Quasi-Experimental Designs
Help!
|
|
||||
|---|---|---|---|---|---|
| Structures and procedures used in constructing research designs. | Design components
🗑
|
||||
| A quasi-experimental design in which the results obtained from nonequivalent expertimental and control groups are compared. | Nonequivalent comparison group design
🗑
|
||||
| An outcome in which the experimental and the control groups differ at pretesting and both increase from pre- to posttesting, but the experimental group increases at a faster rate. | Increasing treatment and control groups
🗑
|
||||
| Participates in one group experience a different rate of maturation than participants in another group. | Selection-maturation effect
🗑
|
||||
| An extraneous event occuring between pretest and posttest influences participants in one group differently than participants in another group. | Selection-history effect
🗑
|
||||
| Participants' scores in one group are affected bt the process of measurement differently than participants in another group. | Selection-instrumentation effect
🗑
|
||||
| Participants that drop out of one group are dissimilar to those in another group. | Selection-attrition effect
🗑
|
||||
| Participatns in one group display a different rate of regression to the mean than participants in another group. | Selection-regression effect
🗑
|
||||
| An outcome in which the experimental and the control groups differ at pretesting, and only the experimental group's scores change from pre- to posttesting. | First increasing treatment effect
🗑
|
||||
| An outcome in which the control group performs better than the experimental group at pretesting, but only the experimental group improves from pre- to pretesting. | Second increasing treatment effect
🗑
|
||||
| An outcome in which the control group performs better at pretesting but the experimental group performs better at posttesting. | Crossover effect
🗑
|
||||
| A quasi-experimental design in which a treatment effect is assessed by comparing the pattern of pre- and posttest scores for a single group of resaerch participants. | Interrupted time-series design
🗑
|
||||
| A design that assigns participants to groups based on their scores on an assignment variable and assesses the effect of a treatment by looking for a discontinuity in the groups regression lines. | Regression discontinuity design
🗑
|
||||
| Measure used to assign participants to experimental and control groups. Those with scores below the cutoff score are assigned to one group, and those with scores above the cutoff are assigned to the other group. | Assignment measure
🗑
|
||||
| AKA panel study (longitudinal study). ppts are studied over a period of time to see if their risk factors will cause a predicted outcome. Outcome from participants in each cohort is measured and relationships with specific characteristics determined. | Cohort Design
🗑
|
||||
| Provides a tentative answer to the "direction of causation" problem (the "Chicken-egg" question). I.e. does increase coffee consumption cause depression or vice versa or both? | Cross-lagged panel design
🗑
|
||||
| A research design in which an experimental procedure is applied but all extraneous variables are not controlled. | Quasi-experimental design
🗑
|
||||
| What makes a design a quasi-experimental design? | Does not meet all the requirements necessary for controlling extraneous variables. Lacks Random Assignment of ppt to groups.
🗑
|
||||
| How can you rule out rival hypotheses in quasi-experimental designs? | 1. identification and study of plausible threats to internal validity
2. control by design (i.e. adding pretests & control groups) design components
3. coherent pattern matching (more than one hypothesis)
🗑
|
||||
| What are the 6 different design components? | 1. control/comparison groups
2. pretest
3. posttest
4. within-participants/bt participants IV
5. inclusion of interesting theoretical IV
6. measurment of theoretical DV
🗑
|
||||
| Most common quasi-experimental design? | Nonequivalent comparison group design
🗑
|
||||
| Diagram the nonequivalent comparison group design | subjects divided between (without random assignment)
experiemental group: pretest - treatment -posttest
control group: pretest - treatment - posttest
🗑
|
||||
| 6 types of Quasi-Experimental Designs/sub categories | 1. Nonequivalent Comparison Group design
2. Time-Series Design
3. Interrupted Time-Series Design
4. Cohort Design
5. Cross-lagged design
6. Regression Discontinuity Design
🗑
|
||||
| What are the 6 biases that result from no random assignment in a quasi experimental design? | 1. selection bias
2. selection-attrition bias
3. selection-maturation bias
4. selection-instrumentation bias
5. selection-regression bias
6. selection-history bias
🗑
|
||||
| What are the 4 possible outcomes for nonequivalent comparison group design? | 1. Increasing treatment and control groups
2. First increasing treatment effect
3. Second increasing treatment effect
4. Crossover effect
🗑
|
||||
| What rival hypotheses can exist in Outcome I from using a nonequivalent comparison group design | Increasing Treatment and Control Groups: (figure 10.3) Both increase. Control group increases slightly (s-maturation); experimenta group in creases dramatically. -> Threats: selection maturation. selection history, selection-regression
🗑
|
||||
| What rival hypotheses can exist in Outcome II from using a nonequivalent comparison group design | First increasing treatment effect: (figure 10.4) Control group shows no change. Experimental group dramatically changes Threats: s-history
🗑
|
||||
| What rival hypotheses can exist in Outcome III from using a nonequivalent comparison group design | Second increasing threatment efect. (10.5) Control no change but started higher than experimental (s-regression). Experimental increases. Threats: s-regression, selection bias.
🗑
|
||||
| What rival hypotheses can exist in Outcome IV from using a nonequivalent comparison group design | Cross over effect: (10.6) Ideal image. Experiment began lower and ended up higher than control line. Control does not change. Threats: confounding variables.
🗑
|
||||
| What are the two ways in which one can tule out threats to the nonequivalent comparison group design? | 1. Matching: when you cannot randomly select, you can match. But do not match low scores and match high scores because this will cause regression artifact.
2. Statistical control: using stats to determine like-characteristics into groups. ANCOVA.
🗑
|
||||
| What is ANCOVA? | Reliabilty adjusted anaylsis of covariance. Another statistically adjusting approach is: propensity score matching and selection modeling.
🗑
|
||||
| How are rival hypotheses ruled out in a time-series design and what rival hypothesis cannot be ruled out. | liminated regression effect. ARIMA
History effect cannot be ruled out
🗑
|
||||
| In what situation would you use a regression discontinuity design and what evidence would be needed to infer a treatment effect using this design | Find out cut off score, either pick the ones above or below cut off score for treatment. Purposely making a regression op= test cut off c=cut off
x=treatment o2=measure
Experimental group: Op C X O2
Control group: Op C O2
contin. line :(
b
🗑
|
||||
| What is a cohort design and why can this design be used | Cohort designs is useful when looking at archival evidence or studying effects over generations. Cohorts in this case is compating group before the treatment group.
🗑
|
||||
| When would you use a cross lagged panel design and what are the three components of this design. Explain the purpose of each component | 1. auto-correlation -> <-
2. synchronous correlation ^ v
3. cross-lagged correlation X line
determining which came first? Which has the strongest primary difrection of causality.
🗑
|
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:
nga
Popular Psychology sets