Methods Flashcards
hindsight bias
the tendency to believe, after learning an outcome, that you knew this info prior
overconfidence
humans tend to think they know more than they do
theory vs hypothesis
theory- a proven explanation of organized principles
hypothesis- a testable prediction that has not been completely proven
operational definition
a report of all procedures to specifically define your experiment’s variables
population
the participants in the group being studied
random sample
a sample of the population that can unbiasedly and equally report results
correlation
a measure of how much one factor predicts another
correlation coefficient
a statistical index of the relationship between things on a scale between -1 to +1.
positive=increasexincrease w/ high correlation
negative=increasexdecrease w/ high correlation
zero= no correlation
illusory correlations
perceived but nonexistent correlations (we notice coincidences more often) between vivid cases
experiment
a way to research the effects of an independent variable on a dependent variable
random assignment
assigning participants to experimental and control group by chance
double blind procedure
neither the participants nor staff know whether participants have received treatment or placebo- corrects volunteer and experimenter bias
placebo effect
experimental results caused by expectations alone
measures of central tendency
mean, median, mode
measures of variation
range and standard deviation
false consensus
incorrectly believing everyone agrees with your own opinions
hawthorn effect
people change the way they act in the experiment because they know they are being watched
single blind procedure
participants don’t know which group they’re in- corrects participant/volunteer bias
informed consent
people have a right to know they are being studied and what it is
deception
not clarifying an aspect of an experiment
in order to do this you need special permission from the psych committee (IRB)
debrief
after experiment interview to assess participant wellbeing
stratified sampling
instead of random sampling, you sample a percentage that is proportionate to the population
third variable problem
two things appear correlated but there is a third variable that correlates with both
case studies
observing to discover more about universal principles based on one person/small group
can study unique things
can’t generalize
surveys
asking a group for their attitudes/beliefs directly, based on self reports
provides large random samples BUT sampling errors common (wording+lying)
naturalistic observation
experimenter observes and records behavior without interfering/manipulating the situation
provides insight on natural conditions BUT cannot manipulate variables so does not fully explain behaviors
longitudinal studies
measuring the same group of time
time=IV
developmental research
better prediction of changes BUT takes time and group gets smaller
cross sectional studies
measuring different groups to compare
pre-determined IV (not manipulated)
takes less time BUT may not be accurate due to cohort effect
testing
standardized questions normed against a large group
compares individual to a population
scatterplot
plot two measured variables against each other
no IV, two DV
can help with prediction BUT not causation
laboratory observation
experimenter changes the IV and randomly assigns to conditions of IV to measure DV
determines causation BUT artificial environment; Hawthorn Effect
confidentiality
participant information is not released without consent
validity vs reliability
Reliability refers to the consistency of a measure (whether the results can be reproduced under the same conditions). Validity refers to the accuracy of a measure (whether the results really do represent what they are supposed to measure).
