PSY 301 Exam 1

Types of reliability = consistency

-1. Test-retest reliability (scores at time 1 = scores at time 2) -use scatterplot or r to evaluate - PP slide 11 -2. Interrater reliability (inter-observer) -percent agreement (85%)t vs correlation (.7); how to increase (clarify instructions; train observers) -use scatterplot or r to evaluate - PP slide 12 -3. Internal reliability (Internal consistency) -Cronbach's alpha (criteria - .9; .8; .7; .5)

Frequency claims (examples of)

-A frequency claim describes a particular rate or degree of a single variable (involve only 1 measured variable) -example=Just 15% of Americans smoke.

What are the components of an empirical journal article?

-Abstract -Introduction -Method -Results -Discussion -References

Association claims (correlational)

-An association claim argues that one level of a variable is likely to be associated with a particular level of another variable (involve at least 2 measured variables)-said to correlate -positive association:romantic partners who express gratitude are 3 times more likely to stay together -negative association:people who multitask the most are the worst at it -zero association:a late night dinner is not linked to childhood obesity

4 types of validity

-Construct=are you measuring what you claim to be? -External=generalizibility -Statistical=are you using the appropriate test statistic? -Internal=cause/effect; random assignment increases internal validity

Measurement scales-interval

-Differences between categories are meaningful quantities -Differences represent equal increments (intervals) -Not a true zero (zero represents zero degrees not no temp.)

Measurement scales-ratio

-Ordering of scores -Equal intervals -True zero (how many shoes do you own?) -Physical attributes of objects

Causal claims

-Two variables, one of which causes the other -One manipulated variable (x) & one measured variable (y)

known groups paradigm

-a method for establishing criterion validity -researcher tests two or more groups, who are known to differ on the variable of interest, to ensure that they score differently on a measure of that variable

Applied versus basic versus translational research (goals and examples of each)

-basic research goal=enhance general body of knowledge (ex=how stress influences academic cheating) -applied research goal=solve some type of real-world problem (ex=what can we do to support women with depression?) -translational research goal=bring together applied and basic (ex=can we apply Pavlov's dog research to humans?)

History of human knowledge-Philosophy & Physiology

-basis of experimental psych -philosophy=speculation vs experimentation, empiricism -physiology=pioneered early techniques

Types of measurement

-behavioral=direct observation -physiological=internal bodily process -self-report-most common

Interrogating frequency claims

-construct=needs operational definition of what is being studied -external validity=generalizibility

Interrogating association claims

-construct=needs operational definition of what is being studied -external=generalizibility -statistical validity=using proper test statistic

Measurement scales-nominal

-events assigned to categories -arbitrary # assignment -no order implied -weakest level

Experiments can support causal claims

-internal validity is top priority -experiment, IV, DV, random assignment

Finding & reading research

-journal articles (empirical versus review); edited and full-length books -Psyc Info versus Google Scholar

Scientific journal versus journalism (risks & benefits of journalism coverage)

-journalism audience = public -journalists turn scholarly article into readings that are accessible to public but is the story accurate?

History of human knowledge-Metaphysical

-metaphysical=supernatural -animism=every object has a soul -explaining behavior based on gods & religion -astrology=celestial bodies attributed to behavior

Measurement scales-ordinal

-ordering of objects, behaviors, or individuals on some dimension -cannot quantify differences between categories

Research versus Experience

-research=probabilistic (findings are not expected to explain all of the cases all the time) -experience has no comparison group

Theory-data cycle-what makes a "good" theory? = falsifiable; parsimonious; weight of evidence

-supported by data -falsifiable=can be shown as false by experiment -parsimonious=simple -weight of evidence=found data consistent with theory

Theory-data cycle -theory; hypothesis; data; empiricism

-theory=general statement about relationship between variables -hypothesis=make testable predictions based on theory -data=collecting data that may or may not support hypothesis and theory -empiricism=reflecting back on data

Interrogating causal claims

3 conditions that need to be present= 1. co-variation=show that variables are related 2. temporal sequence=show that x comes before y 3. eliminating confounds b/c they threaten internal validity

Operational versus conceptual definitions (variables) (examples of too)

A conceptual definition tells you what the concept means, while an operational definition only tells you how to measure it -operational definition=deprived of food for 12 hours -conceptual definition=hunger is the desire for food

Confounds

Factors that undermine the ability to draw causal inferences from an experiment-variables

Type I & Type II Errors

Type I=researchers conclude that there is an effect when there isn't Type II=researchers conclude that there is not an effect when there is

Research versus Intuition

Ways where Intuition is Biased: -being swayed by a good story -availability heuristic: people decide that what comes to mind more is what is true -confirmation bias: people seek out information that confirm their beliefs -bias blind spot: everyone but "me" falls for biases

Sasha believes that she is a nice person. To confirm that, she asks all her friends whether she is a nice person; they all agree that she is. Sasha concludes that she is a nice person and says she has evidence of it. However, she does not ask any of her enemies whether they think she is a nice person. This is an example of which of the following? a. confirmation bias b. availability heuristic c. fourth cell reasoning d. overconfidence

a. confirmation bias

convergent validity

an empirical test of the extent to which a self-report measure correlates with other measure of similar construct -example:should correlate with other studies of depression

Salma conducts a study and finds that her data do not completely support her theory. Which of the following statements should she avoid saying? a. "my data are inconsistent with my theory" b. "my data disprove my theory" c. "my theory needs amending" d. "I may need to collect more data"

b. "my data disprove my theory"

Which of the following is an example of applied research? a. a school psychologist who is interested in the components of self-concept b. an educational psychologist who looks for a way to increase math skills in 8 year olds c. a personality psychologist who studies the difference between introverts and extroverts d. a cognitive psychologist who looks at the differences in problem solving abilities of women and men

b. an educational psychologist who looks for a way to increase math skills in 8 year olds

Compared with doing a generic internet search, why is PsycINFO a superior way to find scientific sources? a. it is free b. it searches only sources in psychology and related fields c. it can be done on any computer d. it searches research scientists' websites

b. it searches only sources in psychology and related fields

Dr. Ramon makes the following claim: "Watching television leads people to spend less time communicating with their spouses, study says." Dr. LaSalle makes the claim: "Research shows that making more money correlates with spending less time talking with your spouse." Which type of claim is Dr. Ramon making? a. anecdotal claim b. association claim c. causal claim d. frequency claim

c. causal claim

What does it mean that behavioral research is probabilistic? a. conclusions drawn from behavioral research are probably true b. behavioral research involves probability sampling c. inferences drawn from behavioral research are not expected to explain all cases d. behavioral research requires the calculation of probability estimates

c. inferences drawn from behavioral research are not expected to explain all cases

Categorical versus continuous variables

categorical=variable whose levels are categories (male and female) continuous=numerical

Articles that could be considered journalism: a. are typically written by scientists b. are typically written for scientists c. are hard to access d. do not require specialized education to read

d. do not require specialized education to read

discriminant (divergent validity)

empirical test of the extent to which a self-report measure does not correlate strongly with measure of dissimilar constructs -example: should not correlate with with constructs that are very different from depression

criterion validity

est. the extent to which a measure is associated with a behavioral outcome is should be associated with -example:what test would correlate with key behavior needed to success in job?

constructs

explanatory variable which is not directly observable

Face and Content validity

face validity= It looks like what you want to measure content validity=The measure contains all the parts that your theory says it should contain

What validities are most important for what claims?

frequency=construct & external association=construct, external, & statistical casual=internal

Producers versus consumers of research - why are both important?

producer= for coursework in psych, for grad school, for working in a research lab consumer=for psych classes, when reading news stories based on research, for future careers

Peer review cycle

scientists share the results of their research by publishing in peer-reviewed scientific journals

Empiricism

systematic observation

Variables (manipulated versus measured) versus constants

variables change while constants stay the same -manipulated variable=independent, predictor variable -measured variable=dependent variable