91Ó°ÊÓ

The following two surveys were conducted in January 1991 to assess how the American public viewed media coverage of the Persian Gulf war. Survey 1 was an Area Code 900 telephone poll survey conducted by \(A B C\) News. Viewers were asked to call a certain 900 number if they believed that the media were doing a good job of covering the war and a different 900 number if they believed that the media were not doing a good job in covering the war. Each call cost 50 cents. Of the 60,000 respondents, \(83 \%\) believed that the media were not doing a good job. Survey 2 was a telephone poll of 1500 randomly selected households across the United States conducted by the Times-Mirror survey organization. In this poll, \(80 \%\) of the respondents indicated that they approved of the press coverage of the war. (a) Briefly discuss survey 1 , indicating any possible types of bias. (b) Briefly discuss survey \(2,\) indicating any possible types of bias. (c) Can you explain the discrepancy between the results of the two surveys? (d) In your opinion, which of the two surveys gives the more reliable data?

Step by step solution

01

Discuss Survey 1

Survey 1 used an area code 900 telephone call to gather its data from viewers. Several biases could potentially exist in this survey. An example is selection bias; it only includes those with access to a phone, are watching ABC news and are willing to pay 50 cents for the call. People who do not have the means to make the call or are not motivated enough to pay 50 cents are automatically excluded from the survey. This survey also ignores the possibility of multiple votes by the same person, introducing another potential bias.

02

Discuss Survey 2

Survey 2 was conducted by randomly selecting 1500 households across the United States. This drastically minimizes selection bias as opposed to Survey 1. It is a more representative sampling of the general population's views. Despite being preferable to Survey 1, potential bias may still be present. There could be non-response bias if there were those who declined to participate in the survey or could not be reached.

03

Explain Discrepancies

The discrepancy in the results of the two surveys can be explained by the biases discussed above. Survey 1 only included people who took the effort and paid to participate which may suggest a more strongly held opinion. On the other hand, Survey 2 was a randomized survey reaching out to a wide spectrum of households, reducing the intensity and selection bias, thus reflecting a less negative view about media coverage of the war.

04

Determining the More Reliable Survey

The more reliable survey is likely Survey 2. The use of random sampling better represents the population than a self-selected audience like in Survey 1. While both surveys have potential biases, the nature of bias in Survey 1 (self-selection and potential multiple entries by the same person) makes Survey 2 a more reliable data set.

Unlock Step-by-Step Solutions & Ace Your Exams!

• Full Textbook Solutions

  Get detailed explanations and key concepts

• Unlimited Al creation

  Al flashcards, explanations, exams and more...

• Ads-free access

  To over 500 millions flashcards

• Money-back guarantee

  We refund you if you fail your exam.

Over 30 million students worldwide already upgrade their learning with 91Ó°ÊÓ!

Key Concepts

These are the key concepts you need to understand to accurately answer the question.

Selection Bias

Selection bias occurs when certain individuals in a population are more likely to be included in a survey than others, leading to skewed results that do not accurately represent the entire population. In Survey 1, the bias is evident because participants self-selected by choosing to call the 900 number. This means that their responses may not reflect the views of individuals who did not watch ABC News, did not have access to a phone, or chose not to spend 50 cents for the call. Those willing to participate may have stronger opinions, which can distort the findings.

To minimize selection bias in surveys, ensuring a sampling method that gives every individual an equal chance to participate is critical. This helps in gathering data that more accurately represents the broader population's views.

Random Sampling

Random sampling is a method used to select individuals from a population in such a way that each person has an equal chance of being chosen. This technique is crucial in reducing bias and increasing the reliability of survey results. In Survey 2, the use of random sampling by selecting 1500 households across the United States helps to ensure that the sample is more representative of the general public's views.

Random sampling is beneficial in:

• Providing a more accurate reflection of the population's opinions.
• Reducing the likelihood of selection bias.
• Ensuring diversity in the sample group, which can lead to more comprehensive insights.

By employing random sampling, researchers can better generalize their findings to a larger population.

Non-response Bias

Non-response bias occurs when individuals chosen for a survey do not participate, and these non-responders have different opinions from those who do respond. This can lead to inaccuracies in survey findings, as the collected data may over-represent certain viewpoints. In Survey 2, non-response bias is a potential concern since some households may decline participation or be unreachable.

To address non-response bias, researchers can:

• Follow up with non-responders to encourage participation.
• Ensure the survey method is accessible and convenient for respondents.
• Analyze differences between responders and non-responders, if possible, to understand the level of bias.

Efforts to mitigate non-response bias can significantly improve the validity of survey results.

Data Reliability

Data reliability refers to the trustworthiness and consistency of data collected through surveys or research studies. Reliable data should accurately reflect the views of the target population without being skewed by biases or errors. In evaluating the two surveys, Survey 2 is considered more reliable due to its use of random sampling, which provides a more comprehensive picture of public opinion.

Reliable survey data should:

• Minimize various biases, including selection and non-response.
• Be collected using consistent and standardized methods.
• Accurately reflect the diversity within the population.

By focusing on these aspects, researchers ensure that their findings are valid and can be confidently used for decision-making and policy formulation.