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;
12 Cards in this Set
- Front
- Back
One Sample T-test
|
don't know population standard deviation, use our sample to estimate the population standard deviation
|
|
Sampling dist. of population variance
|
positively skewed because we underestimate the pop standard deviation, to get it closer to normal we take a large sample --> 120 and up.
|
|
T-distribution properties
|
based off of degrees of freedom.
For each degree of freedom there is a separate t-distribution. compare our results to t-distribution |
|
T-distribution (continued) achieving accurate results
|
the larger the df, smaller the spread of dist.
the smaller the df, the wider the spread of dist. using a larger distribution means better results |
|
finding one sample t-value
|
we replace the pop. mean in the equation with the standard deviation of the sample.
|
|
Confidence intervals for one sample t-test
|
we are .95 sure that the pop mean is or is not included in the upper and lower levels
|
|
Dependent Means T-test
|
Telling the difference between time 1 and 2. No population
use control and experimental conditions or time 1 and 2 |
|
Difference formula
|
time 1 - time 2
|
|
Null and Alt. Hypothesis dependent samples
|
MD = 0
MD doesn't equal 0 |
|
Difference data
|
Take the difference between time 1 and 2 and conduct a normal t-test on it. Then look up the t-value and compare. Were trying to find out if there's a difference, so it needs to be statistically different from 0.
|
|
Confidence Intervals
|
mean of the difference +/- t-value(SD)
if 0 (the value of the dist. of the mean dif. mean) is not in between these two values you reject the null. |
|
Null and Alt. Hypothesis one samples
|
sample mean = population mean
sample mean does not equal population mean |