Making Inferences about Causality In general, children who watch violent television programs tend to behave more aggressively toward their peers and siblings. Question: Can we assume a causal relationship between these two variables? Watching violent TV Acting violent +

Making Inferences about Causality Answer: not necessarily Although causality generally implies correlation, correlation does not necessarily imply causality. There are at least three other ways to explain the correlation between TV viewing and aggressive behavior.

Making Inferences about Causality (a) Acting aggressively makes you want to watch more violent TV. Watching violent TV Acting violent +

Making Inferences about Causality (b) Acting violent makes you want to watch more TV and watching TV makes you act more violently. Watching violent TV Acting violent + +

Making Inferences about Causality (c) A “third variable” influences both variables, causing them to be correlated. Watching violent TV Acting violent Living in a violent family ++

How can we tease apart these various possibilities? One way to do so is to conduct an experiment. In an experiment, at least one variable is manipulated (i.e., systematically varied) by the researcher in order to study its effects on another variable.

Experimental Research Features of an experiment (a) At least one variable is manipulated or varied by the experimenter: independent variable (IV) (b) The variable presumably affected by the manipulation is called the dependent variable (DV) (c) random assignment to conditions Watching violent TV Acting violent IVDV +

Independent Variable: Watching violent TV Levels: (a) view an episode of the Sopranos (b) view an episode of the Sopranos in which the violent scenes have been edited Dependent Variable: Aggressive behavior Number of times the child punches his or her peers on the playground IVDV

Random Assignment Why is random assignment important? Consider what would happen if we assigned men to the “violent” level of the IV and women to the “non-violent” level of the IV. Sex would be correlated with the IV.

Random Assignment Confounding variable: a variable that influences the dependent variable and is associated with the independent variable When confounding variables are present, we cannot make a strong inference that the independent variable causes the dependent variable.

Random Assignment Random assignment to conditions helps to remove the problem of confounding variables. When people are randomly assigned to conditions, we should (in the long run) have equal numbers of men and women in our two conditions. As a result of random assignment, the possible confound (e.g., sex) is uncorrelated with the independent variable.

Random Assignment Previously, we had discussed the possibility that the violence of the family context is a “third variable” that might be causing both violent TV viewing and aggressive behavior. We could control for this possible confound by randomly assigning people to violent TV viewing conditions. Theoretically, there should be an equal number of people from violent families in each condition.

Confounding Variables and Non- Confounding Variables A variable can exist that has a genuine effect on the dependent variable but that is uncorrelated with the independent variable.

Confounding Variables and Non- confounding Variables Watching violent TV Acting violent Living in a violent family Living in a violent family Watching violent TV Acting violent ++++

Review If we can systematically manipulate a variable and show that it has an effect on another variable, then we have a strong basis for concluding that one variable affects the other.

Factorial Designs What about situations in which we wish to manipulate more than one variable? Why might we want to manipulate more than one variable in an experiment? –to study multiple variables at once –we may have reason to believe that the effects of one variable on another are conditional upon a third variable. Example: It may be the case that whether or not people behave aggressively after viewing violent television depends on whether they’ve been provoked/threatened.

Factorial Designs Multiple independent variables Factorial designs [# of levels]  [# of levels] IV#1 IV#2 Example: a 2  3 factorial design 2 levels of the first IV, “violent TV viewing” (e.g., watching violent TV and nonviolent TV) and 3 levels of second IV, “provocation” (e.g., 0 threats, 1 threat, 2 threats)

Factorial Designs Possible outcomes in a 2  2 design main effect: manipulating one of the IV’s produces a change in the DV in a 2  2 design, you can have 0, 1, or 2 main effects interaction: the effect of one IV on the DV is dependent on the other IV

No main effect of A or B, no interaction Aggressive TV viewing ProvocationsA1A2 B120 B220 Aggressive TV viewing Aggressive behavior (DV) Provocations This represents a situation in which the experimental manipulations have no effects on the dependent variable.

Main effect of A, no main effect of B and no interaction Aggressive TV viewing ProvocationsA1A2 B B Aggressive TV viewing Aggressive behavior (DV) Provocations Watching violent TV leads to increases in aggressive behavior.

Main effect of B, no main effect of A and no interaction Aggressive TV viewing ProvocationsA1A2 B120 B Aggressive TV viewing Aggressive behavior (DV) Provocations Being provoked leads to increases in aggressive behavior.

Main effect of A and B, no interaction Aggressive TV viewing ProvocationsA1A2 B B Aggressive TV viewing Aggressive behavior (DV) Provocations Watching violent TV leads to aggressive behavior. and Being provoked leads to increases in aggressive behavior.

No main effect of A or B; interaction Aggressive TV viewing ProvocationsA1A2 B B Aggressive TV viewing Aggressive behavior (DV) Provocations Whether people behave aggressively after watching violent TV depends on whether they’ve been provoked. If provoked, violent TV leads people to behave aggressively. If not provoked, violent TV leads people to behave less aggressively.

Main effect of A, no main effect of B; interaction Aggressive TV viewing ProvocationsA1A2 B B Aggressive TV viewing Aggressive behavior (DV) Provocations Watching violent TV leads to less aggressive behavior. and it depends. Watching violent TV leads people to behave less aggressively when they have not been provoked.

Main effect of B, no main effect of A; interaction Aggressive TV viewing ProvocationsA1A2 B B Aggressive TV viewing Aggressive behavior (DV) Provocations Being provoked leads to more aggressive behavior. and it depends. Being provoked leads to more aggressive behavior when watching violent TV. When not watching violent TV, provoked and non-provoked people are equally aggressive.

Main effect of A and B; interaction Aggressive TV viewing ProvocationsA1A2 B120 B Aggressive TV viewing Aggressive behavior (DV) Provocations Watching violent TV leads to more aggressive behavior. and Being provoked leads to increases in aggressive behavior. and it depends. In the absence of provocation, there is no effect of violent TV viewing on behavior. When provoked, watching violent TV leads people to behave more aggressively.

Experimental Research Between- and within-subjects designs between-subjects: different people are exposed to each level of the IV within-subjects: the same people exposed to each level of the IV Mixed design: one factor is a between- subjects factor and the other is a within- subjects factor

Pros and cons of different designs BetweenWithin Pros(a) Minimize reactance effects(a) Requires fewer research subjects Cons(a) Requires more research subjects (b) The people in the two conditions may vary for reasons that have nothing to do with your manipulation. (a) Awareness of different levels of independent variable (b) Learning & practice effects

Counter-balancing t1 t2 t3 Person 1 T1T2T3 Person 2 T1T3T2 Person 3 T2T1T3 Person 4 T2T3T2 Person 5 T3T1T2 Person 6 T3T2T1 Counter-balancing helps to ensure that the specific test used (T1, T2, T3) is uncorrelated with order of presentation