Statistics Interval PANIC Guide

Parameter

p is the true proportion of all (context)

Assumptions

SRS, The sample size (n) is less than 10% of the population (independent), Large Counts: np >= 10 and n(1−p) >= 10

Name

1 Prop. Z-interval

Interval Calculation

invNorm for Z-score, successes/sample size for p-hat: p-hat +- z-score * sqrt(p-hat(1-p-hat)/n)

Conclusion

We are (confidence level)% confident that the true (difference in) proportion of (context) who have (context) is between (confidence interval)

Confidence Level

If we take many, many samples of (population) and calculate a confidence interval for each, about (confidence level)% of them would contain the true proportion of (context)

Interval Containment

.50

If interval contains 0

No strong evidence of difference

If interval does not contain 0

Evidence of difference

Parameter (2-prop)

p1 - p2 is the difference in true proportion of (context)

Name (2-prop)

2 prop Z-interval