IRM Lecture 1
Quiz yourself by thinking what should be in
each of the black spaces below before clicking
on it to display the answer.
Help!
|
|
||||
|---|---|---|---|---|---|
| What are the two stages of answering surveys? | The judgement phase and the response translation phase.
🗑
|
||||
| What is the judgement phase? | In survey answering, it is the first phase whereby the participant thinks about the question
🗑
|
||||
| What is the response translation phase? | In survey answering, it is the second phase whereby a participant translates their internal psychological state into some kind of value on a response scale.
🗑
|
||||
| How does one word survey questions such that the participant is able to understand it? | 1. Read the research literature to find out how other researchers approached the problem
2. Consulting a panel of experts who know a lot about these people
🗑
|
||||
| What is pilot testing? | They are practice studies that are designed to help researchers refine the measures of manipulations they wish to use in the real study.
🗑
|
||||
| What is a focus group? | A small but representative sample of participants from the group a researcher wishes to understand that meet together and discuss their experiences, led by the researcher.
🗑
|
||||
| What is the difference between open-ended questions and structured self-report questions? | Open-ended questions allow people to respond however they see fit, but structured self-report questions force people to use a specific response scale e.g. circling a number.
🗑
|
||||
| How can open-ended questions help in survey items? |
1. They can be used to refine structured ratings scales (wording etc)
2. They can be used as primary source of data
🗑
|
||||
| In what ways are structured self-report questions better than open-ended questions? | 1. They provide meaningful numbers
2. Unlike open-ended questions, they do not need to be coded painstakingly by teams of raters to be used as data
3. They avoid the problem of irrelevant responses.
🗑
|
||||
| How should questions be worded? | They should be worded clearly and simply (using informal and understandable language)
🗑
|
||||
| What should be avoided when writing survey items? | -Negations (both single and double negatives)
-Forced-choice items
-Questions that do not yield everyone in the same way (answered by everyone in the same way)
-Loaded questions
-Double-barreled questions
🗑
|
||||
| What are double barreled questions? | Questions that ask for the participant to evaluate two different things with a single response
🗑
|
||||
| What are forced-choice questions? | Questions that ask the participant to choose between two or more options.
🗑
|
||||
| What is a restriction of range? Why should they be avoided? | It occurs when people's scores on a measure have little or no variation. They make it difficult to find anything that will predict people's scores on that measure.
🗑
|
||||
| What is a floor effect? | They occur when everyone responds at the same low level on a question.
🗑
|
||||
| What is a ceiling effect? | They occur when everyone responds at the same high level on a question.
🗑
|
||||
| What are the ways of solving restriction of range? | 1. Adjust questions or response scales accordingly
2. Use hyperbole
🗑
|
||||
| What are loaded questions? When can they be used? | Questions that indicate in their wording which response the researcher considers most desirable.
They can be used when researchers wish to get people to respond to questions about topics that are inherently loaded e.g. politics
🗑
|
||||
| What are the ways to get participants to respond as optimally as possible? | -Making sure questions are relevant to everyone in your study
-Writing multiple questions to assess the same construct
-Using positively worded and negatively worded questions that assess the same construct
-Establish a judgement context
🗑
|
||||
| In making sure questions are relevant to everyone in their study, researchers should also write questions that are gender neutral and culturally unbiased. Why? | 1. Construct validity: If the perspective of the questions ignore the thoughts and feelings of a significant portion of the sample, that portion would not provide useful data.
2. Need to consider the fact that there is diversity in a sample.
🗑
|
||||
| Why must one write multiple questions to assess the same construct? | Idiosyncratic sources of noise associated with each question is cancelled out by noises from other questions, thus increasing the reliability of the construct.
🗑
|
||||
| What are positively worded and negatively worded questions? | Positively worded questions are questions that are designed to be rated more strongly by people who are high on a construct, while negatively worded questions are questions that are designed to be rated more strongly by people who are low on a construct.
🗑
|
||||
| Why should negatively worded questions be used in addition to positively worded questions? | Response bias (yay-saying) can contaminate people's responses.
🗑
|
||||
| Why should a judgemental context be included? | People evaluate things relative to other things.
🗑
|
||||
| How can researchers establish a judgemental context for survey items? | 1. Include instructions that establish the appropriate instructions
2. Include warm-up/practice items at the beginning of the survey
🗑
|
||||
| What is another purpose for warm-up questions, other than establishing a judgmental context? | They can be used to get people to open up about sensitive topics.
🗑
|
||||
| How can one ensure that participants are comfortable during question answering? | - Easing them into sensitive questions
- Asking sensitive questions sensitively
- Guaranteeing participants' anonymity.
🗑
|
||||
| What is the best way to ask sensitive questions? | Ask easy or innocuous questions first and ask the sensitive questions later when they would feel more comfortable
🗑
|
||||
| Why should one ask sensitive questions sensitively? | 1. It will decrease the likelihood that people would answer dishonestly.
🗑
|
||||
| How should sensitive questions be worded? | They must be clear about what they mean and they must not be phrased in ways that are pejorative or judgemental
🗑
|
||||
| How should one reassure participants that they will be anonymous? | Written and verbal isnstructions must say:
1. No interest in the responses of any one person
2. The participants should not include personally identifying info on survey
3. Responses will only be seen by researchers entering and coding the data
🗑
|
||||
| What should researchers consider when designing a scale? | 1. How many numbers to use
2. What anchors to use (that create scales with equal appearing intervals)
3. What the best numbering system is to be used
🗑
|
||||
| How many numbers should be used on a scale? | There should be between 3 and 10 response options. Optionally: scales should permit optimal middle range of responses.
🗑
|
||||
| What are anchors? | Adjectives that lend meaning to the numbers on a scale. (e.g. completely agree, completely disagree)
🗑
|
||||
| What anchors should be used in a scale? | Middle anchors and endpoint anchors
🗑
|
||||
| What is an "equal appearing interval"? | It is when the psychological distance implied by a one-unit difference on the rating scale remains constant across the entire range of the scale e.g. "space" between 1 and 3 = "space" between 4 and 6
🗑
|
||||
| Why are adverb modifiers such as "very" or "extremely" used as anchors? | They convey the same information regardless of what question they are used for.
🗑
|
||||
| Why do scales usually have numbers that have no anchors between numbers that do have anchors? | This allows participants to "split the difference" between two responses if they're unable to decide between two anchors.
🗑
|
||||
| Why do scales usually incorporate the question into the response e.g. "how satisfied are you" -> "very satisfied"? | It helps keeps respondents focused on what question they are answering.
🗑
|
||||
| What are unipolar and bipolar scales? | Unipolar scales ask respondents to make ratings on dimensions that begin at a low value and move upwards. Bipolar scales ask respondents to rate a dimensions that deviates in both directions (e.g. -1 and +1 from 0) from a zero point.
🗑
|
||||
| Why are bipolar scales allowed, despite usually having more than 10 responses? | This is due to the usual response process.
1. Participants decide where they fall in relation to the midpoint
2. They then use only the side of the scale that is appropriate for their rating.
🗑
|
Review the information in the table. When you are ready to quiz yourself you can hide individual columns or the entire table. Then you can click on the empty cells to reveal the answer. Try to recall what will be displayed before clicking the empty cell.
To hide a column, click on the column name.
To hide the entire table, click on the "Hide All" button.
You may also shuffle the rows of the table by clicking on the "Shuffle" button.
Or sort by any of the columns using the down arrow next to any column heading.
If you know all the data on any row, you can temporarily remove it by tapping the trash can to the right of the row.
To hide a column, click on the column name.
To hide the entire table, click on the "Hide All" button.
You may also shuffle the rows of the table by clicking on the "Shuffle" button.
Or sort by any of the columns using the down arrow next to any column heading.
If you know all the data on any row, you can temporarily remove it by tapping the trash can to the right of the row.
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
Created by:
TheSouthDeservedMore
Popular Computers sets