Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
19 Cards in this Set
- Front
- Back
Population
|
collection of people / entire group interested in
|
|
Census
|
data on all the cases out there; every 10 years in USA
|
|
Sample
|
subset of cases selected from underlying total population
|
|
Population Distribution
|
• Y on x axis
• Center at MY • One standard deviation? |
|
Sample Distribution
|
a subset of the population which we have data on
• We want to use the sample to say something about the population • Y on x axis • Centered at Y Bar • One standard deviation from mean |
|
Sampling Distribution
|
a distribution of all the means we could have gotten if we sampled infinitely; the distribution of y bars (means); does NOT exist, just a hypothetical thought experiment; what could have happened if I had gotten a different mean (y bar)
• Centered at MY Bar (equals MY) • Y Bar on x axis • One standard error from Mean |
|
Parameter
|
Value used to represent certain population characteristic
• Population mean is a parameter used to indicate average value of a quantity |
|
Statistic
|
Quantity calculated from sample of data
|
|
Standard Error
|
standard deviation of sampling distribution – how far off on average we are from the mean
• sigmaY /square root N |
|
Null Hypothesis
|
comes from someone else; what you are trying to disprove
|
|
Alternative Hypothesis
|
What your hunch is; what you are trying to prove
|
|
P-Value
|
probability of observing results as supportive of alternative hypothesis or more supportive of what we got if null is true
|
|
Statistical Significance
|
when we have a p-value of less than .05; we are able to reject the null
|
|
Type I error
|
reject a true null hypothesis; worst b/c we are going against conventional wisdom and we are wrong
|
|
Type II error
|
accept false null; go along with conventional wisdom
|
|
Confidence Interval
|
likely location of population mean
• Calculated by adding lowest and highest values to original (null) value |
|
Normal Distribution
|
bell curve distribution; symmetrical around mean, has predictable area under curve, one standard deviation captures 68% area under curve, two standard devs. 95%, and three = 99%
|
|
T-distribution
|
Fatter tails than normal distribution
|
|
• T-score
|
how many standard errors Ybar is away from MY under the null
• Bigger score, then reject null |