A sample produced a list of 5024 licensed drivers. The investigators then chose

Question

A sample produced a list of 5024 licensed drivers. The investigators then chose an SRS of 880 of these drivers to answer questions about their driving habits. How would you assign labels to the 5024 drivers? Use Table B, starting at line 104, to choose the first 5 drivers in the sample. Driver 1: Driver 2: Driver 3: Driver 4: Driver 5: One question asked was "Recalling the last ten traffic lights you drove through, how many of them were red when you entered the intersections?" Of the 880 respondents, 171 admitted that at least one light had been red. A practical problem with this survey is that people may not give truthful answers. What is the likely direction of the bias: do you think more or fewer than 171 of the 880 respondents really ran a red light? More Fewer Why would there be such a bias? People may be concerned that they will get in trouble if they admit to running red lights Those agreeing to respond may be more likely to have more time available and thus are less likely to run red lights The test suffers from sample bias The test suffers from response bias

you can find table B here as I am not able to upload it

http://www.unc.edu/~nielsen/soci708/statistical_functions/ips6e/ips6e_table-b.pdf

Explanation / Answer

1. Since 5024 is the total number of drivers, the labels will be a 4 digit number that ranges from 0001 to 5024. Another way to do it is 4 digit number that ranges from 0000 to 5023. We will take the first way.

We will assign the first way and every driver will have the label. e.g. 2358 or 5013 or 1222 or 4784 and so on.

Method used is select the starting number from the line 104 and at a particular position in the line 104. Pick the first 4 digits and assign to the sample no. 1, if the 4 digit number is bigger than 5024 skip to the next 4 digits, if the 4 digit number is same as any of the previously selected numbers then skip to the next 4 digits. Repeat the process till you get 880 unique 4 digit numbers ranging between 0001 to 5024

To select 5 drivers, look at the line 104. Let us start from the second column. The number is 38889.

driver 1 - 3888

driver 2 - 2274 (skipped 9930, 7460)

driver 3 - 0011

driver 4 - 4816 (skipped 8584, 8487, 6752, 5739, 5592, 9400, 7699, 7191)

driver 5 - 0779

2. There will be bias in the answers. More drivers are likely to say that they skipped very less number of red signals. It is very much possible that more than 171 drivers ran the red light.

3. There is bias because there is a fear that their answers will lead

a) to convicting them of running past the red lights

b) to others judging them that they are not ethical and legally bound citizens,

Related Questions

Navigate

• Browse (All)
• Browse A
• Subjects

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.