Experimental Control & Design Psych 231: Research Methods in Psychology.

Slides:



Advertisements
Similar presentations
Validity, Sampling & Experimental Control Psych 231: Research Methods in Psychology.
Advertisements

Validity, Sampling & Experimental Control Psych 231: Research Methods in Psychology.
Experimental Design: Single factor designs Psych 231: Research Methods in Psychology.
Using Statistics in Research Psych 231: Research Methods in Psychology.
Writing with APA style (cont.) & Experiment Basics: Variables Psych 231: Research Methods in Psychology.
Review for Exam 2 Psych 231: Research Methods in Psychology.
Psych 231: Research Methods in Psychology
Experimental Control & Design Psych 231: Research Methods in Psychology.
Experiment Basics: Variables
Experimental Control cont. Psych 231: Research Methods in Psychology.
Experimental Design: Single factor designs Psych 231: Research Methods in Psychology.
Statistics for the Social Sciences Psychology 340 Spring 2005 Statistics & Research Methods.
Statistics for the Social Sciences
Experimental Designs Psych 231: Research Methods in Psychology.
Sampling & Experimental Control Psych 231: Research Methods in Psychology.
Experimental Design: Single factor designs Psych 231: Research Methods in Psychology.
Experimental Control Psych 231: Research Methods in Psychology.
Psych 231: Research Methods in Psychology
Sampling & Experimental Control Psych 231: Research Methods in Psychology.
© 2001 Dr. Laura Snodgrass, Ph.D.1 Basic Experimental Design Common Problems Assigning Participants to Groups Single variable experiments –bivalent –multivalent.
Variables cont. Psych 231: Research Methods in Psychology.
Sampling & Experimental Control Psych 231: Research Methods in Psychology.
Using Statistics in Research Psych 231: Research Methods in Psychology.
Psych 231: Research Methods in Psychology
Experiment Basics: Variables Psych 231: Research Methods in Psychology.
Experiment Basics: Designs Psych 231: Research Methods in Psychology.
Chapter 7 Experimental Design: Independent Groups Design.
Experiment Basics: Designs Psych 231: Research Methods in Psychology.
Between groups designs (2) – outline 1.Block randomization 2.Natural groups designs 3.Subject loss 4.Some unsatisfactory alternatives to true experiments.
Statistics (cont.) Psych 231: Research Methods in Psychology.
Experiment Basics: Variables Psych 231: Research Methods in Psychology.
Experiment Basics: Variables Psych 231: Research Methods in Psychology.
Experiment Basics: Control Psych 231: Research Methods in Psychology.
1.) *Experiment* 2.) Quasi-Experiment 3.) Correlation 4.) Naturalistic Observation 5.) Case Study 6.) Survey Research.
Statistics for the Social Sciences Psychology 340 Spring 2010 Introductions & Review of some basic research methods.
Reasoning in Psychology Using Statistics Psychology
Experiment Basics: Designs Psych 231: Research Methods in Psychology.
Chapter 8: Between Subjects Designs
Experiment Basics: Variables Psych 231: Research Methods in Psychology.
Experiment Basics: Designs Psych 231: Research Methods in Psychology.
Experiment Basics: Designs Psych 231: Research Methods in Psychology.
Experiment Basics: Designs Psych 231: Research Methods in Psychology.
Experiment Basics: Designs Psych 231: Research Methods in Psychology.
Experiment Basics: Control Psych 231: Research Methods in Psychology.
Experiment Basics: Variables
Experiment Basics: Variables
Experiment Basics: Designs
Reasoning in Psychology Using Statistics
Experiment Basics: Variables
Internal Validity – Control through
2 independent Groups Graziano & Raulin (1997).
Experiment Basics: Designs
Experiment Basics: Designs
Experiment Basics: Control
Experiment Basics: Designs
Experiment Basics: Designs
Establishing the Direction of the Relationship
Experiment Basics: Designs
Experiment Basics: Variables
Experiment Basics: Control
Experiment Basics: Designs
Experiment Basics: Control
Reasoning in Psychology Using Statistics
Experiment Basics: Control
Experiment Basics: Designs
Experiment Basics: Designs
Experiment Basics: Designs
Experiment Basics: Variables
Experiment Basics: Designs
Reasoning in Psychology Using Statistics
Presentation transcript:

Experimental Control & Design Psych 231: Research Methods in Psychology

Announcements Don’t forget, in labs IRB worksheet for group projects Methods and Appendix for group projects Next week: Turning in first draft of class experiment write-up IN LABS Piloting group projects in labs next week, so need to have everything ready to go (the following week you are collecting the “real” data)

Experimental Control Our goal: To test the possibility of a systematic relationship between the variability in our IV and how that affects the variability of our DV. Control is used to: Minimize excessive variability To reduce the potential of confounds (systematic variability not part of the research design)

Experimental Control Our goal: To test the possibility of a systematic relationship between the variability in our IV and how that affects the variability of our DV. T = NR exp + NR other + R NR exp : Manipulated independent variables (IV) NR other : extraneous variables (EV) which covary with IV Random (R) Variability Nonrandom (NR) Variability Imprecision in measurement (DV) Randomly varying extraneous variables (EV) Condfounds Our hypothesis: the IV will result in changes in the DV

Experimental Control: Weight analogy Variability in a simple experiment: R NR other Treatment group Control group T = NR exp + NR other + R R NR exp NR other Absence of the treatment ( NR exp = 0 ) “perfect experiment” - no confounds ( NR other = 0 )

Experimental Control: Weight analogy Variability in a simple experiment: R NR exp R Treatment group Control group T = NR exp + NR other + R Difference Detector Our experiment is a “difference detector”

Experimental Control: Weight analogy If there is an effect of the treatment then NR exp will ≠ 0 R NR exp R Treatment group Control group Difference Detector Our experiment can detect the effect of the treatment Our experiment can detect the effect of the treatment

Things making detection difficult Potential Problems Confounding Excessive random variability Difference Detector

Potential Problems Confound If an EV co-varies with IV, then NR other component of data will be present, and may lead to misattribution of effect to IV IV DV EV Co-vary together

Confounding R NR exp NR other R Difference Detector Experiment can detect an effect, but can’t tell where it is from Experiment can detect an effect, but can’t tell where it is from Confound Hard to detect the effect of NR exp because the effect looks like it could be from NR exp but could be due to the NR other

Potential Problems Excessive random variability If experimental control procedures are not applied Then R component of data will be excessively large, and may make NR exp undetectable

Excessive random variability R NR exp R Difference Detector Experiment can’t detect the effect of the treatment Experiment can’t detect the effect of the treatment If R is large relative to NR exp then detecting a difference may be difficult

Reduced random variability But if we reduce the size of NR other and R relative to NR exp then detecting gets easier RR NR exp Difference Detector Our experiment can detect the effect of the treatment Our experiment can detect the effect of the treatment So try to minimize this by using good measures of DV, good manipulations of IV, etc.

Controlling Variability How do we introduce control? Methods of Experimental Control Constancy/Randomization Comparison Production

Methods of Controlling Variability Constancy/Randomization If there is a variable that may be related to the DV that you can’t (or don’t want to) manipulate Control variable: hold it constant Random variable: let it vary randomly across all of the experimental conditions

Methods of Controlling Variability Comparison An experiment always makes a comparison, so it must have at least two groups Sometimes there are control groups This is often the absence of the treatment Training group No training (Control) group Without control groups if is harder to see what is really happening in the experiment It is easier to be swayed by plausibility or inappropriate comparisons Useful for eliminating potential confounds

Methods of Controlling Variability Comparison An experiment always makes a comparison, so it must have at least two groups Sometimes there are control groups This is often the absence of the treatment 1 week of Training group 2 weeks of Training group Sometimes there are a range of values of the IV 3 weeks of Training group

Methods of Controlling Variability Production The experimenter selects the specific values of the Independent Variables 1 week of Training group 2 weeks of Training group 3 weeks of Training group Need to do this carefully Suppose that you don’t find a difference in the DV across your different groups Is this because the IV and DV aren’t related? Or is it because your levels of IV weren’t different enough

Experimental designs So far we’ve covered a lot of the about details experiments generally Now let’s consider some specific experimental designs. Some bad (but common) designs Some good designs 1 Factor, two levels 1 Factor, multi-levels Between & within factors Factorial (more than 1 factor)

Poorly designed experiments Bad design example 1: Does standing close to somebody cause them to move? “hmm… that’s an empirical question. Let’s see what happens if …” So you stand closely to people and see how long before they move Problem: no control group to establish the comparison group (this design is sometimes called “one-shot case study design”)

Poorly designed experiments Bad design example 2: Testing the effectiveness of a stop smoking relaxation program The participants choose which group (relaxation or no program) to be in

Poorly designed experiments Non-equivalent control groups participants Training group No training (Control) group Measure Self Assignment Independent Variable Dependent Variable Random Assignment Problem: selection bias for the two groups, need to do random assignment to groups Problem: selection bias for the two groups, need to do random assignment to groups Bad design example 2:

Poorly designed experiments Bad design example 3: Does a relaxation program decrease the urge to smoke? Pretest desire level – give relaxation program – posttest desire to smoke

Poorly designed experiments One group pretest-posttest design participantsPre-test Training group Post-test Measure Independent Variable Dependent Variable Problems include: history, maturation, testing, and more Pre-test No Training group Post-test Measure Add another factor Bad design example 3:

1 factor - 2 levels Good design example How does anxiety level affect test performance? Two groups take the same test Grp1 (moderate anxiety group): 5 min lecture on the importance of good grades for success Grp2 (low anxiety group): 5 min lecture on how good grades don’t matter, just trying is good enough 1 Factor (Independent variable), two levels Basically you want to compare two treatments (conditions) The statistics are pretty easy, a t-test

1 factor - 2 levels participants Low Moderate Test Random Assignment Anxiety Dependent Variable Good design example How does anxiety level affect test performance?

anxiety low moderate 8060 lowmoderate test performance anxiety One factor Two levels Use a t-test to see if these points are statistically different T-test = Observed difference between conditions Difference expected by chance Good design example How does anxiety level affect test performance? 1 factor - 2 levels

Advantages: Simple, relatively easy to interpret the results Is the independent variable worth studying? If no effect, then usually don’t bother with a more complex design Sometimes two levels is all you need One theory predicts one pattern and another predicts a different pattern 1 factor - 2 levels

low moderate test performance anxiety What happens within of the ranges that you test? Interpolation Disadvantages: “True” shape of the function is hard to see Interpolation and Extrapolation are not a good idea 1 factor - 2 levels

Extrapolation lowmoderate test performance anxiety What happens outside of the ranges that you test? Disadvantages: “True” shape of the function is hard to see Interpolation and Extrapolation are not a good idea 1 factor - 2 levels high

1 Factor - multilevel experiments For more complex theories you will typically need more complex designs (more than two levels of one IV) 1 factor - more than two levels Basically you want to compare more than two conditions The statistics are a little more difficult, an ANOVA (Analysis of Variance)

Good design example (similar to earlier ex.) How does anxiety level affect test performance? Two groups take the same test Grp1 (moderate anxiety group): 5 min lecture on the importance of good grades for success Grp2 (low anxiety group): 5 min lecture on how good grades don’t matter, just trying is good enough 1 Factor - multilevel experiments Grp3 (high anxiety group): 5 min lecture on how the students must pass this test to pass the course

1 factor - 3 levels participants Low Moderate Test Random Assignment Anxiety Dependent Variable High Test

1 Factor - multilevel experiments anxiety low mod high 8060 lowmod test performance anxiety high

1 Factor - multilevel experiments Advantages Gives a better picture of the relationship (function) Generally, the more levels you have, the less you have to worry about your range of the independent variable

Relationship between Anxiety and Performance lowmoderate test performance anxiety 2 levels highlowmod test performance anxiety 3 levels

1 Factor - multilevel experiments Disadvantages Needs more resources (participants and/or stimuli) Requires more complex statistical analysis (analysis of variance and pair-wise comparisons)

Pair-wise comparisons The ANOVA just tells you that not all of the groups are equal. If this is your conclusion (you get a “significant ANOVA”) then you should do further tests to see where the differences are High vs. Low High vs. Moderate Low vs. Moderate