
bd0f3b7a8c63872d5b00fd613d81bf95.ppt
- Количество слайдов: 35
Experiment Basics: Designs Psych 231: Research Methods in Psychology
Exam 2 on Monday n Review sessions after labs n n n Thursday in DEG 19, 530 -630 Friday in DEG 13, 2 -3 Announcements
A 1 A 2 Condition mean A 1 B 1 Condition What’s the effect of A at B 1? What’s the effect of A at B 2? A 2 B 1 Condition mean B 1 mean Condition A 1 B 2 Interaction of AB A 2 B 2 A 1 mean B 2 mean A 2 mean Main effect of A Marginal means 2 x 2 factorial design Main effect of B
A A 2 B 1 30 60 45 B 2 30 60 B 45 Dependent Variable A 1 Main Effect of B Main Effect of A Main effect of B Interaction of A x B B 1 B 2 A 1 A ✓ X X • At A 1: B 1 = B 2 • At A 2: B 1 = B 2 The effect of A doesn’t depend on level of B Examples of outcomes
A B 1 A 2 60 60 60 B B 2 30 30 45 45 30 Dependent Variable A 1 Main Effect of B Main Effect of A Main effect of A X Main effect of B ✓ Interaction of A x B X B 1 B 2 A 1 A • At A 1: B 1 - B 2 = 30 • At A 2: B 1 - B 2 = 30 The effect of A doesn’t depend on level of B Examples of outcomes
A 60 30 45 30 60 45 B 1 A 2 45 B B 2 45 Dependent Variable A 1 Main Effect of B Main Effect of A Main effect of A X Main effect of B X Interaction of A x B ✓ B 1 B 2 A 1 A • At A 1: B 1 - B 2 = +30 • At A 2: B 1 - B 2 = -30 The effect of A does depend on level of B Examples of outcomes
A 30 60 45 30 30 30 B 1 A 2 45 B B 2 30 Dependent Variable A 1 Main Effect of B Main Effect of A Main effect of B Interaction of A x B B 1 B 2 A 1 A ✓ ✓ ✓ • At A 1: B 1 - B 2 = 0 • At A 2: B 1 - B 2 = 30 The effect of A doesn’t depend on level of B Examples of outcomes
Let’s add another variable: test difficulty. anxiety hard low mod anxiety high low Test difficulty test performance easy medium hard medium easy mod high 35 80 35 65 80 80 80 60 main effect of anxiety Interaction ? Yes: effect of anxiety depends on level of test difficulty Anxiety and Test Performance main effect of difficulty 50 70 80
n Advantages n Interaction effects – Can only see interaction effects with a factorial design two separate 1 -factor studies Can not see the interaction – ≠ one 2 -factor study Can see the interaction Adding factors decreases the random variability – Because you are controlling more of the variables that R influence the dependent variable – This increases the statistical Power (your ability to detect an effect) of the statistical tests – Increases generalizability of the results – Because you have a situation closer to the real world (where all sorts of variables are interacting) Factorial Designs R
n Disadvantages n n n Experiments can become very large, and unwieldy The statistical analyses get much more complex Interpretation of the results can get more difficult • In particular for higher-order interactions For action movies, who • Higher-order interactions (when you have more than two factors, e. g. , ABC). For Rom. Coms, who stars matters for men, matters for both men & women but not women Action Movie Romantic Comedy Here there is a three way interaction: gender X who stars X type of movie Factorial Designs
n n So far we’ve covered a lot of the about details experiments generally Now let’s consider some specific experimental designs. n n Some bad (but common) designs Some good designs • • 1 Factor, two levels 1 Factor, multi-levels Factorial (more than 1 factor) Between & within factors Experimental designs
n What is the effect of presenting words in color on memory for those words? n So you present lists of words for recall either in color or in black-and-white. Clock Chair Cab n Clock Chair Cab Two different designs to examine this question Example
n Between-Groups Factor § 2 -levels, Each of the participants is in only one level of the IV § Sometimes referred to as “independent samples” design levels Colored words Clock Chair Cab participants Test BW words Clock Chair Cab
n Within-Groups Factor § 2 -levels, All of the participants are in both levels of the IV §Sometimes called “repeated measures” design levels participants Colored words Clock Chair Cab Test BW words Clock Chair Cab Test
n Mixed factorial designs n Treat some factors as within-subjects (participants get all levels of that factor) and others as between-subjects (each level of this factor gets a different group of participants). Our class experiment is a 2 x 2 mixed factorial design Cell phone Social & present Non-Social Sites participants Cell phone absent Social & Non-Social Sites Between groups factor Mixed factorial designs Test Within groups factor
n Between-subjects designs n n Each participant participates in one and only one condition of the experiment. Within-subjects designs n All participants participate in all of the conditions of the experiment. Colored words Test participants BW words participants Colored words Test BW words Test Between vs. Within Subjects Designs
n Between-subjects designs n n Each participant participates in one and only one condition of the experiment. Within-subjects designs n All participants participate in all of the conditions of the experiment. Colored words Test participants BW words participants Colored words Test BW words Test Between vs. Within Subjects Designs
n Advantages: n NR R NR n participants Colored words Test BW words Test Don’t have to worry about individual differences • Same people in all of the conditions • Variability between conditions is smaller (removing the variability from individual differences), which increases R your chances of detecting a small sized effect Fewer participants are required Within subjects designs
n Disadvantages: n n Range effects Order effects: participants Colored words Test BW words Test • Carry-over effects • Progressive error • Counterbalancing is probably necessary to address these order effects Within subjects designs
n Range effects (context effects) n n The range of values for your levels may impact performance (typically best performance in middle of range). Since all the participants get the full range of possible values, they may “adapt” their performance (the DV) to this range. $50 $60 $75 $100 Which bike to buy? • Buyers prefer the $60 bike • Add the high end bike -> buyers prefer the $75 bike Within subjects designs
n Carry-over effects n n Transfer between conditions is possible Effects may persist from one condition into another • e. g. Alcohol vs no alcohol experiment on the effects on hand-eye coordination. Hard to know how long the effects of alcohol may persist. Condition 1 Condition 2 test Order effects How long do we wait for the effects to wear off? test
n Progressive error n Result because the conditions are spread out over time (time becomes a possible confound) • Practice effects – improvement due to repeated practice • Fatigue effects – performance deteriorates as participants get bored, tired, distracted participants Colored words Test BW words Test Time Are colored words remembered better because they’re colored or because they came first? Order effects
n Counterbalancing is probably necessary n This is used to control for “order effects” • Ideally, use every possible order • But the number of orders scales up fast • n!, e. g. , AB = 2! = 2 orders; ABC = 3! = 6 orders, ABCD = 4! = 24 orders, …. n All counterbalancing assumes Symmetrical Transfer • The assumption that AB and BA have reverse effects and thus cancel out in a counterbalanced design Dealing with Order Effects
n Simple case n n Two conditions A & B Two counterbalanced orders: • AB • BA Colored words Test BW words Test Colored words Test participants Makes it a Factorial Design: Now you can examine the Main effects of Order apart from the main effect of Word color (and see if it the two interact with each other) Counterbalancing
n Often it is not practical to use every possible ordering n n Example: consider four conditions (ABCD = 4! = 24 possible orders) Partial counterbalancing Latin square designs • a form of partial counterbalancing, so that each group of trials occur in each position an equal number of times 1) Unbalanced Latin square: each condition appears in each position (4 orders) Order 1 A Order 2 B B C D A Order 3 C D A B Order 4 D A B C Partial counterbalancing
n Often it is not practical to use every possible ordering n n Example: consider four conditions (ABCD = 4! = 24 possible orders) Partial counterbalancing Latin square designs • a form of partial counterbalancing, so that each group of trials occur in each position an equal number of times 2) Balanced Latin square: each condition appears before and after all others (8 orders) A B C D A B D C B C D A B C A D C D A B C D B A D A B C D A C B Partial counterbalancing
n Between-subjects designs n Each participant participates in one and only one condition of the experiment. n Within-subjects designs n All participants participate in all of the conditions of the experiment. Colored words Test participants BW words participants Colored words Test BW words Test Between vs. Within Subjects Designs
n Clock Colored words Chair Cab Advantages: Test participants BW Clock words Chair Cab n Independence of groups (levels of the IV) • No range effects • Exposure to different levels of the independent variable(s) cannot “contaminate” the dependent variable • No order effects to worry about • Counterbalancing is not required • Sometimes between groups is a ‘must, ’ because you can’t reverse the effects of prior exposure to other levels of the IV • Reduced demand characteristics • Harder to guess what the experiment is about without experiencing the other levels of IV Between subjects designs
n Clock Colored words Chair Cab Disadvantages Test participants BW Clock words Chair Cab n Individual differences between the people in the groups • Excessive variability • Non-Equivalent groups Between subjects designs
n The groups are composed of different individuals participants Colored words BW words Individual differences Test
n The groups are composed of different individuals participants n Colored words BW words Excessive variability due to individual differences n Test Harder to detect the effect of the IV if there is one Individual differences NR R R
n The groups are composed of different individuals participants n Colored words Test BW words Non-Equivalent groups (possible confound) n The groups may differ not only because of the IV, but also because the groups are composed of different individuals Individual differences
n Strive for Equivalent groups n Created equally • Use the same process to create both groups n Treated equally • Keep the experience as similar as possible for the two groups n Composed of equivalent individuals • Random assignment to groups - eliminate bias • Matching groups - match each individuals in one group to an individual in the other group on relevant characteristics Dealing with Individual Differences
Group A Red Short 21 yrs Blue tall 23 yrs Green average 22 yrs Brown tall 22 yrs Group B matched Red Short 21 yrs Blue tall 23 yrs Green average 22 yrs Brown tall 22 yrs n Matched groups n n Trying to create equivalent groups Also trying to reduce some of the overall variability • Eliminating variability from the variables that you matched people on Color Height Age Identical twin studies are attempts to do “super” matched group designs Matching groups
n n Relevant stuff from Ex 1 Variables n n n types, operationalizing IV: methods of manipulation, getting the right range DV: measurement • Validity and Reliability n n n Sampling Control, Bias, and Confounding Experimental Designs n n Vocabulary Single factor designs Between & Within Factorial designs Exam 2 Topics (Chpts 5, 6, 11, 12)
bd0f3b7a8c63872d5b00fd613d81bf95.ppt