{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

April19 - Random Samples Our purpose in drawing samples is...

Info icon This preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
Random Samples Our purpose in drawing samples is to make inferences about the populations from which our samples are drawn Random selection, however, will produce varying estimates from one sample to another But these multiple estimates (if we draw multiple samples) themselves take on the shape of a normal distribution, which we can use to determine how close any single sample’s estimate is to the population parameter and with what confidence
Image of page 1

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

View Full Document Right Arrow Icon
Randomization, response bias, and sampling bias: a famous example Literary Digest mailed 10 million surveys in 1936 and asked whether respondents planned to vote for Alfred Landon or FDR for president. Received 2.4 million replies Predicted results: Landon would receive 52% of popular vote and 370 vs. 161 electoral votes for FDR
Image of page 2
The 1936 Election Results Electoral College Votes Landon FDR Literary Digest Predict’n 370 161 Actual results 8 523 What went wrong here?
Image of page 3

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

View Full Document Right Arrow Icon
1936 Literary Digest Survey Response bias: 24% completion rate Sampling bias:
Image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}