1 / 11

Ch. 20 Chance errors in sampling

Ch. 20 Chance errors in sampling. Finding the EV and SE of a percent Our temporary assumptions are that we know how to find the average & SD of a box.

becky
Télécharger la présentation

Ch. 20 Chance errors in sampling

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Ch. 20 Chance errors in sampling • Finding the EV and SE of a percent • Our temporary assumptions are that we know how to find the average & SD of a box.

  2. Example 1: We have a group of 100,000 people, of which 20% have college degrees and 80% do not. Suppose we draw an SRS of 100 people. Fill in the blanks: The percent of college educated people in the sample is around ____, give or take ____ or so.

  3. Set up the box model and determine how many tickets there are of each type. • Find the average, SD of the box, EV of the sum, SE of the sum. • Change to percents.

  4. In general, EV of percent = (EV of sum)/(sample size)x100% SE of percent = (SE of sum)/(sample size)x100% • A flaw in SRS is that it is not realistic. If the population size is large compared to the sample size, EV & SE are good approximations. (Correction for SE discussed later & EV doesn’t need to corrected. See Ex. A #4 solution)

  5. EV & SE for percentages depend on average and SD of box and sample size, not population size. • EV for percentage for sample is equal to population percent. • Increasing the sample size increases the EV of sum and increases the SE of sum, but more slowly than EV. • Increasing the sample size has no effect on EV for percent but the SE for percent goes down.

  6. Example 2: Same situation as Example 1 except the sample size is 400.

  7. Activity: Work in pairs on Exercise Set A #2, 6 p. 361 #2. A university has 25,000 students, of whom 10,000 are older than 25. The registrar draws an SRS of 400 students. a) Find the EV & SE for the number of students in the sample older than 25. b) Find the EV & SE for the percentage of students in the sample older than 25. c) The percentage of students in the sample who are older than 25 will be around ____ , give or take ______ or so.

  8. #6. 900 draws are made at random with replacement from a box which has 1 red marble and 9 blue ones. The SE for the percentage of red marbles in the sample is 1%. A sample percentage which is 1 SE above its EV equals: _________ CHOICES: • 10%+1% (2) 1.01x10% Explain.

  9. Using the Normal Curve • Example 3: Return to Example 1. Estimate the chance that more than 22% of the sample will have college degrees. • Why is it okay to use the normal curve for estimates? We know that it is okay for sums and a percent is just a re-scaling of a sum.

  10. In our college degree example, the variable was qualitative, so the variable was clear cut. Compare this to the example in the book on p. 363. Here the variable is quantitative and the cut-point is arbitrary. This could lead to potential interpretation issues and possibly biases results. • Note: We do not yet have a way to work with average income in a sample, just net income.

  11. Correction factor • SE when drawing without replacement = (correction factor)x(SE when drawing w/o replacement) Correction factor = sqrt(# tickets in box - # of draws)/(# tickets in box – 1)

More Related