Research Methods exam 1

Empiricism

Empiricism

using evidence from the senses or from instruments that assist the senses as the basis for conclusions

basic research

research done to enhance the general body of knowledge ◦E.g., measuring motivations in depressed v. non-depressed individuals

translational research

uses findings from basic research to develop and test applications ◦E.g., developing a therapy for depression that affects motivation

applied research

research done with a practical problem in mind. E.g., developing new therapy for depression

theory

a set of statements that describes general principles about how variables relate to one another e.g., What is the link between violent video games and aggression?

hypothesis

a way of stating the specific outcome the researcher expects to observe if the theory is accurate (PREDICTION) ◦e.g., Playing a violent video game will increase subsequent aggression

3 features of a good theory

• supported by data

• falsifiable

• parsimonious

Parsimony (Occam's Razor)

the simplest explanation is the best

Falsifiability

Can the claim be disproved?

• theories are often unfalsifiable

Why is proof impossible? If we cannot prove, then what do we do in science?

we never actually 'prove' anything ◦Our theories can only be consistent with the data (or 'not yet falsified')

A scientific view of the world simply represents the weight of converging evidence ◦Given the data, what is most likely to be correct

Scientific method

A series of steps followed to solve problems including collecting data, formulating a hypothesis, testing the hypothesis, and stating conclusions.

Theory-Data Cycle

theory, research questions, research design, hypothesis, data

Personal experience

relying on personal experience can lead us to erroneous conclusions

• lack of comparison groups

• probabilistic Ex: working out clears my head

Confounds- other factors which may have caused a change in your outcome of interest

intuition

◦We tend to reinforce our previously-held ideas

authority

◦Authority figures are subject to the same biases produced by personal experience and intuition that we are

ex; learning styles

How do confounds and comparison groups affect these sources of information

What is meant by real-world events being probabilistic?

findings will not explain all individuals all of the time- only on average

Good-story heuristic

if it sounds plausible, believe it

availability heuristic

we judge the likelihood and frequency of an event by the ease with which relevant examples come to mind

confirmation bias

we seek out and attend to evidence that confirms our beliefs, but ignore evidence that contradicts them

confirmatory hypothesis testing

the tendency to ask only the questions that will lead to the expected answer

empirical scientific thinking

based on actual data, not just intuition or personal experience

objective scientific thinking

◦utilizes clearly defined methods that allow others to collect and evaluate the same data

systematic scientific thinking

observations are structured so that they can speak directly to the issue being evaluated

variable levels

nominal, ordinal, interval, ratio

measured variable

a variable that is being observed/recorded

manipulated variable

: a variable that is directly under the control of the researcher

independent variable

variable that is manipulated

dependent variable

The outcome factor; the variable that may change in response to manipulations of the independent variable.

operational definition

defines a concept by stating precisely how the concept is measured and/or manipulated in a particular study

frequency claim

describe a particular rate or level of a single variable

Ex: 10% of Americans regularly exercise

association claim

state that one variable is associated with another variable ex; aggression is higher during the warmer months

causal claim

states that one variable is responsible for/caused changes in another variable

ex: alcohol consumption impairs motor skills

Positive correlation

two variables change in the same direction, both becoming either larger or smaller

negative correlation

as one variable increases, the other decreases

no association

when the points in a scatter plot do not have any pattern

construct validity

umbrella term to determine if the underlying, unobservable psychological entity is actually being measured.

4 big validities

construct, external, statistical, internal

Type 1 error

false positive

type 2 error

false negative

3 criteria for causality********

covariance, temporal precedence, internal validity

ethical issues of the Milgram Obedience Study

-extreme stressful to teacher participants

• some experienced long-term guilt after being debriefed

• balanced potential risk to participants and the value of knowledge

ethical issues of the Tuskegee Syphilis experiment

human subjects werent treated respectfully, harmed, members of disadvantaged group

Belmont Report

Purpose was to discuss ethical principles researchers should follow ◦Called partly in response to Tuskegee study Provided three main guiding principles for research: 1.Respect for Persons 2.Beneficence Justice

additional ethical principles by the APA

IRB- Institutional Review Board

• informed consent

• deception -debriefing

• data fabrication and falsification

Anonymous vs confidential data

◦Anonymous—researchers do not collect any information that could be used to identify (e.g., name, birthdate)a participant

◦Confidential—researchers collect some information that could be used to identify (e.g., name, birthdate) a participant, but they prevent its disclosure

informed consent

◦Researcher must explain the study to participants in everyday language and give them a chance to decide whether to participate.

deception

Researchers withhold some detail(s) of the experiment through omission or commission:

Debriefing

◦Describe the nature of the deception and why it was necessary ◦Always provided in studies with deception

data fabrication

◦Researcher invents/creates data that fits hypotheses

data falsification

◦Researcher influences study results by: ◦Selectively deleting data ◦Influencing participants to behave in hypothesized way

observational measure

◦Recording observable behaviors or physical traces of behaviors

physiological measures

◦Recording biological data such as brain activity, hormone level, or heart rate

self-report measures

◦Recording responses to ratings scales, questionnaires, and/or interviews Multiple rates possible for same question

scales of measurement

nominal(names, ex: eye colors, religions) , ordinal, interval, ratio

categorical variable

levels are categories

quantitative/continuous variable

levels are coded with meaningful numbers along a continuum.

3 types of quantitative variables

ordinal- order (1st, 2nd, level of education interval- equal intervals (temperature, IQ) ratio- Zero means something, height weight

Reliability

how consistent the results of a measure are.

Validity

whether the operationalization of a construct is measuring what it is supposed to measure

relationship between reliability and validity

possible to be reliable and not valid

not possible to be valid and not reliablfe

test-retest reliability

simply involves measuring the same individuals twice and correlating their scores

interrater reliability

reliability focuses on whether two individuals use the operational definition the same way

internal reliability

focuses on whether people give consistent responses to the test uses cronbachs alpha

5 types of construct validity

1.Face validity 2.Content validity 3.Criterion validity 4.Convergent validity Discriminant validity

Which of the types of construct validity are subjective and which are empirical?

subject: face and content empirical; convergent, criterion, and discriminant

convergent validity

asks whether a measure is correlated with measures of similar constructs ◦E.g., Does a measure of intelligence correlate with other aptitude measures (e.g., Stanford-Binet vs. Wonderlic)

discriminant validity

asks whether a measure is correlated with measures of dissimilar constructs

external validity

extent to which we can generalize findings to real-world settings