Stats Chapter 11-13

Front 1

Computing Confidence intervals

Back 1

- p hat+/- SE
-SE(p hat)= sqrt( p hat* q hat/ n)

Front 2

What does confidence intervals mean

Back 2

- We are 95% confident that the true proportion lies in our interval between p hat+/- 2SE(p hat).

Front 3

Certainty and Precision

Back 3

-increase certainty by larger margin of error
-increase precision by smaller confidence interval
-They have an inverse relationship

Front 4

Margin of error

Back 4

ME= z* sqrt(p hat* q hat/ n)

Front 5

Why do we need t-distributions?

Back 5

-there is extra variation in Standard error for small samples causing incorrect margin of errors
-with t-models, you have narrower peak than normal model and have fatter tails.

Front 6

Confidence interval for the population mean

Back 6

y-bar +/- t*(n-1) X SE(y bar)

SE(y bar)= s/ sqrt(n)

Front 7

Null hypothesis and p-value

Back 7

- A low enough p-value says that the data we have observed would be very unlikely if our null hypothesis was true; not just random chance there is evidence against the null. "reject null"
-A high enough p-value means not enough evidence to reject null. "fail to reject null"

Front 8

Alpha level and significance level

Back 8

-arbitrary threshold value for our p-value. if p-value falls below our alpha level then we will reject the null.
- "we reject the null hypothesis at the 5% significance level"