Probabilities
The Unit Normal Table allows for calculation of probabilities because it is a...
The proportion of scores that are above or below a particular score.
What is probability.
Reject a null hypothesis that is actually true.
Find an effect where there actually is none.
What is Type I Error?
This is the calculation for estimated standard error.
What is:
sM = _s_
√n
This is the Mean Difference.
MD = _ΣD_
n
This is the likelihood of a specific outcome given all possible outcomes.
What is a basic probability?
The average distance all scores are from the mean.
What is standard deviation?
==DAILY DOUBLE==
These are the four steps of a hypothesis test.
When do you calculate effect size? (two answers)
1) State hypotheses (Null and Alternative)
2) Define critical region (alpha and tails)
3) Calculate z or t
4) Reject or Fail to Reject the Ho
Calculate effect size when it is significant.
Only when Dr. M asks for it.
This is the formula for finding t.
t = _M-μ_
sM
What type of study is being run for the following:
Evaluating the effectiveness of study sessions by comparing test scores before and after a session.
What is repeated-measures study?
If you have a negative z-score marked on a normal distribution, on which side will the body be when using the unit normal table?
What is right?
The larger the sample size (n), the more probable it is that the sample mean will be close to the population mean.
What is the Law of Large Numbers?
This happens when you:
Fail to reject the null hypothesis when it is actually false.
Do not find an effect when there actually is one.
What is Type II Error?
You must remember to report this when calculating a t-Statistic.
What is reporting the p value?
p< α OR p>α
Replace α with your alpha level numerical value.
This always equals zero.
What is μD.
The mean of the difference scores.
T/F: A probability MUST be a positive number.
What is True.
The distance one score is from the mean of the sample/population in units of standard deviation.
What is z-score?
This is the probability that a statistical test will correctly reject a false null hypothesis.
Also the probability that a test will identify a treatment effect if one exists.
What is POWER!
What is df (degrees of freedom) = n-1
Sample size minus 1.
These are the advantages of a related samples design.
What are:
Controls for individual differences.
Smaller sample size needed.
No need for population parameters.
Once a sample is selected, it is replaced before the next sample is selected.
What is random sample with replacement?
The natural discrepancy, or amount of error, between a sample statistic and its corresponding population parameter.
What is sampling error?
== SECOND DAILY DOUBLE ==
It is the calculation for Cohen's d.
These are the effect size for Cohen's d.
What is: (M-μ) /s
Also: mean difference/standard deviation
What are:
.2 (small)
.5 (medium)
.8 (large)
== DAILY DOUBLE == (Yes, the third one!)
This is the calculation for r2.
These are the degrees of magnitude for r2.
What is: r2 = __t2__
t2 + df
What are:
.01 small
.09 medium
.25 large
>.50 very large
This is how you find the degrees of freedom (df) for a matched participants design.
n - 1
n = pairs, not individuals.