7 - Samples, Proportions, Confidence Intervals

Distribution of a Sample Proportion

1. Calculate SE to estimate how theoretical sample proportions cluster around pop proportion

2. Distribution of theoretical sample proportions is affected by sample size

3. Larger sample - closer sample proportions cluster around pop proportion

Estimating Standard Error of a Proportion

Calculating SE for a Proportion

Point Estimates

Estimate of a population mean

1. SM based on a random sample is not equal to pop mean (but best estimate we have)

2. Calculate Confidence Interval - interval estimate to give us greater confidence

Confidence Intervals

Interval for which we can say with a certain level of confidence that the value we’re trying to estimate lies between 2 values

1. 95%

2. 99%

Distribution of Sample Proportions/Means

Confidence Intervals with Proportions

Rules of Confidence Intervals

1. Pop SD should be used to calculate CI (but we don’t have this data)

2. Use sample SD as Reasonable Estimate of pop SD if:

   *Data is normally distributed

   *Or sample size greater than 30

Conclusions