LSU PSYC 2017 Exam 2 Cobb

research samples are foundational to

psychological research

populations refer to the

entire group

we make inferences about our population of interest based on

findings from research (sample)

biased sample - unrepresentative sample

some members of the population of interest have a much higher probability of being included in the sample compared to other members

unbiased sample - representative sample

all members of the population have an equal chance of being included in the sample

self-selection

sampling only those who volunteer

external validity

an indication of how well the results of a study generalize to, or represent, individuals or contexts besides those in the study itself

generalizability

the extent to which the subjects in a study represent the populations they are intended to represent; how well the settings in a study represent other setting contexts

sample

the group of people included in a research study

sampling

how we get from population to the sample, the process of selection a subset of people in the population

which term does not belong with the other?

a. generalizable sample

b. externally valid sample

c. representative sample

d. biased sample

d. biased sample

population of interest: drivers.

method 1: asking drivers to complete a survey when they stop to add coins to a parking meter

method 2: obtaining a list of licensed drivers in each state and selecting a sample using a random number generator

method 2

population of interest: students who have taken PSYC 2017 at LSU

method 1: obtaining a list of all students who have taken PSYC 2017 and select a random set of 100 students

method 2: obtain a list of students from Rate My Professor and contacting those students

method 1

samples should be representative of our

population of interest

convenience sampling

accessing our sample from a convenient group of people, such as friends, alumni, etc.

purposive sampling

purposefully seeking out people who might fit the population of interest

quota sampling

recruiting based on groups within the population of interest such as 50/50 male/female

snowball sampling

asking participants to provide information of others who might want to participate / be eligible

non probability sampling (higher likelihood of recruiting biased samples)

convenience

purposive

quota

snowball

probability sampling

systematic sampling

cluster sampling

multistage sampling

stratified random sampling

over sampling

(SMOCS)

systematic sampling

randomly choose and number and then identify every x'th participant

cluster sampling

randomly selecting clusters of participants from population

multistage sampling

create random clusters and then randomly sample from those clusters

stratified random sampling

not unlike quota sampling: "strata" or groups are identified and randomly sampled

oversampling

intentionally over representing groups in stratified random sampling

random sampling

creating a sample using some random method so that each member of the population of interest has an equal chance of being in the sample

random sampling increases

external validity

random assignment

used only in experimental designs to assign participants to groups at random

random assignment increases

internal validity

in a frequency claim

external validity is a priority

non probability samples in the real world

non probability samples in research studies

cases where external validity is a lower priority

sampling technique determines external validity

not sample size

open-ended questions

allows respondent to supply their own response (e.g., what do you love about being a psychology student at LSU?)

forced-choice format

respondents have to choose between options given to them (e.g., yes or no)

Likert scale

for interval variables, we can ask people to "rate on a scale" of 1-5 or 1-10, for example (e.g., please rate on a scale of 1 to 5, with 1 being "strongly disagree" and 5 being "strongly agree" )

semantic differential format

respondents are asked to rate using a numeric scale anchored by objectives (e.g., rate your professor on level of difficulty on scale from 1 to 5 [hardest thing I've ever done])

Leading questions

Sometimes two questions seem to be asking the same thing but yield very different responses depending on how they are worded

How fast do you think the car was going when he hit the other car? How fast do you think the car was going when he smashed into the other car? The first option here is less of a loaded or leading question

If the goal of a survey is to capture respondents' true opinions

questions should be worded as neutrally as possible.

doubled-barreled questions

asking two questions in one

Do you agree that the Second Amendment to the United States Constitution guarantees your individual right to own a gun and that the Second Amendment is just as important as your other constitutional rights? This should be two questions, not one question with two parts.

If the goal of a survey is to capture respondents' true opinions

then questions should be asked as simply as possible

negatively worded questions

The more cognitively difficult a question is for people to answer, the more confusion there will be, which can reduce the construct validity of the item. Using double negatives can make questions more difficult for respondents to process.

Does it seem possible or does it seem impossible to you that the Nazi extermination of the Jews never happened?

Negatively worded questions can reduce construct validity by adding to the cognitive load, which may interfere with getting people's true opinions.

question order

Earlier items can influence the way respondents interpret later items.

Suppose the first item on the survey is rather sensitive. That might influence the way respondents answer subsequent questions because they were "primed" by the first item.

One way to control for order effects is to make different versions of the survey with questions in different orders.

Response bias

is any bias in people's response process

Response sets

a general tendency to answer to all the questions in a similar manner regardless of the content of the question.

"yea-saying" (acquiescence)

people answer positively to all the questions • For example, a respondent might answer "5" to every item on Diener's scale of subjective well-being., not because they are a happy person, but rather because they are using a yea-saying shortcut

Fence sitting

people who play it safe by choosing a response in the middle of the scale.

This might involve providing a neutral response or responding, "I don't know."

encouraging accurate responses

• Trying to look good

• Socially desirable responding/faking good

• Faking bad

• Solution: Remind participants that responses are anonymous

how to check for accurate responding

response time

attention check items

response inconsistently

observational research

"A type of study in which individuals are observed or certain outcomes are measured. No attempt is made to affect the outcome (for example, no treatment is given)."

Behaviors can be interpreted differently based on

extraneous information.

Observer bias

when observers see what they expect to see

Expectancy (Observer) effects

when the participants modify their behavior to match observer expectations.

Biases may also be driven by

participant characteristics (e.g., race, gender, etc.)

Masked research design

In a masked design, the observers do not know to which conditions the participants have been assigned, and they are not aware of what the study is about (one way to prevent observer bias and effects)

Reactivity

Participants can alter their behavior just because they know someone is paying attention to them

Is it ethical for researchers to observe the behaviors of others?

It depends.

Survey Research

- Has at least two measured variables that are both self-reported by participants

- Lots of scales and survey questions

- Surveys can take place anywhere

Observational Studies

- Researcher observes and records participant behaviors

- Can include a survey and a behavioral observation

- Participants may be invited into a lab or observed IRL

survey research / observational studies both

- Both can be conducted at one time point or over time

- There is at least one measured variable

- Can support frequency or association claims but never causal claims

- External validity and construct validity are important

- The operationalization of measured variables is key

- The researcher plays little to no role in the active collection of data so as to not influence the study

Key Differences from experiments

- Neither type of study is experimental in nature

- The research context should have no effect on the outcome; researchers are simply looking for relationships and observing

casual claims

a claim arguing that a specific change in one variable is responsible for influencing the value of another variable

causal claims are the

boldest claims scientists can make

experiments are the

only way to make truly casual claims

internal validity

does the study design rule out alternative explanations for the results?

manipulated variable / independent variable

a variable in an experiment that a researcher controls, such as by assigning participants to its different levels (values)

measured variable / dependent variable / predictor / criterion

a variable in a study whose levels (values) are observed and recorded

independent variable

in an experiment, a variable that is manipulated

dependent variable

in an experiment, the variable that is measured

control variable

in an experiment, a variable that a researcher holds constant on purpose

why experiments support causal claims

experiments establish covariance

experiments establish temporal precedence

well-designed experiments establish internal validity

covariance

do the results show that the casual variable is related to the outcome variable? are distinct levels of the independent variable associated with different levels of the dependent variable?

temporal precedence

does the study design ensure that the causal variable comes before the outcome variable in time?

the role of independent variables

allows us to compare one condition to another (i.e., comparison group)

independent variables answer

compared to what?

timing is key

the cause precedes (comes before in time) the effect

A main effect is

A. the most important effect.

B. found only in studies with one independent variable.

C. the overall effect of one independent variable at a time.

C. the overall effect of one independent variable at a time.

An interaction can occur in an experiment with

A. one independent variable.

B. two independent variables.

C. two dependent variables.

B. two independent variables.

In a factorial design, a participant variable is treated like a(n) A. independent variable.

B. dependent variable.

C. design confound.

A. independent variable.

Imagine a factorial design that has two independent variables: one with two levels and the other with three levels. It would be represented in factorial design notation as

A. 2 x 3.

B. 2 x 2 x 3.

C. 2 x 2 × 2.

D. 2 x 2.

A. 2 × 3.

Which of the following phrases provides a clue that a study used a factorial design?

A. "controlled for"

B. "taking into account"

C. "it depends"

C. "it depends."

Experiments with Two Independent Variables Can Show Interactions

Intuitive interactions

Factorial designs study two independent variables

Factorial designs can test limits

Factorial designs can test theories

Interpreting factorial results: main effects and interactions

Interactions

Experiments with two IVs allow the experimenter to test multiple hypotheses at the same time.

Interaction

An interaction between two independent variables occur when the effect of one variable on the DV depends on another variable.

Key phrases

- "The value of education on future earning depends on the major"

- "The effect of caffeine on performance depends on the difficulty of the test"

- "Participants who receive both an SSRI and CBT see a greater reduction in depressive symptoms than those with SSRI or CBT alone."

A psychologists favorite phrase

"it depends"

interaction effect

Another phrase indicating a moderator

With Factorial Designs, IVs are also called

factors

Number of _____ in a factorial design is all possible combinations of the IVs

cells

Main effects

the effect of one IV on the DV (One main effect for each IV)

The degree to which the effect of the a IV

depends on a second IV

When there is an interaction in your data, it is usually

more important than any main effects you may find.

Because interactions tell us about another variable that can influence a relationship we're interested in

○ When a relationship is stronger

○ When a relationship is weaker

○ For situations where a relationship exists or doesn't exist

interactions are more representative of the real world because

they take multiple variables into account

Factorial designs can test

limits; theories

Multiple IVs usually means we have multiple levels of the IV

which creates multiple cells or unique conditions

if some outside event (such as a change in weather) influences most of the people in a study between the time of the pretest and posttest, this would be a(n)

history threat

Dr. Wilson conducted a long term study on friendship. he noticed that the most introverted people dropped out by the 3rd session. Therefore, his study might be affected by which of the following internal validity threats?

attrition

Which of the following is NOT a source of unsystematic variance?

design confounds