The Milgram Experiment

an investigation of how far people would go to obey an instruction provided by an authority figure

The Scientific Method

describes the cycle researchers use to methodologically answer questions

Identify question/problem, gather information and establish a theory, develop a hypothesis, design and conduct an experiment, analyze data and draw conclusion, refine and repeat

what is the scientific method steps?

the tuskegee syphillis study

a study which led to developing a consensus of guidelines for the treatment of all research participants due to how misleading patients in this study led to preventable deaths

the hawthorne effect

when participants alter their behavior due to their awareness of being observed

respect for persons

value that all people deserve to have their autonomy--their right to self-govern--respected. informed consent, consider vulnerable populations, decisional impairment (lack of understanding rights and risks), and situational vulnerability (outside pressure). Plus, if deception is necessary it should pose minimal risk

beneficence or concern for welfare

do good for participants and society, weight the benefit of knowledge gained from costs, and avoid breaches of confidentiality

justice

strives to establish "equality" in the research process, with the exception of an inclusion criteria for the study or exclusion criteria, and eligibility criteria, which all ensures that the participants are addressing the research question

Institutional Review Board

a committee of independent individuals who review and assess if the research project will be carried out in a manner consistent with the general ethical principles

fidelity and responsibility (APA)

establish relationships of trust with those they work with

integrity (APA)

psychologists promote the pursuit of truth and accuracy and do not engage in fraud

integrity with relationships (CPA)

psychologists are committed to openness and accuracy and minimal bias in their relationships with individuals and society

descriptive methods

identifying "what is" without necessarily understanding "why it is"

naturalistic observation (field research)

the observation of behavior as it happens in a natural environment, without any manipulation or control of conditions

interrater reliability

when all of the researchers agree on the differences in the study

operational definition

created when designing a study and it is how researchers decide to measure (operationalize) a variable

construct validity

concerns about the quality of a study's operationalization of a variable challenge its _____

participant observation

a research method in which the researcher becomes a part of the group under investigation

case study

an in-depth analysis of a unique circumstance or individual

surveys

an efficient way to collect information and capture people's opinions, attitudes, or experiences

sampling error

occurs when the sample differs meaningfully from the population

random sampling

most effective way to achieve a representative sample

question order bias

answering one question first influences the answer to a later question

response bias

the tendency for people to answer questions in a way they feel they are expected to answer, or in systemic ways that are otherwise inaccurate

acquiescent response bias

refers to a tendency for participants to indiscriminately "agree" with most, if not all, items on a survey regardless of their actual opinion

socially desirable bias

a systematic approach to answering questions where the bias is not indiscriminate; instead, participants respond in specific ways that they believe would be acceptable by others

illusory superiority

the tendency to describe our own behavior is called

volunteer bias

those who volunteer may have differed systematically from those who refused; thus participants may have disproportionately represented individuals already comfortable discussing taboo topics

correlational research

after collecting data, researchers usually verify between variables, showing how closely two variables are related

scatterplot

common way to display a correlation

positively correlated

when one variable increases so does the other, when one decreases so does the other

negatively correlated

when an increase in one variable is accompanied by a decrease in another

zero correlation

there is no apparent relationship between variables

correlation coefficient

quantifies the strength of a correlation by how closely the two variables are related. the closer the value is to 1.0 regardless of (+,-), the stronger it is.

causality

that one variable directly affects another

experimental control

researchers conducting an experiment exert some degree of control over the environment to determine if their manipulation causes any changes to participant's responses and actions

manipulated independent variables

the aspects of the environment that are manipulated

experimental group

receives the treatment of interest

comparison group

identical to the experimental group but receives a "known" or "standard" treatment

control group

if the comparison group represents a lack of treatment entirely

measured independent variables

aspects of the environment that are not manipulated by the researchers but are also not influenced by other aspects of the study

constant

when everyone in the study is the same along a certain dimension, and that dimension has only one level

confounding variables

extraneous factors that can influence both the independent and dependent variables in a study, potentially leading to misleading conclusions about cause-and-effect relationships.

internal validity

success at eliminating other possible explanations that might explain an observed relationship, has a HIGH degree of _____

dependent variable

outcome measure, the variable the experimenter counts or measures, and generally believes is affected by one or more of the independent variables

consistency with prior research or theory, should be as simple as possible, specific, testable, falsifiable

experimental hypothesis characteristics are this:

random assignment

ensures that there is no systematic bias when assigning participants to levels of the manipulated independent variable

external validity

how generalizable the study findings are

construct validity

how the evidence itself was collected, how well-designed, and how well the study operationalizes any measures or manipulated variables

ecological validity

lab vs. real world in the experiment and how it applies differently

a stratified sample

used when a population has identifiable subgroups

internal validity

how well a study rules out alternative explanations for an observed relationship

temporal order

variables thought to be causes must come before variable thought to be effects

an established correlation between the variables of interest

if they seem to correlate as long as there is a non-zero r-value or d-value that describe the relationship between the two variables, this prerequisite is met

third variables

must be eliminated as alternative explanations. threats are met by holding constants and randomly assigning participants

statistical validity

interrogate the aspect of a claim's evidence, whether the researchers have conducted statistical analyses correctly, and measuring central tendencies

mean

the average: used most commonly but outliers can distort it

median

middle number

mode

most useful for categorical data, such as car color- most common one

standard deviation

average distance of each score from the mean. if the scores are spread out then this is large, if they are clustered together this is smaller.

inferential statistics

methods that let us infer patterns from data and interrogate statistical validity by testing whether our interpretations are reasonable

confidence interval

useful when we want to know how likely the mean differs from a meaningful value like zero (no effect)

mean (M), standard deviation (SD), and the number of participants (n)

what you need to calculate the confidence interval

if it has 0 in the range then you cannot confidently say that the treatment was effective

what does the Confidence interval range tell us?

correlational inferences

lets researchers infer the strength and direction of a relationship

cohen's d

measure of effect size that tells us about how meaningful the difference between two group averages is, given the amount of variability in each group

0 means no effect, less than 0.5 is a small effect, greater than 0.5 is medium, greater than 0.8 is large. Larger means likely important differences between groups

how to read cohen's d numbers

null hypothesis

calculates a p-value, the probability of obtaining our results (or more extreme ones) if the null (no difference) were true

if p is less than 0.5 we reject the null and infer that the effect is unlikely due to chance

how to read the null hypothesis

the placebo effect

a phenomenon where a person experiences a real improvement in their condition after receiving a treatment that has no therapeutic effect, often due to their belief in the treatment's efficacy

operational definition

defining what you are manipulation in as much detail as possible