Chapter 7

Question 1

What are the elements of the classical experimental design?

Answer 1

1. an IV (stimulus) and a DV
2. pre-testing (measures the dependent variable prior to stimulus exposure) and post-testing (measures the dependent variable after stimulus exposure)
3. experimental and control groups

Question 2

What’s the stimulus in an experiment

Answer 2

the independent variable

Question 3

Controls help us avoid _____ and enhance ______

Answer 3

Bias

Validity

Question 4

What’s the purpose of placebos in an experiment?

Answer 4

They help to avoid the impact of being studied
- oftentimes the double-blind method is used (subject doesn’t know if they’re getting the placebo and neither does the researcher)

Question 5

What are classical and natural experiments?

Answer 5

Classical : researcher manipulates the independent variable

Natural : researcher does not have to manipulate the independent variable - group assignment and administration of the independent variable are outside the research’s control
- usually there are less ethical issues because you’re not manipulating anything
- another benefit is their external validity

Question 6

Describe the romanian orphans study

Answer 6

• natural experiment
• romanian orphans were treated like animals and there were at least half a million cases of severely rejected kids
• longterm study - looked at those who were in orphanages from just after birth up to about age 4
• compared 2 groups - one of kids who had been institutionalized for less than 6 months and kids who had been for 6 or more months
• needed a control group of adoptees who hadn’t experienced any isolation or deprivation –> this made sure that it wasn’t just the result of adoption that impacted the romanian kids

Question 7

When are experiments especially very well suited?

Answer 7

Well suited to research projects involving relatively limited and well-defined concepts propositions

Also especially appropriate for hypothesis testing

because they’re focused on determining causation, they’re also better suited to explanatory than to descriptive purposes

Question 8

What does it mean that the independent variable is a dichotomous variable

Answer 8

The experimental stimulus (independent variable) variable has two attributes, either present or not present

Question 9

What is the one problem that plagues many forms of research? explain how the example of Roethlisberger and Dickson’s study shows this

Answer 9

The fact that the very act of studying something may change it - problem of validity

Their study in 1939 looked at employee satisfaction - but the workers they were testing responded more to the attention given them by the researchers than to the actual improved working conditions (ex. when they dimmed the lights, productivity still went up) - resulted in the Hawthorne effect

• this problem is accounted for by including a control group who does not receive the independent variable stimulus

Question 10

What is the hawthorne effect?

Answer 10

It refers to any impact of research on the subject of study

Question 11

What do control groups guard against?

Answer 11

Not only the effects of the experiments themselves but also the effects of any events outside the laboratory during the experiments

Question 12

is the issue of generalizability more or less significant in explanatory research and descriptive research ?

Answer 12

It is less significant in explanatory research and more significant in descriptive research

Question 13

What is probability sampling?

Answer 13

Beginning with a sampling frame composed of all the people in the population under study, the researcher might select two probability samples. If these samples each resemble the total population from which they’re selected, they’ll also resemble each other.

probability samples of less than 100 are not likely to be terribly representative - therefore they are not used in social scientific experiments very often

Question 14

What do probability sampling and random assignment respectively ensure?

Answer 14

Probability sampling : ensures that the subjects from whom actual data are gathered will be as representative as possible of some larger population
Random assignment : ensures that the subjects exposed to the test factor (experimental group) are as comparable as possible to those exposed to the control factor (control group)

Question 15

What is random assignment?

Answer 15

Study participants are assigned to the treatment or control group using a randomization procedure
** is it the generally preferred method
–> the 20 subjects randomly assigned to the experimental group will be reasonably similar to the 20 assigned to the control group.
–> our assumption of similarity in the two groups depends in part on the number of subjects involved

Question 16

What is the matching method for selecting subjects?

Answer 16

pairs of subjects are matched on the basis of their similarities on one or more variables; then one member of the pair is assigned to the experimental group and the other to the control group.
–> desired result is the same as with random assignment : The overall average description of the experimental group should be the same as that of the control group.
*In some cases, we may delay assigning subjects to experimental and control groups until we have initially measured the dependent variable

Question 17

What are some arguments in favour of random assignment over matching?
When is matching the preferred method?

Answer 17

First, you may not be in a position to know in advance which variables are relevant for the matching process.

Second, most of the statistics used to analyze the results of experiments assume randomization. Failure to design your experiment that way, then, makes your later use of those statistics less meaningful.

*random assignment makes sense only if you have a fairly large pool of subjects, so that the laws of probability sampling apply. With only a few subjects, matching would be a better procedure.

Question 18

What is internal invalidity?

Answer 18

the possibility that the conclusions drawn from experimental results may not accurately reflect what went on in the experiment itself.
–> The threat of internal invalidity is present whenever anything other than the experimental stimulus can affect the dependent variable

Question 19

Describe history, maturation, and testing, as sources of internal invalidity

Answer 19

History. During the course of the experiment, historical events may occur that will confound the experimental results

Maturation. People are continually growing and changing, and such changes affect the results of the experiment. In a long-term experiment, the fact that the subjects grow older (and wiser?) may have an effect.

Testing. Often the process of testing and retesting will influence people’s behaviour, thereby confounding the experimental results.

Question 20

Describe instrumentation, statistical regression, and experimental mortality as sources of internal invalidity

Answer 20

Instrumentation : If we use different measures of the dependent variable in the pretest and posttest (say, different questionnaires about prejudice), how can we be sure they’re comparable to one another

Statistical regression : if changes occur by virtue of subjects starting out in extreme positions (ex. people who are rly bad at math)

Experimental mortality : Often, experimental subjects will drop out of the experiment before it’s completed, which can affect statistical comparisons and conclusion

Question 21

Describe causal time order, diffusion or imitation of treatments, and compensation as sources of internal invalidity

Answer 21

causal time order : ambiguity about the time order of the experimental stimulus and the dependent variable

diffusion or imitation of treatments : When experimental and control-group subjects can communicate with each other, experimental subjects could pass on some elements of the experimental stimulus to the control group

Compensation : subjects in the control group are often deprived of something considered to be of value. In such cases, there may be pressures to offer some form of compensation

Question 22

Describe compensatory rivalry and demoralization as sources of internal invalidity

Answer 22

compensatory rivalry : the subjects deprived of the experimental stimulus may try to compensate for the missing stimulus by working harder.

demoralization : feelings of deprivation within the control group may result in their giving up

Question 23

What is external invalidity?

Answer 23

Refers to the possibility that conclusions drawn from experimental results may not be generalizable to the “real” world.

Question 24

What is the Solomon four-group design? What problem does it address?

Answer 24

It adds an experimental and control group that both skip the pretest

–> addresses the problem of testing interaction with the stimulus

Question 25

What is the post-test-only control group design?

Answer 25

It consists of the second half (Groups 3 and 4) of the Solomon design. As the authors argue persuasively, with proper randomization only Groups 3 and 4 are needed for a true experiment that controls for the problems of internal invalidity as well as for the interaction between testing and stimulus.
*** only applies to experiments where subjects have been assigned to experimental and control groups randomly

Question 26

What is the labelling theory?

Answer 26

addresses the phenomenon of people acting in accord with the ways they are perceived and labelled by others.

Question 27

What is the Pygmalion effect?

Answer 27

Differences in study outcomes attributable to the researcher’s expectations of participants.

ex. telling teachers which students will do best (randomly) and because of this they do the best because of the teachers preconceived idea (rosenthal and jacobson)

Question 28

What are field experiments?

Answer 28

involve experimental designs in real-world conditions where researchers may be able to manipulate some independent variables but have limited control over other experimental conditions such as random assignment of subjects to groups or their exposure to external variables
- advantage of external validity

Question 29

What are the four basic approaches to web-based experiments?

Answer 29

• using an existing online environment
• building your own environment
• collaborating with an online media company
• using crowdsourcing to conduct your own experiment

Question 30

What are the three criteria needed to demonstrate that an independent variable causes changes in a dependent variable?

Answer 30

1. Sequence of time-ordering :independent variable must change prior to observed changes in the dependent variable
2. Association or correlation : the variables must change together systematically
3. Nonspuriousness or authenticity : states that the observed association between the independent and dependent variable is not due to any other variables.

Question 31

What was Zimbardo’s proposed result of the SPE (1971)

Answer 31

People will conform naturally to the requirements to their role - observing brutality in the world doesn’t say anything about the person, it says everyone about the roles that are assigned to them

Question 32

Describe the ethical concerns of the SPE

Answer 32

• shorterm psychological harm : there was a 10 year follow up study showing that prisoners didn’t suffer negative longterm effects (maybe because it was a short study or maybe because they were psychologically healthy subjects)
• participation was voluntary and they could leave whenever so that’s good
• did it go too far? - Zimbardo said it went on too long and Zimbardo should not have been the superintendent of the prison (could be a source of internal invalidity because he couldn’t impacted the results)