AP Psych - Unit 1 Research Methods

experiments

required to confirm consistent, repeatable results. it confirms psychological findings, especially when it comes to cataloging and tracking behavior

intuition

our internal feelings or compulsions that are usually wrong

biases

tendency to favor or support only our narrow views

what components are necessary for an experiment

theories, hypothesis, and operational definitions

theories

explanation that organize observations and predict outcomes (overarching ideas)

hypothesis

testable prediction related to a theory that is confirmed or unconfirmed by an experiment

operational definitions

exact procedures to find a variable so the experiment can be replicated

correlation study

how two factors are linked and can predict eachother

-correlation DOES NOT equal causation

cross-sectional study

a type of observational study that analyzes data from a population, or a representative subset, at a specific point in time

longitudinal study

observational research method in which data is gathered for the same subjects repeatedly over a period of time

surveys

a questionnaire that self-reports the anonymous behaviors and characteristics of a certain group

big flaw: response bias

naturalistic observation

unhindered observations of animals or people in their natural environment (people watching)

case studies

one individual or group is studied in depth in hopes of revealing some universal truth

experimental group

group exposed to the treatment

control group

group NOT exposed to the treatment in an experiment

double-blind experiment

both research participants and staff are unaware of which group has placebo and which group has treatment

-used to eliminate bias or interference by researcher

single blind experiment

the participants are unaware of if they have the placebo or treatment. not as truthful as double-blind

histogram

bar graph depicting frequency distribution amongst various populations and groups

scatterplots

a graph cluster of two variables with a slop suggesting a positive (bottom left to top right), negative (top left to bottom right), or none

descriptive statistics

numerical data used to measure and describe characteristics of groups. used in reference to analyze graphs or other data

inferential statistics

to infer from sample data the probability of something being true of a population. used in reference to analyze graphs or other data

correlation coefficient

measures how strong a relationship is between 2 variables, ranging from -1 to 1 to represent the correlation. the closer it is to 0 the weaker it is

positive skew

a right skew distribution which means that bulk of information is skewed to the right

negative skew

a skew in data to the left

biomodal frequency distribution

a dataset./graph that contains two peaks

bell curve

graph/dataset with one peak

central tendencies

central or typical value for a probability distribution (measures of central tendencies are often called averages)

mode

the most frequently occurring score

mean

avg score

median

the middle score in a distribution

range

difference between highest and lowest scores

standard deviation

measure of how much scores vary around a mean

standard deviation 1

68%

standard deviation 2

95%

standard deviation 3

97.5% or 97

independent variable

experimenters manipulate one or more factors

dependent variable

the effect of IV on behavior and mental processes

confounding variables

undesired variables that can impact the data, and unless controlled for, skew and/or ruin the research findings. can be age, gender,e etc

statistical significance

the likely probability that chance was not responsible for results of the study.

-experiments are going to be judged, valued, or dismissed based on this

-if confounding variables ae eliminated it causes the experiment to be pure

random selection

a representative sample selected randomly from diverse population

random assignment

the randomly selected group is put into experimental or control groups randomly

what are random assignment and selection used for?

eliminated bias or lack of diversity

in order to make sure an experiment is valid, what must be there?

a large sample size

why does an experiment need a large sample size to be valid?

it will produce consistent or not anomalous results. if there is a small sample size, there are too many confounding variables that can impact the results

APA/BPS

determines the ethics and procedures, and requires compliance from any prospective experimenters. any experiment must be approved by respective organizations

HIPAA Privacy Rules

requires physicians (mental & physical) to keep patient information confidential. when one turns 18, must put parents on HIPAA form to allow them to access medical papers

local institutional review boards

screen research proposals and safeguards participants well being at each institution, adhering to the policies of APA, BPS, and federal gov. APA always has first say, then review boards approve

institutional animal care and use committee

federally mandated committee in US that oversees its institutions animal program, facilities, and procedures

four ethic rules for experiments

1. obtain informed consent

2. protect from physical harm or discomfort

3. keep information about participants confidential

4. fully debrief patients afterwards

5. patients can leave at any time, cannot force people to stay in the study

6. deception must be warranted

sample

subgroup of population

population

all individuals in a group to which the study applies

between-subjects design

participants in the experimental and control groups are different

experimenter bias

phenomenon that occurs when a researcher expectations or preferences about the outcome of a study influence the results obtained

demand characteristics

the clues participants discover about the purpose of the study, including rumors they hear about the study suggesting how they should respond

placebo

the imitation treatment

placebo effect

experimental participants change their behavior in the absence of any kind of experimental manipulation

within-subjects design

a research design that uses each participant as his or her own control

counterbalancing

a procedure that assigns half the subjects to one of the treatments first and the other half of the subjects to the other treatment first

quasi-experimental research designs

controlled experiments, but participants are not randomly assigned

retrospective

look at the effect and seek the cause

test method

procedures used to measure attributes of individuals at a particular time and place

reliability

consistency or repeatability

validity definition

correctly predicts what its supposed to do

elementary statistics

involves the analysis of numerical data about representative samples of populations

representative sample

sample mimics general population

lurking variable

variable is responsible for relationship

positive correlation

variables that increase and decrease together

negative correlation

as one variable increases the other decreases

illusory correlation

belief of correlation that doesnt exist

debriefing

must be told the true purpose of study