Ch 5: How do we misinterpret? Common threats to validity Flashcards Preview

Research Psychology > Ch 5: How do we misinterpret? Common threats to validity > Flashcards

Flashcards in Ch 5: How do we misinterpret? Common threats to validity Deck (21):

What is a pseudo-experimet?

pseudo-experiment (or false experiment) is a research design in which someone tests a claim (e.g., a product, a charm, a clinical treatment) by exposing people to the variable of interest and noting that these people fell, think, or behave as expected.

Example: "Melanie wore her lucky bowling shoes and bowled a 247," or "David carried a fishing weight in his pocket and got a dime from Jill Long."


What is selection bias?

Sampling people from an unrepresentative sample (by using imperfect sampling techniques) is reffered to as selection bias.

Example: Think of Literary Digest only sending surveys to people with cars and phones in the 1930s. They said that Alf Landon would be president over Franklin Roosevelt. This was because the people they sent surveys to were more wealthy and therefor more likely to vote Republican


What is noresponse bias?

Nonresponse bias is similar to selction bias except that in the case of nonresponse bias, the respondents themselves are the source of the bias. Because people who choose to answer surverys are systematically different from people who choose not to do so, surverys that have low response rates may yeild information that is highly misleading.

Example: Think of the Hite study about US women having extramarital affairs. Hite found that 70% of women had a extramarital affair. However, she only had 4,500 out of 100,000 respond to her mailed surverys, which was about a 4.5% response rate. This caused the results to be highly inaccurate.


What is history?

As the name implies, history refers to the changes that occur more or less across the board in a very large group of people such as a nation or culture


What is maturation?

In contrast to history, maturation refers to the specific developmental or experimental changes that occur in a particular person, or a particular age cohor, over time.

Examples: During times of famine in a perticular culture or region, most people lose weight. During adolescence, most people grow and gain weight.


What is regression toward the mean?

1. Regression toward the mean is the tendency for people who receive high or low scores on a particular measure to score closer to the mean on a subsequent testing.

2. The types of studies that are most likely to be infulenced by regression toward the mean are pretest-posttest studiess that do not have a control group

Example: Lebron James will most likely be on the cover of SI when he is scoring highest. If after the cover comes out he starts to score lower, this is not a curse, it simply is regression toward the mean.


What are testing effects?

Testing effects is a problem found in pretest-posttest designs that have no control group. This refers to the tendency for most participants to preform better on a test or personatilty measure the second time they take it.

Example: Imagine a student takes the Math SAT and gets a 505, then takes a SAT Math course and scores a 530 the next time. This same student could have gotten the same higher score simply because he took the test again, having nothing to do with the SAT Math course.


What is experimental mortality, or attribution?

1. Experimental mortality is when a number of participants fail to complete an experiment or study.

2. This can be especially troublesome when it happens in experiments or longitudinal studies that take a very long time to complete


What is heterogeneous attrition?

Heterogenous attrition occurs when the attrition rates in two or more conditions of an experiment are noticeably different.


What is homogeneous attrition?

1. Studies in which there is an equal level of attrition across all of the experimental conditions suffer from homogeneous attrition

2. Any individual differences associated with atrittion should thus be constant in the two different conditions


What is participant reaction bias?

Participant reaction bias is the bias that occurs when people realize they are being studied and behave in ways that they normally wouldn't.

Ways this could be problomatic:

1. The participants may try to do what what they think the researcher expects

2. The participants may try to do the opposite of what they think the research wants

3. The participants may try to whatever will make them look good


What is participant expectancies?

Participant expectancies occur when participants, consiously or unconsiously, try to behave in ways they believe to be consistant with the experimenter's hypothesis


What are demand characteristics?

Characteristics of an experiment itself that subtly suggest how people are expected to behave are referred to as demand characteristics 

Example: Simply having a gun in the room can cause people to be more aggressive


What is participant reactance?

The tendency of participants to try to disconfirm an experimenter's hypothesis represents a form of participant bias, participant reactance


What is evaluation apprehension?

Evaluation apprehension refers to people's concerns about being judged favorable or unfavorably by another person

Example: In an agression study, a participant may not want to shock someone because they realize that their shocks are being counted up as an index of aggression.


What is unobrusive observation?

1. Unobtrusive observations happen when research participants do not realize that they are being studied at all

2. In lab experiments in which people do know they they are being studied, unobtrusive observation may prevent people from realizing which aspect of their behavior is being studied


What is the mere measurement effect?

The mere measurement effect is when inquiring about future behavior may influence people to engage in this particular behavior, simply because they were asked about it

Example: If someone is asked if they will be buying a car in the next year they are slightly more likely to do it



What is eperimenter bias?

Experimenters bias is when experimenters' expectations about their studies bias their experimental observations

Example: Think of the "dull" and "bright" rats talked about in class. Experimenters found that the "bright" rats did better even though there was no difference in the rats.


What is a confound?

1. A confound (sometimes refered to as a nuisance variable) is a broad term used to identify any situation in which some additional variable (a) caries systematically with the independent variable and (b) also varies systematically with the dependent variable.

2. Confounds are variables that a researcher hadn't thought about or couldn't control, but ones that could be leading to a spurious (or false) association between an independent and dependent variable


What is an artifact?

1. An artifact is a broad term for important but overlooked variables that are held constant in a given study or set of studies.

2. Artifants do not threaten internal validity, but they do effect external validity

Example: If it is hot in the experiment and control condition of your experiment, you have no need to worry about how heat could become your independent variable. This would not effect the internal validity (causality) but it would effect external validity (generalizability). The same test done in an outside environment proabably won't have the same hot conditions.