Question

1. Political parties rely heavily upon polling to measure their support in the electorate. Below are the results of two polls conducted in 1996 and 1997 for four political parties.

$NRjLWdV7014AAAAASUVORK5CYII=$ $QAAAAASUVORK5CYII=$

1. The polling organization selects people to participate in the poll using random-digit dialing and then uses some procedure to randomly select a member of the household called. Why doesn’t the polling organization just ask people in the nearest shopping center? (4 points)
   
   
   
2. Compute the estimated standard error for the level of support of the L party in 1996. Interpret this value. (4 points)
   
   
   

3. Construct an approximate 95% confidence interval for the level of support for the N party in 1996. Interpret this interval. (4 points)
   
   
   
4. Has the level of support for the R party changed between 1996 and 1997? Create a 95% confidence for both 1996 and 1997 for the R party.Use any summary statistics, intervals, or graphs that are appropriate. (4 points)
   
   
   
   
5. The 1996 poll interviewed 1183 people in Canada and gave a certain level of precision as shown above. What sample sizes would be required for polls in the United States (population 10 times larger) to give the same level of precision? Explain. (4 points)
   
   
   
6. This is an actual query received from a statistical consulting service.

"Can you answer a question for us regarding percentage of returns? If a survey was mailed to 4,000 households asking three simple questions and included a postage-paid return postcard, how many responses would be considered representative? Any guidance you could give would be appreciated."

How would you respond to this query? (4 points)

Answer 1

Solution :

Given that

Solution Given hat withouta ante That- The t on PPi en That 1 83 - 83 0 0139

So- Estimatad propotionCoud Vo a Given that 0.135) (0-18 So- tion Given Jhat The Lonfidanc Inkval foy 1416 in (0.186ナ0-a34 O. 2D1 to 0,247

of Sufortnhe popalation Could a 3 Ve mane4 constant) Chanpe lee Suport iv n The 38S he SAME level 3es nt The level of predi bn Analog dependn on Sampls ise &o Popult ian y uud in clay Giwen a าน he Respondents ave asdf-Scuctu Sample So popula tion