Construct Validity of Surveys and Polls - Survey o used when people are asked about a consumer product - Poll o used when people are asked about their social or political opinions - Surveys and polls o A method of posing questions Don't forget about the age old question of ece 3111
If you want to learn more check out ischiopubic ramus ridge
If you want to learn more check out huntington's disease has been traced to a loss of cells in the
We also discuss several other topics like 63.546 x 2
We also discuss several other topics like What does apologetic means?
If you want to learn more check out stat 110 notes
to a sample of people over the phone, in personal interviews, online written questionnaires, or online - Question format - Wording of the questions - Encouraging accurate responses Choosing Questions Format - Open-ended questions o Allow respondents to answer any way they like o Spontaneous, detailed information o Needs coding and categorization ▪ Time-consuming, difficult - Forced-choice format o People give their opinion by picking the best or more options o Frequently used in political polls - Likert scale o People are presented with a statement and are asked to use a rating scale to indicate their degree of agreement o For example, strongly agree, agree, neither agree or disagree, disagree, strongly disagree o If it does not follow this format exactly, it may be called Likert-type scale - Semantic differential format o Respondent might be asked to rate a target object using a numerical scale anchored with adjectives Writing Well-Worded Questions - Leading Questions o Leading or priming respondents to respond in a certain way o Word questions as neutrally as possible to get true opinions - Double-barreled question o Questions that ask multiple things o Don’t know which part of the question respondents are responding to o Have poor construct validity - Negative wording o Items are cognitively difficult to process o Captures memory or motivation to respond accurately o Can make surveys unnecessarily complicated o Reduce construct validity - Question Order o The order in which questions are asked can also affect the responses to a survey o Responses to earlier questions can change the way respondents understand and answer the later questions o Different versions of survey, with different order of questions Encouraging Accurate Responses - Giving meaningful responses efficiently o Self-report can sometimes be ideal - Using shortcuts o Response sets or non-differentiation ▪ Respondents adapt a consistent way of answering all the questions ▪ A type of shortcut respondents can take when answering survey questions ▪ Weakens construct validity ▪ Two types -> Acquiescence and fence sitting o Acquiescence or yea-saying ▪ Occurs when people say yes or strongly agree to every item instead of thinking carefully about each one ▪ Weakens construct validity ▪ Reverse word items ∙ A way to differentiate between respondent who is yea-saying and one who really does agree with all the items o Fence sitting ▪ Playing it safe by answering in the middle of the scale, especially when the survey items are controversial ▪ Remove the neutral option - Trying to look Good o Socially desirable responding or faking good or faking bad o Concern about giving an unpopular response o Solution ▪ Anonymity ▪ Include filler questions – mask true purpose of survey ▪ Collect friend’s ratings ▪ Implicit measure ∙ People can’t control - Self reporting “more than they can know” o Respondents unintentionally give inaccurate responses o Fail to recognize causes of own thoughts, behaviors, and feelings - Self reporting memories of event o People’s memories for the events they have participated in are not very accurate o Confidence of memory not equal accuracy of memory Is Self-report the Best or Worst option? - Ideal opinion o Demographic information o Subjective perspectives (what they think) - Only option o Measuring a non-observable trait Observational research - Researcher watches people or animals and systematically records how they behave or what they are doing Observational vs Self-report - Many researchers think behavioral data > survey data - How would participants respond to the previous types of questions in a questionnaire? o How many words do you speak a day? o How many positive/ negative comments do you (other parents) give your (their) child during hockey games? o How does your child react when you return home from work? Construct Validity of Behavioral Science - Do the observations accurately measure the variable or interest? - Measurement reliability & validity - Observations can be better than self-reports - The construct validity of observations can be threatened by three problems o Observer bias o Observer effect o Reactivity Observer bias: when observer see what they expect to see - Occurs when observers’ expectations influence their interpretation of the participants’ behaviors or the outcome of the study - Observers record what they want or expect to see, rather then what is really happening (often times, unintentional) - Affects how observers interpret behaviors they’ve watching Observer effects: when participants confirm observer expectations - When observers actually change the behavior of those they are observing, such that participants’’ behavior changes to match observer expectations Reactivity - Occurs when people change their behavior (react) in some way when they know another person is watching - Solutions o Blend in ▪ Make unobtrusive observations – that is, make yourself less noticeable ▪ For example, one-way mirrors, pretend to be causal onlooker o Wait it out ▪ Wait to make observations until targets get used to their presence, or forget about being observed o Measure the behavior’s results ▪ Instead of measuring behavior, researchers measure the traces that a behavior leaves behind ▪ Use unobtrusive data Preventing Observer Bias and Observe Effects - Codebooks o Clear rating scale, reduces bias - Multiple observers o Interrater reliability - Masked (blind) research designs o Observers are unaware of the conditions to which participants are assigned, or study’s hypotheses Observing people ethically - Study must be reviewed by the IRB. - Must obtain permission in advance to watch or videotape people’s private behavior. - If filmed covertly, must explain at the end of filming. If people object, the film must be discarded