power analysis Flashcards
what are the limitations of alpha (.05)
It is not a measure of the magnitude of the effect
Two samples could get completely different results because they have different samples.
what is a type 1 error
think there is an effect but there isnt
what is a type 2 error
think there isnt an effect but there is
what is effect size a measure of
the magnitude of the effect independent of sample size
what is statistical power
The probability of making a type 2 error
- normally set at .80
- the probability of making a type 2 error is .20
Type 1 : Type 2 = 1:4
What does statistical power depend on?
sample size (the larger the sample the more power) Effect size Precision of measure (the more precise a measure the better it provides a measure of the latent variable)
What does a prospective power analysis asses
= a prior
A prior power analysis computes the required sample size given an effect size, power and alpha
what are the types of retrospective power analysis
- A priori
- sensitivity
- post hoc
A retrospective prior tests
the amount of participants the effect you found would need to be significant
what does a retrospective sensitivity test
the minimum effect size which could have been found given sample size, power, alpha
what does a post hoc power analysis test
the achieved power
how do you report an a priori analysis
An a priori power analysis indicated that it would be necessary to recruit __ participants per group in order to detect an effect size of d/r/f = __, with alpha set at .05, at 80% power.
how do you report a sensitivity power analysis
A power analysis indicated that that with a sample of __ in the intervention condition and __ in the control condition, it would be possible to detect a minimum effect size of d/r/f = __, with alpha set at .05, at 80% power.
how do you report achieved power analysis
The effect size for the experiment was calculated as d = __. A power analysis indicated that with a sample of __ in the intervention condition and __ in the control, and with alpha set at .05, the analysis only achieved __ power.
How do you report a post hoc analysis
The effect size for the experiment was calculated as d = 0.28. A power analysis indicated that it would be necessary to recruit at least 202 participants per condition to detect this effect size, with alpha set at .05, at 80% power.
