Chapter Four Flashcards
(21 cards)
Statistical Test
Used to determine results from a sample are convincing enough to say something about the whole population
Null hypothesis
Claims there’s no effect or difference.
H0, always includes an equality
Alternative hypothesis
Claim for which we seek evidence
Ha; always includes inequality
Randomization distribution
A collection of statistics from samples simulated assuming the null hypothesis is true
P-value
Proportion of samples that, if null hypothesis is true, that would give a stat as extreme as (or more extreme than) the observed sample
The further we move from the null, the more ___ the p value
Extreme (smaller)
Possible outcomes from a statistical test
Small p-value: reject the null hypothesis in favor of the alternative
Not small value: do not reject the null
Significance level (a)
The threshold below which the p value is considered small enough to reject the null hypothesis
Statistically significant
Results are statically significant if the p value is less than the significance level ( means we can reject the null hypothesis)
The smaller the p value, the ____ the evidence against the null
Stronger
Significance level
The threshold below which the p value is deemed small enough to reject the null hypothesis
When the p value is greater than the significance level
Don’t reject the null
If the p value is less than the significance level
Reject the null hypothesis
Criteria for creating randomization samples
Be consistent with the null hypothesis
Use data in the original sample
Difference between bootstrap and randomization distribution
Bootstrap centered around the sample statistic
Randomization centered around the null hypothesis
When are confidence intervals useful?
When estimating population parameters. They give a range of plausible values
When are hypothesis tests useful?
When you want to test hypotheses about population parameters
Type I error
Rejecting a true null hypothesis (false positive)
Type II error
Failing to reject a false null hypothesis (false negative)
Decrease chances of a type I error by
Using lower significance level
Decrease chances of a Type II error
Use a higher significance level
