Surveys and Questionnaires Flashcards
Surveys
composed of a series of questions that are posed to a group of subjects
T/F surveys can be conducted as a written or electronic questionnaire
True
Can also be conducted as an oral interview
Questionnaires
Structured surveys, self administered
Advantages of surveys and questionnaires
generally more efficient than interviews because respondents complete on their own time
data can be gathered from a large sample in a wide geographical distribution in a short time
standardized written forms used to reduce potential bias from interactions with the interviewer
particularly useful for assessing attitudes/values
disadvantages of surveys and questionnaires
not as useful for studying behavior that require objective observation
potential for misunderstanding or misinterpreting questions or responses
accuracy or motivation of respondent unknown
Major concerns of surveys and questionnaires
- Low Return Rate
- 60-80% excellent
- 30-60% for most studies - Self Report
- researcher doesn’t directly observe behavior
- always some potential for bias
- subject to recall bias when asked to remember past events
- generally valid for variables such as injury, mobility function, etc.
- only direct way to obtain information for perceptions, fears, motivations, and attitudes
Design of surveys
- identify questions
- formulate hypothesis
- develop a questionnaire outline
- review any existing instruments
- design the instrument
- preliminary drafts
- pilot testing and revisions
Open ended questions
ask respondents to answer in their own words
useful for asking for feelings/opinions without bias by researcher
used in pilot study to determine range or responses, then converted to MC item
difficult to code and analyze
Closed end questions
should be exhaustive and mutually exclusive
provide MC questions
easily coded and provide great uniformity across responses
doesn’t allow respondents to express their own personal viewpoints
ordinal scales
used with ordinal variables: pain measured by min, mod, severe function by min assist, mod, max, dependent
Systematic review
uses explicit methods to identify, select, appraise, and synthesize results
Narrative review
good source of information on background of a specific topic
doesn’t include a detailed description of methods/criteria used to select/evaluate articles
Meta analysis
synthesizes results as part of a systematic review
uses quantitative methods to develop single overall estimate of intervention effect
Types of bias
selection
performance
attrition
detection
Forest plots
results for meta analysis
what is direction of effect?
what is size of effect?
whether effects are consistent across studies