Reading...
Play button
Play button
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;
22 Cards in this Set
- Front
- Back
|
Estimation (inferential statistics) allows to calculate, what?
|
Confidence intervals regarding the true population mean
|
|
|
What is a Confidence interval?
|
the window between which you can be relatively certain that the true population mean falls- the population parameter
|
|
|
the mean +/- 2SE = what percentage CI?
|
95%
|
|
|
How do you calculate SE?
|
SD divided by the square root of n
|
|
|
a 99% CI has how man SE of the mean?
|
+3 -3
|
|
|
What does hypothesis testing allow us to do?
|
estimate the probability of a given result assuming the null is true
|
|
|
in hypothesis testing, there are features of the raw data included in calculations. What are usually included?
|
1. mean of groups
2. variance of groups 3. standard deviation 4. standard error |
|
|
what does a p-value represent
|
the probability of obtaining that value assuming the null hypothesis is true
|
|
|
the higher the observed statistic (p-value)
|
the more unlikely that it could occur by chance factors alone
|
|
|
What is the ultimate endpoint regarding determining statistical significance?
|
p value
|
|
|
In order to determine statistical significance, what must you compare the p value to?
|
the alpha value
|
|
|
alpha level
|
a p value chosen by the researcher to determine significance level
|
|
|
What 2 values are usually set as the alpha values?
|
0.05 or 0.01
|
|
|
If a p-value is < or equal to the alpha-value, then that result is considered to be
|
statistically significant
|
|
|
can you prove the null?
|
no
|
|
|
what can a p-value allow you to do to the null hypothesis?
|
reject it
or fail to reject it |
|
|
What is the most stringent alpha value possible?
|
0.01
|
|
|
If a value is statistically significant, then you can conclude that
|
the result was unlikely due to chance or sampling error, thus was "real"
|
|
|
if something is considered to be meaningful, then that is describing
|
clinical significance
|
|
|
You get a result that your value is statistically significant. Therefore you conclude that:
a. it is clinically significant b. it is not clinically significant c. it may be clinically significant |
c. it MAY be clinically significant- this is a judgement call
|
|
|
a type I error refers to:
|
rejecting the null hypothesis when it is actually true
|
|
|
a type II error refers to:
|
retaining the null (fail to reject it) when it is actually false.
|
