1/11
Looks like no tags are added yet.
Name | Mastery | Learn | Test | Matching | Spaced | Call with Kai |
|---|
No analytics yet
Send a link to your students to track their progress
Confidence Interval
Range of values that is plausible for the true population parameter. Calculated by sample data!
Formula = point estimate ± margin of error
Confidence Level (C%)
How convinced we are that this interval captures the true parameter value. C is the area between 2 critical values (z*). Repeating a process = C% confident in true parameter being between confidence intervals.
Critical values (z*)
The boundaries of the confidence interval.
Formula: InvNorm( (100-C%)/200, 0, 1) = z*
There is no negatives for critical values, so make them all positive!
Interpreting Confidence Interval
“We are C% confident that the interval from ___ to ___ captures the true proportion of [context]”
Interpreting Confidence Levels
“If we take many sample sizes from this population, about __% of them will result in an interval that captures the actual parameter value.”
Conditions for Confidence Intervals
Random, Independent, and Normal
Random Condition
Randomly Selected (sampling) or Randomly Assigned (experiment)
Independent Condition
10% condition: n > 0.1N
No need to look/confirm this in experiments
Normal Condition
Large Counts Condition: np̂ > 10 and n(1-p̂) > 0.1 so the sampling distribution is approximately normal.
Standard Error
The standard deviations of our sampling distribution using p̂, not p. Shows how close p̂ will be to p in repeated SRS.
Formula: SEp̂ = { [ (p̂)(1-p̂ ) ] / n }
One Prop. Z-Int. (A)
Test for confidence intervals and confidence levels.