This preview shows page 1. Sign up to view the full content.
Unformatted text preview: Z
score [in the direcDon you care about!] a) That percentage = power Power = 59.87% 0.58 0.74 0.9 1.06 1.22 .94 Shaded region is power Opposite shaded region is beta β Z = 0.25, Raw = 0.94 4. Using the normal curve table, determine the probability (percentage) of geeng a score more extreme than that Z
score [in the direcDon you care about!] a) That percentage = power Power = 59.87% b) Beta is the opposite of power (β = 100%
Power) β = 100%
59.87% = 40.13% 0.58 0.74 0.9 1.06 1.22 .94 Shaded region is power Opposite shaded region is beta β Z = 0.25, Raw = 0.94 So what does this mean?? Power = 59.87% β = 40.13% Power is the probability that a study will produce a staDsDcally signiﬁcant result if the research hypothesis is true. Our study design has about a 60% chance of ﬁnding a signiﬁcant result. Beta is the probability that we will fail to reject the null hypothesis, when in reality the null hypothesis is false. Our study design has about a 40% chance of making a Type II error. 13 9/29/13 0.58 0.74 0.9 1.06 1.22 .94 Shaded region is power Opposite shaded region is beta β Z = 0.25, Raw = 0.94 Shaded region is alpha 0.88 1.04 1.2 1.36 1.52 Z =
1.645, Raw = 0.94 Power is inﬂuenced by: 1. Eﬀect size 2. PopulaDon standard deviaDon 3. Sample size 4. Signiﬁcance level 5. One
vs. Two
tailed tests 1. Eﬀect size The greater the predicted mean diﬀerence, the more power you have. This is due to less overlap between the distribuDons (so easier to ﬁnd an eﬀect) 14 9/29/13...
View
Full
Document
This note was uploaded on 03/24/2014 for the course PSY 21201 taught by Professor Bernard during the Winter '13 term at SUNY Stony Brook.
 Winter '13
 bernard
 Psychology

Click to edit the document details