Tuesday November 17 2015 Test 3 Chapter 10 Introduction to Simple Experiments Red Elliot et al 2007 thought this might have an impact on education approach goals avoidance goals Does the color red activate avoidance goals Students were given anagrams When ID numbers were printed in red students did worse The color of the ID was the IV REPLICATION tried using different color booklets study 2 DV anagrams study 3 DV analogies vocabulary study 4 DV math problems solves Can Elliot et al claim the color CAUSED these effects This is a well designed experiment so YES Does it pass the 3 tests covariance temporal precedence internal validity Problems to look for Bad Messy Methodology internal validity 1 What are potential problems when designing an experiment that can decrease Tuesday November 17 2015 lack of control comparison group confounds aka design confounds noise variable ex Anagram Dif culty whenever possible it is important to keep everything equivalent between conditions keeping things even lack of random sample random assignment unsystemic variability chances of error Matched Group Design relatively random groups Different Types of Experimental Designs Between Subjects Designs based on information you assign participants into groups so that you have AKA Independent groups design Different groups of participants are exposed to different levels of the independent variable Basic Strategy Posttest Only Design Different groups get different treatments i e levels of IV We measure and record DV after treatment use statistics to determine whether IV had a statistically reliable effect Within Participants Designs AKA within groups designs All participants are exposed to all levels of the independent variable Randomized 2 Group Design Advantages simple 2 relatively few participants required data and stats easy easy to interpret no pre testing required to ensure equality of group we rely on randomization Tuesday November 17 2015 Disadvantages Doesn t provide a large amount of info may be insensitive to effects when participants differ greatly Not to say pre posttests are abad thing you can still use randomization but get a sense for whether the changes in your DV are actually based on your experimental design Randomized Multi Group Design the logic of the 2 group design can be extended to 3 or more groups multi group designs permit comparing two or more treatments to one or more control groups multiple control groups may be necessary to rule out alternative explanations consider potential alternative explanations if you do nd an effect carefully design one more control groups to rule out these explanations Alternatives to Randomized Designs to maximize our ability to detect an effect we may want to work to make sure all groups are equal on characteristics that might in uence DV Matched group designs help to control for error variance controls participant related variability by matching groups on characteristics that in uence performance e g age has a large effect on cognitive ability we may want to match groups on age Matches pairs design similar to the randomized 2 group design measure your sample Kansas Video Game Intervention Study 3 Tuesday November 17 2015 retirement community in Kansas Large age range ADD INFO Matched Multi Group Designs similar to the randomized ADD INFO Disadvantages of Matched Design More dif cult to implement need to measure all participants before study if you have many groups may be dif cult to nd a lot of people who match requires the use of slightly less powerful statistics so make sure the thing you are matching on really does in uence DV Within Groups Designs Taking matching to the extreme think of a between subjects design as matching each participant with someone who is just like them Advantages reduces error variance due to individual differences among subjects across treatment groups reduced error variance results in a more powerful design effects of independent variable are more likely to be detected requires fewer participants Disadvantages More demands put on participants longer study more complicated study may increase drop out rate When participants do drop out all their data is unusable Mistakes more costly again because you lose a large amount of data Carry over effects a major issue of within participant designs 4 Tuesday November 17 2015 Exposure to a previous treatment affects performance in a subsequent treatment Not an issue in between participant designs 6 sources of carry over effects 1 Learning learning a task in the rst treatment may affect performance in the second irrespective of IV 2 Fatigue Earlier treatments may affect performance in later treatments because participants will get tired 3 Habituation Repeated exposure to a stimulus may lead to unresponsiveness to that stimulus 4 Sensitization Exposure to a stimulus may make a subject respond more strongly to another that came before setting 5 Contrast Participants will compare the current treatment to treatments 6 Adaption Physiological changes over time based on experimental In general carryover effect can causes changes in your DV Dealing with carryover counterbalancing Advantages all possible combinations of treatments are represents Partial Counterbalancing includes only some of the possible treatment orders reverse counterbalancing used with small of conditions Latin Squares Design Control for ordinal position of each treatment each condition precedes or follows each other condition once Limitations 5 Tuesday November 17 2015 Sometimes treatments produce irresponsible effects Different carryover effects A B produces a different effect compares to B A Random Order Assign random order of treatment for each participant Carry over effects may not completely balance but are randomly distributed across treatments try to minimize carryover effects treatment order as IV If you have enough participants in your study you can include treatment order as an IV in your analysis will let you know if signi cant carryover effects are present in your study you can include treatment order as an IV in your analysis Will let you know if signi cant carryover effects are present in your study but at that point its too late but may be useful in the planning of future studies Ef ciency of a within subjects design Subjects are NOT randomly assigned to treatment conditions the same subjects are used in all conditions Repeated Measures Design Bick and Dozier 2008 one group interact with own toddler
View Full Document
Unlocking...