Chapter 8 part 1(1)

862 views

Published on

0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
862
On SlideShare
0
From Embeds
0
Number of Embeds
2
Actions
Shares
0
Downloads
70
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Chapter 8 part 1(1)

  1. 1. Chapter 8
  2. 2. Research Design The plan or strategy used to answer the research question This is where we put to use all of the things that we have learned about validity and reliability.
  3. 3. Experimental Research Design• Weak vs. Strong experimental design
  4. 4. Weak Experimental Designs Do not control for many extraneous variables Provide weak evidence of cause and effect Have threats to internal validity
  5. 5. One-group Posttest- OnlyDesign Influence of a treatment is investigated with only one group of individuals  Single test after treatment (“posttest”) Example: New reading program in 1st grade  Does program improve reading skills?
  6. 6. One-group Posttest-onlyDesign Treatment Posttest Measure X O
  7. 7.  Problems? Extraneous variables? Why/when would you use this design? If there is background information on DV and prior work has shown mechanism by which IV impact DV.
  8. 8. One-group Pretest-Posttest Design A treatment condition is interjected between pre- and posttest of the dependent variable.Pretest measure Treatment Posttest Measure O X O Compare
  9. 9. One-group Pretest-Posttest Design Advantage over one-group posttest? Problems? Threats to internal validity? Why would we use this design?  If we cannot create an equal group for comparison, we can get SOME information this way
  10. 10. Nonequivalent Posttest-Only Design  Performance of an experimental group is compared with that of a nonequivalent control group at posttest Posttest Treatment MeasureExperimental Group X O CompareControl Group O
  11. 11.  Advantage over previous designs? Problems? Threat to internal validity?  Selection Best thing to do is to use random assignment.  Creates equivalent groups Next best is to use matching on relevant variables.  Will discuss this next chapter
  12. 12. Strong Experimental ResearchDesigns Designs that effectively control extraneous variables and provide strong evidence of cause and effect
  13. 13.  To control for extraneous variables you must eliminate potential rival hypotheses. Done in two ways:  Control Techniques- more on this next week (ch. 7)  Control Group
  14. 14.  Control group  comparison group  Does not receive “active” level of IV ○ No intervention or standard experience Experimental group  receives a level of the IV intended to produce effect
  15. 15. Functions of a Control Group1. Serve as a comparison to the experimental group. Did the treatment/manipulation have an effect?Estimate Counterfactual- what the participants’ responses would have been had they not received the treatment
  16. 16. Functions of a Control Group2. Control for rival hypotheses  With random assignment, extraneous variables will have an equivalent impact on both groups
  17. 17. Strong Experimental ResearchDesigns Basic designs – one IV and one DV  Between-participants  Within-Participants (repeated measures) Factorial Designs – multiple IVs
  18. 18. Posttest-Only Control Group Design  This design looks familiar, right?  What is different now? Posttest Treatment MeasureExperimental Group X O CompareControl Group O
  19. 19. Posttest-Only Control GroupDesign We could have more than 1 experimental group Posttest Treatment MeasureControl Group OExperimental Group 1 X1 O CompareExperimental Group 2 X2 O
  20. 20. Important time-out: Benefits of randomized control group Avoid many threats to internal validity  Examples?
  21. 21. Pretest-Posttest Control GroupDesign Simply add pretest to previous design What comparisons will we make? Pretest Posttest Treatment Measure Measure Experimental O X O Group Control O O Group
  22. 22. Benefits of Pretest Ensure equivalency of groups Detect ceiling and floor effects  Select participants accordingly Can empirically demonstrate effect of treatment  Change scores See if initial position on DV is important  Treatment may affect hi/low differently

×