy to choose the right amount of power – too little
power caused by too little participants means that the study might not be sensitive enough
to detect an effect that might be of importance – too much power caused by too many
participants might make the study too sensitive, which mean tiny effects of no practical
significance might be found
Statistical significance – usually proclaimed when the p-value is < 0.05 – use it to say the
result is unlikely to be due to chance
Practical significance – determined by the size of the effect and its application. Who cares is
the effect is reliable, is it useful? Does it matter? Is it worth spending a lot of money on?
Appeal to ignorance – involves thrusting an assertion into a region of uncertainty
False dichotomy – when a person asserts that there are only 2 possible answers
Denialism – implies a broader rejection of a series of claims or an entire body of evidence
and theories
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
The variability of the effect you are looking for (more variability = lower power) The size of the effect you are looking for (larger effect = more power) Sample size (larger sample size = more power) Statistical significance usually proclaimed when the p-value is < 0. 05 use it to say the result is unlikely to be due to chance. Practical significance determined by the size of the effect and its application. Appeal to ignorance involves thrusting an assertion into a region of uncertainty. False dichotomy when a person asserts that there are only 2 possible answers.
