Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
60 Cards in this Set
- Front
- Back
|
Name two reasons for non-experimental and observational research
|
1. Used as initial study to start project
2. Cheaper to do than experimental and allow you to better hypothesize if there is a relationship between the variables at all and determine if it’s worth researching further. It also helps you see what relationships do exist so you might change the focus of your research based on that knowledge |
|
|
What is a disadvantage of non-experimental and observational research:
|
1. It’s not scientific so doesn’t give much info or allow for conclusions to be drawn
2. You have to identify exactly what you hope to learn from research and how you will collect data. You have to think about why you’re doing this study. |
|
|
How do you make an observational study scientific (so you can make conclusions about variable relationships)? (4 points)
|
1. Must serve formulated research purpose
2. Must be planned deliberately 3. Must be recorded systematically 4. Must be subjected to checks and controls on validity and reliability |
|
|
What do you need to do to begin observational study?
|
1. Find construct
2. Operationalize the construct 3. Identify variables 4. Pick setting and schedule and coding strategy 5. Figure out exactly how observational coding will be collected 6. Analyze data |
|
|
What is an advantage of open-ended questions?
|
Permits respondents to answer more completely and to reveal reasoning behind answers. Allows for discovery of something not anticipated by survey designers.
|
|
|
What is a disadvantage of open-ended questions?
|
Harder to code and harder for respondents to articulate and answer. Open ended are better for smaller studies
|
|
|
What are advantages of closed-ended questions?
|
Easier to code and analyze, respondents don’t need to be as articulate as in open-ended questions.
|
|
|
What are disadvantages of closed-ended questions?
|
issues being studied may be too complex to reduce to a small set of alternatives, or respondents may not agree with any offered answers. Closed ended are better in larger studies.
|
|
|
What is verification in a survey?
|
collection of items on a questionnaire designed to detect dishonest answers
|
|
|
What is visual analogue scale?
|
question that asks for response by marking line between the minimum or maximum value for the statement (agree/disagree)
|
|
|
What is the Likert Scale?
|
Asks for rating of the extent of agreement or disagreement with a statement, rating scale (measure magnitude, not just direction)
|
|
|
What does Branching items on a survey mean?
|
permits respondents to skip inappropriate items
|
|
|
What are advantages of Face to Face Surveys?
|
Easier to make sure subjects answer questions, and in appropriate order, and to see where they misinterpret question so it can be rephrased in clearer way.
|
|
|
What are disadvantages of Face to Face surveys?
|
Presence of interviewer creates social situation that may result in biased responses, more expensive, less safety for interviewers who must administer tests in unsafe locations, and more difficult to supervise interviewers
|
|
|
What are advantages of Written Response Surveys?
|
Cheap to administer, reduced interviewer bias, may be administered to group (very efficient), may be dropped off at a particular location, or may be mailed to respondents.
|
|
|
What is a disadvantage of Written Response Survey?
|
No chance of clarifying questions that might be misunderstood
|
|
|
What are advantages of computerized administration of Surveys?
|
Impersonal (reduced social desirability),
Consistent, can check for invalid responses before being submitted and warn interviewers, Can control sequencing and branching of questions, Available 24-hours a day, Cheap, Higher response rate. |
|
|
What are disadvantages of computerized administration of surveys?
|
Uncooperative participants will provide meaningless data,
Dishonest interviewers cause problems, People w/o computers can’t respond |
|
|
What are advantages of Telephone Survey Administration?
|
Low cost,
Rapid, Possibility of using computer-assisted interview, Can be conducted from central location where interviewers can be supervised. |
|
|
What are disadvantages of Telephone Survey Administration?
|
Low external validity,
Less anonymous and introduce possibility of interviewer bias, Harder to determine seriousness of interviewee, Must be relatively short. |
|
|
What are Haphazard Samples?
|
Population subgroup for whose selection the researcher uses hit-or-miss methods
|
|
|
What are Purposive Samples?
|
Nonrandom sample that is chosen for some characteristic that it possesses
|
|
|
What are convenience samples
|
Nonrandom sample that is chosen for practical reasons
|
|
|
What is the sampling frame?
|
Population as it is defined for the purposes of selecting subjects for a study
|
|
|
What is a systematic sample?
|
Probability sample that isn’t randomly selected
|
|
|
What are stratified Random Samples?
|
Random sample in which two or more subsamples are represented according to some predetermined proportion, generally in the same proportion as they exist in the population
|
|
|
What is a true experiment?
|
A research procedure in which the scientist has complete control over all aspects: the who, what, when, where, and how
|
|
|
What is a Quasi Experiment?
|
Experiment in which investigator lacks degree of control over conditions possible in a true experiment
|
|
|
What are the two basic elements of an experimental design?
|
1. Presence of control group or control condition
2. Random assignment to groups or order of conditions |
|
|
What are order effects?
|
Changes in a subject’s performance resulting from the position in which a condition appears in an experiment. More general and result from warm-up, learning, fatigue, and the like.
|
|
|
What are sequencing effects?
|
Changes in a subject’s performance resulting from interactions among the conditions themselves
|
|
|
How do you control for Order Effects?
|
Counterbalancing-arranging that each condition occur equally often in each ordinal position
|
|
|
How do you control for Sequencing Effects?
|
Arranging that each condition follow every other condition equally often
|
|
|
What is block randomization?
|
Control procedure in which order of conditions is randomized but with each condition being presented once before any condition is repeated. Useful when conditions are presented several times to each subject
|
|
|
What is Reverse Counterbalancing?
|
Method of control in which conditions are presented in order the first time and then in reverse order. Useful when you suspect confounding variables will act in linear manner over conditions.
|
|
|
What is a Latin Square?
|
Control procedure in which each subject experiences each condition in a different order from other subjects.
|
|
|
What are the advantages and disadvantages of Latin Square?
|
• Disadvantage: Controls for order but not sequence of conditions.
• Advantage: permits greater flexibility in choosing number of subjects to be tested |
|
|
What are advantages and disadvantages of two-condition research design?
|
• Advantage: all subjects experience both conditions in counterbalanced order
• Disadvantage: many experiments involve more than two conditions, also possibility of carryover effects from one condition to the other |
|
|
What is a one-group posttest only design?
|
o Research design that measures the behavior of a single group of subjects after they are given a treatment
|
|
|
What is the Posttest only design with Nonequivalent Control Groups?
|
o Nonequivalent Control Group- group of subjects that isn’t randomly selected from the same population as the experimental group
|
|
|
What is the one-group Pretest-Posttest Design?
|
o Research design that measures the behavior of a single group of subjects both before and after treatment
|
|
|
Why use multiple variable experiments? (3 points)
|
1. Efficiency: might not require much additional effort
2. You might have more than one alternative hypothesis to rule out 3. Reveals interactions among variables |
|
|
What is the "main effect"?
|
In a factorial experiment, the effect of one independent variable, averaged over all levels of another independent variable
|
|
|
What is a Synergistic Effect of interactions?
|
o Interaction in which the two independent variables reinforce each other’s effects
|
|
|
What is an antagonistic interaction?
|
o Interaction in which the two independent variables tend to reverse each other’s effects
|
|
|
What kind of design needs the least number of participants?
|
Within Subjects Design
|
|
|
How do you make observational research scientific?
|
1. Planned deliberately
2. Recorded systematically 3. Serve formulated Research Purpose 4. Subjected to checks and control of validity and reliability |
|
|
What is archival research?
|
Data already exists in some data base and is available to researchers and can be retrieved and studied. You don't do research, you create hypothesis and operationalize based on research already done.
|
|
|
What is Participant-observer Research?
|
Researcher becomes a member of group b.c observations can't otherwise be possible
|
|
|
What are advantages of observational research?
|
1. increase external validity
2. May increase construct validity 3. May generate new hypothesis or improve your hypothesis 4. May identify limitations of theories |
|
|
What are disadvantages of observational research?
|
1. Low internal validity
2. May reduce reliability of measures b/c there's no way to retest subjects 3. Still need to show generalizable to other settings |
|
|
What are common Survey Mistakes?
|
1. Poor wording
2. Surveillance (subjects know they're being watched) 3. Lack of knowledge of subject on topic 4. Appearance/demeanor of researcher |
|
|
What is a Dichotomous Question?
|
Survey question with 2 possible alternatives
|
|
|
When is a Likert Scale used?
|
When you want info about beliefs and attitudes
|
|
|
What is the Guttman Scale and when is it used?
|
Series of related items allow you to show range of opinions and when you stop answering it implies you disagree with everything that will follow. Mores useful for opinions than even Likert.
|
|
|
Good survey questions should be...
|
Mutually exclusive and exhaustive
Simple Important idea at the end of the question Chronological Specific Well worded Not double barreled Short Allows for full range of opinion to be expressed |
|
|
What is a static group design?
|
Survey in which groups are different on some IV to see how that influences dependent behavior.
|
|
|
What is a trend study?
|
Repeatedly sample from the same population but participants aren't the same. Done over long time periods
|
|
|
What is a cohort study?
|
Limited population focus, characteristics, specific to see change over time, monitor that one group and compare between cohorts
|
|
|
What is a panel design?
|
Repeated testing of same participants to study change in respondents characteristics over time
|
