Nov. 21st/26th - Chapter 7 CONT. Flashcards
READINGS
Surveys:
Formatting the questionnaire
- Should appear attractive and professional
- Presented in clear font, free of spelling errors
- Respondents should find it easy to identify questions and their corresponding response options
- Leave enough spaces between q’s so that people don’t become confused when reading the questionnaire
- Consider q order: most interesting first
- Stay concise
- In a survey with multiple questionnaires, randomizing the order of questionnaires
- Randomizing order of items (q’s) helps evenly distribute effects of fatigue or order
- Should be optimized to improve response rates in online surveys
- Consider the necessity of every question you plan on including
Administering Surveys
2 main ways to administer surveys:
- Questionnaire format
- Respondents read q’s and indicate their responses on a paper or online form
- Interview format
- An interviewer asks the q’s and records responses from the verbal interaction
For EITHER Questionnaire or Interview format, there are a number of challenges that emerge when you use the same participants repeatedly; ISSUES COMMON TO ALL STUDIES THAT USE A WITHIN-SUBJECTS DESIGN OR HAVE A LONGITUDINAL COMPONENT
- Maintaining confidential records
- Changes in an institution or even society at large might influence responses recorded over a period of time (EX: university funding cuts)
- Participants won’t all stay in the study as time goes on - some inevitably drop out of the study over time: A sample that starts out random or representative of a population can actually become biased over time, it it’s not entirely random who drops out versus who decides to stay
Questionnaires
- Present respondents with questions in written format, and answers are written out or typed into an online form
- Q’s can be administered in person to groups or individuals, through the mail, on the internet, or through mobile devices
Questionnaires
Questionnaires - Benefits
- Low cost
- Allow respondent to be completely anonymous, as long as no identifying information is asked
- Anonymity might encourage more honest answers to q’s
Questionnaires
Questionnaires - Cons
- Require p’s to be both motivated and attentive to complete q’s properly
- Some may have difficulty reading and understanding q’s
- This case, useful to administer survey in-person
Questionnaires
Person administration to groups or individuals:
Advantage?
- Researchers are able to distribute questionnaires to groups of individuals
- EX: university class, parents attending a school meeting
Advantage:
* Having a captive audience that is likely to complete the questionnaire once they start it
* Researcher is present, people can ask q’s if necessary
Questionnaires
Mail surveys:
Disadvantage?
Paper surveys can also be mailed to individuals at a home or business address
Disadvantage:
* Low rate of responding; can be easily ignored
* Even when filling out q’s, something may distract p’s, have difficulties with the q, or may become bored and simply throw the form in the recycling bin
Questionnaires
Internet surveys:
Advantages and Disadvantages
Easy, inexpensive, most common approach for delivering surveys
Advantages:
* Responses can be downloaded immediately (better than manually analyzing)
* Researchers and polling organizations can build **databases of people interested in participating in surveys who they can email **with an invitation to participate and, if appropriate, to forward the link to other potential participants
* Easily advertisable - Target ads
* Can be combined with other technologies to gather data
Disadvantages:
* Will results be similar to what might be found using more traditional methods?
* However, been found that data collected on the internet are comparable to that collected in person
* True characteristics of respondents are ambiguous
* To meet ethical guidelines, researchers usually state that only 16 years of age or older
Interviews - person-to-person interaction
The fact that an interview involves an interaction between people has important implications:
- People are often more likely to agree to answer questions for a real person than to answer a mailed questionnaire
- Response rates tend to be higher when interviews are used compared to questionnaires
- Interviewer and respondent can establish a rapport that helps motivate the person to answer all the questions, rather than leave questions unanswered
Interviews: Advantages
- Interviewer can address any problems the person might have in understanding questions
- An interviewer can ask follow-up questions if needed for clarity
Interviews: Problems
Interviewer bias: term summarizes all of the different biases that can arise from the fact that the interviewer is a person interacting with another person
* EX: interviewer could subtly influence the respondent’s answers by inadvertently showing approval or disapproval of certain answers
Interviewer must be skilled in working with groups to facilitate communication and to deal with problems that may arise
Interview Methods
3 methods of deliverance:
- Face-to-face
- Telephone
- Focus group
Interviews - 3 methods of deliverance
Face-to-face
Face-to-face: require that the interviewer and respondent meet to conduct the interview
* Tends to be expensive and time-consuming
* Thus, more likely to be used when sample size is fairly small and when there are clear benefits to a face-to-face interaction
Interviews - 3 methods of deliverance
Telephone:
- Typically used for large-scale surveys
- Less expensive
- Allow data to be collected quickly, as researchers can work on the same survey at once - directly entering data
Interviews - 3 methods of deliverance
Focus Group
Interview with a group of about 6-10 people brought together for a period of usually 2-3 hours
* Often, group members are selected because they have particular knowledge or interest in the topic
* As the focus group requires people to spend time and money travelling, there’s typically an incentive to participate
Q’s tend to be open-minded, asked of the WHOLE group
Focus Group - Advantage
People can respond to one another, one comment can trigger a variety of responses
Interpreting Survey Results:
Population and Samples
Population: a set of people of interest to the researcher
* Can be any group of people
* Small populations - easy to study EVERYONE within it
* Most commonly, populations too big to be possible
* Thus, researchers collect data on a sample of the population in an attempt to learn something about the larger population from which the sample was drawn
- With proper sampling, information from respondents can be obtained to estimate characteristics of the population
- NOTE: more of the population sampled, the more confident we can be that the results we would observe were able to test everyone in the population
Interpreting Survey Results
Confidence Intervals:
Basic Definition
- When researchers make inferences, or estimates, about a population using a sample, they do so with a certain degree of confidence: since we’re only making informed guesses, we’re never 100% certain
- Whenever we see an estimate, we should wonder about the uncertainty that surrounds this estimate
- One way to quantify uncertainty is through a confidence interval: EX - an estimate for an average approval rating of 61% might also report a 95% confidence interval between 58 and 64%
