stat 20 chap19 - Stat20 Chap 19 Sample survey 1 / 23...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
Stat20 Chap 19 Sample survey 1 / 23
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sampling In a study, investigators frequently want to know some numerical facts about a large class of individuals: predicting results of US Presidential elections predicting the number of deaths in Iraq due to the war However, studying this large class is often impractical or impossible. Only part of it can be examined, and the numerical facts of interest can only be estimated by some numbers computed from that part 2 / 23
Background image of page 2
Defnitions We call the large class of individuals the population . The numerical facts which we want to know about the population are called parameters . The examined part of the population is the sample , and the numbers computed from the sample are called statistics . We then make inference : i.e. generalize the results of the sample to the population. Good inference is only possible if the sample resembles the population. 3 / 23
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Example Suppose we are interested in the percentage of US households with access to internet population all US households parameter % of households with internet access among all US households sample e.g. all households at Berkeley statistic % of households with internet access in the sample Statistics are what investigators know, parameters are what they want to know 4 / 23
Background image of page 4
Sampling The crucial question here is: How should one pick the sample? Main lessons of this chapter: The method of choosing the sample matters a lot The best methods involve the planned use of chance, and leave no room for personal choice 5 / 23
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Ex: The Literary Digest Polls United States Presidential Election, 1936 F.D. Roosevelt (Democrat) vs. A. Landon (Republican) The magazine Literary Digest had correctly predicted the winner of the last 5 elections. Questionnaires were sent out to 10 million people, randomly selected from telephone books and club membership lists 2.4 million responses 43% of the respondents planned to vote for Roosevelt Prediction: Landon wins, and Roosevelt gets 43% of the votes Election result: Roosevelt won, with 62% of the votes. 6 / 23
Background image of page 6
LD Poll population all registered voters in the U.S. parameter
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/10/2011 for the course STAT 20 taught by Professor Staff during the Spring '08 term at University of California, Berkeley.

Page1 / 23

stat 20 chap19 - Stat20 Chap 19 Sample survey 1 / 23...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online