Mass Media Research: An Introduction, 8th Edition Instructor’s Manual (стр. 5 )

Researchers should consider including an incentive, notifying survey subjects beforehand, and personalizing the questionnaire to achieve a reasonable response rate. No matter what type of survey is conducted, it is virtually impossible to obtain a 100% response rate. Therefore, certain elements of the research design can have a significant impact on response rates. Monetary incentives and non-monetary incentives, preliminary notification, personalization of the questionnaire, a follow-up letter, and personal interview may increase response rate in surveys. However, a cover letter, the assurance of anonymity, and a statement of a deadline, stressing the social utility of the study, and appealing to the respondent to help the research do not seem to affect response rates.

Finally, several obstacles are frequently encountered even though surveys are valuable tools in mass media research: 1) subjects are often unable to recall information about themselves or their activities; 2) prestige bias may affect a respondent’s feeling; 3) subjects may purposely deceive researchers; 4) respondents often give elaborate answers to simple questions because they try to know what the purpose of a study is and what the researcher is doing; and, 5) surveys are often complicated by the inability of respondents to explain their true feelings, perceptions, and beliefs.

Exercises

The best way for students to understand how data collection works is to visit a research facility in your area. Most field services are happy to comply, and students will get first-hand knowledge of the interviewing process, CATI systems, and what an interviewer goes through to complete a survey. Go to www. and search for online survey form. Participate in online survey conducted by universities and private sector.

Multiple Choice

1.  Of the following, what is an advantage of survey research?

a)  A large amount of data can be collected with relative ease from a variety of people.

b)  Researchers don’t have to hire interviewers

c)  Cause-and-effect can be established

d)  Any type of respondent can be interviewed

2.  What is the CATI system?

a)  Computer Associated Telephone Institute

b)  Computer Assistant Technique Investigation

c)  Computer Aided Telephone Interviewing

d)  Computer Assigned Television Interviewing

3.  Of following, which is not recommended while designing a questionnaire?

a)  Demographic data should be placed at the first page of the questionnaire

b)  Sensitive items should be placed at the end of the questionnaire

c)  Age and gender information are usually included in the first part of a questionnaire

d)  The questionnaire should be proceed from the general to the specific.

4.  All of the following statements are accurate except:

a)  Long questionnaires cause low completion rates

b)  Shorter questionnaires do not cause respondent mortality

c)  The maximum time limit of one-on-one interview is 10 minutes

d)  Questionnaire length is determined by trial-and-error

5.  Of the following, what is an appropriate way to conduct a pretest?

a)  Use college student samples

b)  In telephone surveys, call 40-50 people and do a run-through

c)  Pretest with the type of respondent who will not participate in the actual study

d)  Conducting a mini-study with a small sample

6.  Which of the following is a disadvantage of mail surveys?

a)  Researchers must use monetary incentives

b)  Researchers are able to know exactly who answers the questions

c)  Low return rate casts doubt on the reliability of the findings

d)  Wide geographic reach

7.  In a telephone survey, the largest number of callbacks is usually made to:

a)  Ineligible respondents

b)  Answering machines

c)  Noncontacts

d)  Initial refusals

True/False

1.  There are three major types of surveys: descriptive, analytical, and cultural. (F)

2.  Surveys are not constrained by geographic boundaries. (T)

3.  The biggest disadvantage of a survey is that independent variables cannot be manipulated the way they are in laboratory experiments. (T)

4.  Group administration combines some of the features of mall surveys and computer assisted personal interviewing. (F)

Fill in the Blank

A (code book) is a menu or list of quantified responses. A (double-barreled question) is one that asks two or more questions simultaneously. Multiple-choice responses must be (mutually exclusive) to enable a respondent to check a response that appropriate to his/her situation. (Screener questions) or (filter questions) are used to eliminate unwanted respondents or to include only respondents who have specific characteristics or who answer questions in a specific manner. (Disk-by-mail surveys or DBM) refers to a survey in which respondents are sent computer disks that contain a self-administrated questionnaire, and they are asked to complete it by using a personal computer.

Short Answer

Compare and contrast mail surveys and telephone surveys. Discuss some general dos and don’ts about writing questions in ppose you are going to use the survey research method to investigate children’s perceptions toward a certain action figure (i. e., Power Rangers, PokeMon, or Barbie doll) on TV. Who would you use in the pretest? What pretest questions would you include?

Chapter 8 - Longitudinal Research

Overview

This chapter introduces longitudinal research. Although relatively rare in mass communication research, this research method involves the collection of data at different points in time. Longitudinal techniques are divided into three different types: 1) a trend study in which different people are asked the same question at different points in time; 2) a cohort analysis involves the study of specific populations, usually all born during a given period, as they change over time; 3) a panel study uses the same individuals who are interviewed several times.

There are several different statistical methods available for this method. Usually, path analysis, log-linear methods, and structural equations are used as statistical techniques to conduct longitudinal analysis.

The three main types of longitudinal studies have advantages and disadvantages. With trend studies, researchers can establish a pattern over time to detect shifts and changes in an event. Another advantage is that trend studies can be based on a comparison of survey data originally constructed for other purposes. Meanwhile, this technique has a vulnerable point. If data are unreliable, a false trend will show up in the results. Trend analysis must be based on consistent measures.

Cohort analysis provides insight into the effect of maturation and social, cultural, and political change. In addition, it can be used with either original data or secondary data. In many instances, this technique can be less expensive than an experiments or a survey. However, this technique can’t completely remove the specific effects of age, cohort, and period from a standard cohort table. In addition, a second disadvantage of the technique is sample mortality.

Panel studies can be useful in answering questions about the dynamics of change. This approach helps solve the problems normally encountered when testing an hypothesis based on a one-shot case study. On the negative side, panel members are often difficult to recruit. In addition, respondents often become sensitized to measurement instruments after repeated interviewing, thus making the sample atypical. Finally, respondent error is always a problem.

It is possible to combine quantitative and qualitative data in a study that extends over time. They point out that this combined technique has certain advantages: 1) the qualitative data can aid in the interpretation of the quantitative data and provide insights that might have been missed; and, 2) qualitative data might suggest new hypotheses that might be examined in subsequent waves of data collection.

This chapter also looks at longitudinal research on the Internet. Using the Internet has both advantages and disadvantages. With the Internet, researchers can recruit a large number of individuals, and the Internet makes it easier for researchers to target and collect data from low-incidence groups. In addition, data collection over the Internet is rapid. However, Internet panels may not be representative of the entire population. Internet panels also get bored or lose interest and drop out as time goes by.

Finally, it is possible to build in a longitudinal dimension to experiments.

Exercises

After dividing your students by gender, and ask them to report the number of times they visited video game arcades per week according to a specific point of time in the past (e. g., when they were 12 years old, 16 years old, and 20 years old). Compare the numbers and discuss age effect and period effect. Let your students select a longitudinal research paper published in an academic journal and present the research findings in class.

Multiple Choice

The first longitudinal study in mass communication area analyzed:

a)  An advertising campaign

b)  A presidential election

c)  Television viewing

d)  Violence in media

Which of the following is not one of the types of longitudinal studies?

a)  Trend studies

b)  Panel studies

c)  Period studies

d)  Cohort analysis

While conducting longitudinal studies, researchers use some advanced statistical techniques including all of the following except:

a)  Chi-square

b)  Path analysis

c)  Structural equations

d)  Log-linear models

Which of the following is not an advantage of trend studies?

a)  Can establish a pattern over time to detect shifts and changes in some event