4 Flashcards
(23 cards)
Hypothesis testing?
How unusual is it to get our data if the null hypothesis is true
!!!!How to undergo hypothesis testing?
•Imagine if the hypothetical population (null hypothesis H_0 true).
•generating a distribution of
Hypothesis testing usually assumes that sampling is?
Random
Null hypothesis?
Specific statement about a population parameter made for the purposes of an argument.
Alternative hypothesis?
Another possible possibility.
Test statistic?
Number calculated to represent the match between a set of data and a null hypothesis. In other words, if n exceeds the test statistic, the null hypothesis can be rejected since the values are extreme.
If the value of the test statistic is approaching y = 0 under the null hypothesis, then?
It is surprising.
P-value is the?
Probability of getting the data or smth as or more unusual if the null hypothesis were true in a test statistic.
Null distribution?
For a test statistic, is the probability distribution of alternative outcomes when a random sample is taken from a hypothetical population in which the null hypothesis is true.
If the null distribution approaches x = +-oo, then?
The null hypothesis is more likely to be disproved.
Statistical significance (alpha)?
Probability used as a criterion for rejecting the null hypothesis.
Alpha is often set as?
0.05, 1/20, which means that its okay for 5% extreme values.
If P < alpha, then?
We can reject the null hypothesis.
What does a p value mean?
Probability of getting the results if the null hypothesis is true.
Type 1 error?
When rejecting a true null hypothesis since the p value calculated was low enough to reject. (Does not depend on sample size because the test takes into account of sample size)
P-hacking
Type II error?
Not rejecting a false null hypothesis. If null hypothesis is false, the probability of a Type II error is beta. The smaller beta, the more power a test has. Beta is lower with a larger sample size.
Power?
Ability of a test to reject a false null hypothesis.
Power = ?
1 - beta
Why do we usually don’t know beta?
Because we don’t know the truth
A larger sample size will tend to give an estimate with a larger/smaller confidence interval?
Smaller
Critical value?
Value of a test statistic beyond which the null hypothesis can be rejected.
Statistically significant?
When p < alpha
