Intro to Research Midterm Study Guide
Intro to Research Midterm Study Guide
Popular in Intro to Research Methods
Popular in Department
This 11 page Study Guide was uploaded by Kim Notetaker on Wednesday October 5, 2016. The Study Guide belongs to at Armstrong State University taught by in Fall 2016. Since its upload, it has received 20 views.
Reviews for Intro to Research Midterm Study Guide
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 10/05/16
PSYC 2200 Study Guide – Midterm Exam I. The Scientific Approach, Hypotheses, and Theories (Ch. 1 and 2) Why study behavioral research methods? o To be good producers and consumers of research. The job of a research producer Act as an empiricist by systematically observing the world. Test theories through research and adapt those theories based on resulting data. Use research to examine both basic and applied research. Test why, when and for whom. Make your work public by submitting to academic journals. Talk to the media about your work. o Empiricism: using evidence from the senses or instruments that aid the senses as the basis for conclusions o Theoryhypothesisdata cycle Theory: set of statements that describes general principles about how variables relate to another. Hypothesis: a way if stating the specific outcome, the researcher expects to observe if the theory is correct. Data: a set of observations to test your hypothesis. HARKing: Hypothesizing After Data Is Known. When you write about research, should you tell a good story or every detail of the research? Characteristics of a good theory Supported by data: You are often slow to give up a theory (Kuhn’s paradigm shift). Falsifiability: the possibility of collecting data and proving a theory wrong. Parsimony: “all things being equal,” which means that simple is best. o Types of research questions Basic research: the goal to enhance the general body of knowledge. PSYC 2200 Applied research: conducted with a particular problem in mind with the hope of improving things. The data is applied to the problem. Translational research: when you use lessons from basic research to develop and test applications. o Questions about why, when, and for whom Mediating variables: explaining why A is related to B (cause). Moderating variables: identify when and for whom a is related to B. o Talking to the media Pros A bigger audience. Help people. People learn what you actually do. Cons Often misquoted. Often misinterpreted. Often misses the point. Other ways of learning about human phenomena o Experience Comparison groups: this allows us to compare what would happen to both groups with and without the thing you are interested in. Confounds: these are alternative explanations for the same effect. Probabilistic nature of research: you can’t take into account enough cases to be sure of the cause and the effect. o Intuition Availability heuristic: things that easily come to mind seem more likely. Confirmatory hypothesis testing: asking questions in a way that you get the answer that you want. Bias blind spot: belief that one will not be biased but they are. o Authorities: can’t always trust them. II. Defining Variables & Introduction to the Four Validities (Ch. 3) PSYC 2200 Variables: anything you can measure or manipulate. o Levels: the value of the variable in the study. o Constants: something in the study that you can change but will not change and it has only 1 level. o Measured variables: a variable that is observed or recorded as it occurs naturally. o Manipulated variables: the variable that the researcher controls and changes. o Dependent variable: the outcome variable; always measured and never manipulated. o Independent variable: the predictor variable; always manipulated but can be measured. o Defining variables Conceptual definition: the precise definition or description of the construct. Operational definition: the specific way a variable will be manipulated or measured. Validity of a study’s conclusions o Definition of validity: the appropriateness of the conclusion or the decision. o Construct validity: how well did the researcher operationalize (use) each variable? o External validity: how well do the results generalize or represent the people outside the study? o Internal validity: in the experiment; how sure are you that the change in the dependent variable is from the independent variable? Confounds: a possible alternative explanation for a research finding. o Statistical validity: how well does the number data support the researcher’s conclusion? Margin of error: indicates the probable true value in the population. Statistical significance: the probability that some of the results occurred by chance or that the result from the sample is so extreme that it couldn’t have come from the population. PSYC 2200 Type I errors: false alarm or a false positive; saying a relationship exist when one doesn’t. This error is more tolerated than a type 2 error. Type II errors: false negative; saying that no relationship exists when one does. III. Introduction to Measurement (Ch. 5) Scales of measurement o Nominal: values are just labels and categories. An example would be, are you happy? Yes or no o Ordinal: the rank ordering and the amount of space between the ratings doesn’t matter. o Interval: the equal differences between the numbers reflects the equal differences on the dimension being measured. This has NO true zero or absolute zero. An example would be how happy you are on a scale of 17. 1 being the least happy and 7 being the most o Ratio: the interval scales plus a ‘true zero.’ This is a good measure of behavior. An example would be asking how many times did you feel happy today? Reliability of measures o Reliability: the consistency, stability or dependability of a measure. o Correlation coefficients: measures the strength and direction of the association between 2 variables Strength: how well can you predict one thing by knowing about the other? (ranges from 0 to +/ 1) 0 = no correlation .1 .3 = small correlation .3 .5 = medium correlation .5 or larger = large correlation Direction: as one variable goes up does the other variable go up or down? o Testretest reliability: the consistency of the results over time. o Interrater reliability: consistency over observers. PSYC 2200 o Internal reliability: consistency over observers. Cronbach’s alpha: Step 1: Compute all possible connections between the items. (item 1 with item 2 and so forth.) Step 2: Take the average of these correlations. Step 3: Fancy math with the average of the correlation and the number of items = Cronbach’s alpha .70 standard Validity of measures o Validity: the degree to which a measure is an accurate representation of the construct we want to measure. o Face validity: Does the measure seem like a plausible one, given the construct of interest. o Content validity: Does the measure capture all parts of the construct of interest? o Criterion validity: Is the measure related to relevant objective outcomes? Knowngroups paradigm: this is when you take groups you know to be different and give them the measures. o Convergent validity: Is the measure related to other measures that assess similar constructs? o Discriminant validity: Is the measure NOT related to other measures that assess different constructs? IV. Surveys and Observations (Ch. 6) Selfreport measures o Openended questions: allows people to respond to the questions freely. Advantage: is that is allows people to tell you what is important to them whether you thought about it or not. Disadvantage: is that you might never get the stuff that you care about; coding the results will be time consuming for you and the participant. o Closedended questions: provide people with specific rating dimensions of interest. Forced choice questions: for nominal data. Likert scale: for interval data. PSYC 2200 Semantic differential scale: a scale from something like foolish to wise. o Question wording Leading questions: makes one answer seem clearly better or more correct than the others. Doublebarreled questions: asking two question at once. Negatively worded questions: using negations makes questions more difficult to understand. o Question order: responses in earlier questions can affect the answers of later questions. o Response sets Acquiescence: the tendency to say yes to everything no matter what you ask. Solution would be to include reverse scored items. Fence sitting: when you stay close to the middle of the scale. Solution to this would be even number of scale points. Social desirability: concern over the impression of one’s responses might convey. Ways to reduce its influence. Anonymity and confidentiality. Give people a social desirability scale and account those score when it comes to your analyses. Include a few items to catch social desirability responding. Use surreptitious measures. Social desirability scale Observational measures o Naturalistic observation: observing behavior as is naturally occurring with no intrusion of the researcher. o Contrived observation: observe the behaviors in a research setting. Participant observation: becoming part of the world you wish to observe as a researcher. o Undisguised observation: the participants will know they are being observed. o Disguised observation: participants don’t know they are being watched. PSYC 2200 Reactivity: people may change their behavior because they know they are being watched Partial concealment strategy: participants know they are being observed but don’t know why. o Options for recording behavior Narratives: full descriptions of the behaviors. Checklists: count the occurrences of specific behaviors. Temporal measures: know the timings of the behaviors. Duration: how long the behavior lasted. Latency: time between an event and the response. Rating scales: outside parties make subjective about behavior on specific measures. o Observer effects Observer bias: observers’ expectations can influence their interpretation of the participant’s behavior Observer expectancy effects: observes’ expectation can actually influence the participants’ behavior. V. Sampling (Ch. 7) Terminology o Population: entire set of people you are interested in. o Sample: the subset of people you actually study. o Census: a study that involves the entire population. Representative sample: all members of the population have an equal chance of being included in the sample. Biased (unrepresentative) sample: some people in the population have a much better chance being included in the sample than others. o Selfselection: sampling from those who volunteer. Random sampling (probability sampling): the process of creating a representative sample, such that each population member has an equal chance of selection. o Simple random sampling: sample chosen completely at random from the population. Sampling frame: a full list of people in the population. o Cluster sampling: 3 Steps. PSYC 2200 Step 1: break population into clusters. Step 2: randomly sample the clusters. Step 3: use everyone from the selected cluster. Multistage sampling: similar but Step 3 changes. Step 3: randomly sample people from each randomly selected cluster. o Stratified random sampling: similar to cluster sampling, but uses demographic groups instead clusters. Step 1: identify the demographic groups for which you want to ensure appropriate representations. Step 2: determine the percent representation of each group within the population. Step 3: randomly sample the right number of people from that group to ensure correct percent representation within the sample. Oversampling: randomly sample MORE THAN the right number of people o Systematic sampling: pick a number and you sample that number person that goes by. o Challenges with random sampling overrepresents people who are “reachable,” and underrepresents those who aren’t. even people who are reachable may not want to participate. Ways to increase response rate Follow up. Give incentives. Check how people who respond differ than those who don’t. Biased sampling o Convenience sampling: sampling from those who are readily available to participate. o Purposive sampling: nonrandomly recruiting a particular type of participants. An example question: how many cancer patients see a therapist at least once peer week. o Snowball sampling: recruitment via participant’s social networks. PSYC 2200 o Quota sampling: pick a target number of participants in a particular category, recruit until you get that number. VI. Research Ethics and the Publishing Process (Ch. 4) The Belmont Report: a broad set of principles to guide research with human subjects. Motivated by the Tuskegee Syphilis Study. o Principle of respect for persons: informed consent, particularly for groups with reduced autonomy. o Principle of beneficence: protect participants from harm, and ensure wellbeing. o Principle of justice: fair balance of benefits and costs associated with research participants. APA standards o Institutional review board (IRB): committee that reviews research at universities and schools to ensure ethical conduct. o Coercion: the explicit or implicit suggestion that someone who chooses not to participate will suffer negative consequences. o Undue influence: offering an incentive too attractive to refuse. o Informed consent: must provide the participants with information about the study, particularly risks and benefits so they can decide if they want to participate. Information included and excluded Reasons informed consent can be problematic (3) People won’t behave naturally. Some people can’t give consent. Consent may be impractical or impossible to obtain. Conditions under which informed consent can be waived (2) Behavior is fully public. Minimal risk. o Deception: researchers withhold some details about the study either though omission or commission. Confederates: an actor playing a specific role for the study. Objections to deception (2) Moral argument. PSYC 2200 Pragmatic concerns. o Debriefing: informing participants about all aspects of the study after the study is over. o Research misconduct Plagiarism: misrepresenting the ideas or words of others as one’s own. Data fabrication: inventing data. Data falsification: inappropriately messing with data. o Research with animals Replacement: find alternatives when possible. Refinement: minimize or eliminate animals’ distress. Reduction: use as few animals as possible. Institutional Animal Care and Use Committee (IACUC) Arguments in favor (3) Benefits for humans and animals. All efforts are made to avoid and minimize suffering. Extent or cruelty is exaggerated. Against (2) No creature should suffer. Violated the principles of justice. The publication process o Steps in submitting a paper for publication (4 steps) Manuscript is sent to one journal for consideration. Editor assigns paper to associate editor. Associate editor identifies 24 reviewers. Write review and decide publish ability. Associate editors Experts in the field. Reviewers Experts in the field. o Possible outcomes (4) and which is most and least common Accept as is. (Least common) Accept with minor revision. Revise and resubmit. PSYC 2200 Reject. (Most common) o Criteria for publication (6) Significance of the question. Interestingness. Methods high in construct, internal and external validity. Appropriate analyses and interpretation of data. Good writing.
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'