Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
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
Research Methods
Exam 2 - RM
| Question | Answer |
|---|---|
| What are the four types of research validity? | Statistical Conclusion Validity, Construct Validity, Internal Validity, External Validity |
| What is statistical conclusion validity? | Do the conclusions of our statistical tests make sense? Do the IV and DV covary (statistically related?) |
| What is construct validity? | It is the extent that we can infer higher-order constructs from our experiment (Is our theory the best explanation for the results?) |
| What are two major threats to construct validity? | Reactivity to experimental situation and experimenter effects |
| What is reactivity to the experimental situation? | The participants motives and perceptions (demand characteristics) may influence their responses. Their primary motive is positive self-presentation. There can be intertreatment and intratreatment interactions. |
| What are experimenter effects and how can they bias experiments? | The experimenter's motive (support the hypothesis) may lead to bias through experimenter attributes or expectencies (effect on experimenter = recording bias, the effect on the participant = different behavior) |
| What is internal validity and what is the primary threat? | Did our IV cause the DV? The primary threat is confounding variables. |
| What are some threats to internal validity? | History, Maturation, Selection, Attrition, Instrumentation, Regression Artifact, Addition and interactive effects |
| What is external validity? | Can we generalize our results? |
| Why do we fail to generalize our results some times? | Lack of random selection, chance variation, the failure to identify interactive effects of independent variables. |
| What are the types of external validity? | Population (can we generalize to target population), Temporal (can we generalize to a different time...seasonal and cyclical variations), ecological (different settings), outcome (relate to related DVs) and treatment variation. |
| What is the relationship between internal and external validity? | usually inverse |
| How do we establish external validity? | through replication |
| What type of validity do we want to prioritize? | depends on whether a causal relationship has been established or not |
| What is the goal of experimentation? | to identify the causal effect of the IV |
| What is randomization? | This is a control technique to equate groups of participants by ensuring that each member has an equal chance of being assigned to any group. |
| What are the benefits of random assignment? | Maximum insurance that the groups are equal. The extraneous variables are randomly distributed over the treatment groups. |
| What are the different matching techniques? | Holding variables constant, yoked control, matching by equating subjects (frequency distribution control), Precision control |
| What are the advantages of using matching? | It controls for the variables on which participants are matched and allows for greater sensitivity in the experiment. |
| What are the disadvantages of holding variables constant? | It restricts the population size and restricts the generalization to only the type of participants in the study |
| When should we build the extraneous variable into the research design? | Only when we are studying the effect of the extraneous variable |
| What is yoked control? | Matching subjects based on when they recieve the treatment |
| What is precision control and what is its disadvantages? | It's hard to identify the variables they should be matched on. Matching participants increases as the number of variables increase. Some variables may be difficult to match. |
| What is frequency distribution control? | we match participants based on the the overall distribution of the selected variable. The groups are statistically similar, but the combination of variables may be mismatched. |
| What is counterbalancing used for? | TO control order and carryover effects |
| What is randomized counterbalancing? | The sequence of conditions is randomly determined for each participant. |
| What is intrasubject counterbalancing? | The participants partake in the conditions in more than one order (may not work with long treatment sequences) |
| What is complete counterbalancing? | All possible sequences of the treatment conditions are used and participants are randomly assigned to a sequence (may not work with more than 3 conditions) |
| What is incomplete counterbalancing? | Not all the possible sequences are used. Each treatment condition must appear an equal time in each ordinal position and must precede or come after every other condition and equal amount of times. |
| What are the types of counterbalancing? | randomized, intrasubject, complete, incomplete |
| How do we control participant effects? | Double-blind placebo model, deception, control participant interpretation. |
| What are some ways to receive concurrent verbal reports? | Sacrifice groups (lose data), concurrent probing, thinking out loud |
| How do we control experimenter effects? | We control recording errors (multiple data recorders, have participants make responses on a computer), control attribute errors (use same experimenter in each condition), and control experimenter expectencies. |
| How do we control experimenter expectancies? | Blind technique (the researcher is unaware of participant's treatment condition), partial blind technique (researcher unaware for portion of research), and automation |
| What is the purpose of research designs? | They control for unwanted variation. |
| What are the weak experimental research designs? | One-group posttest only, one-group pretest-posttest, posttest only with nonequivalent groups. |
| When is the one-group posttest only design useful? | Only when specific background infromation exists on the dependent variable |
| How do we infer causality in the one-group pretest-posttest design? | We must identify and demonstrate that internal validity threats do not exist |
| What is the major weakness of the posttest only design with nonequivalent groups? | the groups aren't equal if they're not randomly assigned. This may confound selection with treatment effect |
| What makes an experimental research design strong? | Control techniques (random assignment) and a control group |
| What are the strong between-participants designs? | Posttest-only control group, Pretest-posttest control group. |
| What is the weakness of the posttest-only control group design? | This does not guarantee that groups are equivalent and there is no pretest to assess equivalence |
| What are the advantages of including a pretest in a control-group design? | We can insure that groups are equivalent before treatment conditions and we can assess additional variables that may interact with the independent variable. ceiling effect, assess change, control differences |
| What is the weakness of using a pretest? | sometimes you won't be able to generalize it to situations without a pretest |
| What are the pros and cons of the within-subjects posttest only design? | pros: Increased sensitivity (individual differences controlled) and fewer participants needed. Cons: difficult for participants, may have carryover effects |
| What is a factorial design? | COntains two or more independent variables |
| What are the advantages of using factorial designs? | More than one IV = precise hypothesis, controls extraneous variable, can see interactive effects |
| Disadvantages of factorial designs | more than 2 IVs can be hard to interpret and logistically time-consuming |
| How do we choose the appropriate experimental design? | We study previous literature. |
| What is the point of the institutional review board? | participant welfare |
| What is power? | the probability that we have correctly rejected the null hypothesis |
| What are factors that influence power? | alpha level, sample size, effect size |
| What needs to be included in the consent form | Enough info so they can decide if they want to do it or not. Where it will be, how long it will take, the procedure and potential risks, potential benefits, compensation, can refuse to answer questions, extra info, can withdraw at any time, confidential |
| What is the purpose of debriefing? | Ethical (return participant to pre-experimental state), educational, methodological, sense of satisfaction |
| Is debriefing effective? | ethical and methodological purposes yes, eductional probably not |
| What is the purpose of a pilot study? | Establishes clarity of instructions, researcher familiar with procedure, provides evidence that we are manipulating the IV adequately. |
Created by:
TaterTot