Lecture 5 Flashcards
What is the rejection region?
Set of potential outcomes that lead to the rejection of the null
What is the decision rule?
Area where we will decide to reject the null
What is a type 1 error?
When you reject the null when the null hypothesis is actually true (denoted as alpha)
How do you read the binomial table?
N= number of trials
Numbers on top: Probability of flipping heads in reality
How do you find a rejection region using the binomial table?
Keep going down the table until you find a number bigger than alpha, then go back one number
What is a type 2 error?
Decreasing alpha will create a possibility that you fail to reject the null, when the null is false (beta)- must have a rejection region smaller than 0.05.
What is power?
What kind of power do we have to detect a real effect? What is the probability that we will correctly reject Ho?
How does power increase?
With a larger sample size
How does one conduct a power analysis?
Establish a value of power before the experiment, use that to calculate sample size. Estimates for alpha and beta, estimates of effect size
What is effect size?
An estimate of how large the difference is between sample groups (Based on past research or pilot study)
What does it mean when we have a 95% confidence interval?
If i did this study 100 times, the true mean would be within the confidence interval 95 times
When does the P value = 0.01 on a bar graph?
When the top of the bottom bar and the bottom of the top bar line up
When does the P-value = less than 0.01 on a bar graph?
If there is a gap between the top of the bottom bar and the bottom of the top bar
WWhen does the P value = 0.05 on a bar graph?
When the two bars overlap by 1/4.
When does statistical significance happen?
When the P-value is less than 0.05, error bars must overlap by 1/4 or less.
