Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
Confidence Intervals
AP Statistics
| Term | Definition |
|---|---|
| general formula for a confidence interval | point estimate ± margin of error (A, B) |
| finding point estimate from confidence interval | take the average (A+B / 2) |
| finding margin of error from confidence interval | B-A / 2, or subtract point estimate from B |
| interpreting a confidence interval | we are (confidence level)% confident that the interval from ___ to ___ captures the true (context) |
| point estimate | statistic, p-hat, x-bar |
| describing parameter | p = TRUE proportion or mean of (context) |
| interpreting a confidence level | if we take many, many samples and calculate a confidence interval for each, about (confidence level)% will capture the true (context/parameter) |
| wider confidence interval | higher confidence level, lower sample size |
| narrower confidence interval | lower confidence level, higher sample size, less variability |
| conditions to check for confidence intervals of a proportion | SRS with context and sample size, 10% condition (n ≤ 0.1(N)), large counts condition (np-hat ≥ 10, n(1-p-hat) ≥ 10) |
| confidence interval formula for one proportion | p-hat (statistic) ± z* (CL) x √p-hat(1-p-hat) / n (standard error) |
| z* for 80% confidence level | 1.28 |
| z* for 90% confidence level | 1.64 |
| z* for 95% confidence level | 1.96 |
| z* for 99% confidence level | 2.58 |
| margin of error formula | z* or t* x standard error |
| why do we check for a random sample | ensures results are generalizable to entire population |
| why do we check 10% condition | when sampling without replacement, ensures independence, allows use of standard error formula |
| why do we check large counts condition/ CLT | ensures normality and the use of invNorm |
| choose | name procedure (1 sample z interval for p or 1 sample t interval for η), identify confidence level, state parameter |
| check | check conditions with work |
| calculate | write general and specific formula, plus in #s, find confidence interval |
| conclude | interpret confidence level in context |
| conservative estimate or no p-hat is given | use 0.5 for p-hat |
| sample size problems | always round up, fill values into margin of error formula |
| finding confidence level of one proportion in calculator | menu 6 6 5, fill in p-hat and sample size |
| t*-interval | wider than z*, use invt on calculator and degrees of freedom (df=n-1) |
| checking normality condition for means | 1. check if population is normal, then 2. check central limit theorem (n ≥ 30), if not 3. sample graph show no strong skewness or outliers (last resort) |
| formula for constructing a confidence interval for one mean | x-bar ± (t*)(s/√n) |
| using invNorm or invt to find z*/t* | type other area into calculator that isn't covered by confidence level, for t* also use df=n-1 (ex. 95% CL --> use 0.025) |
| finding confidence interval for one mean in calculator | menu 6 6 2, type in x-bar, standard error, and sample size |
Created by:
ts2819