research methods (modules 4-8) Flashcards
hindsight bias
- the tendency to believe after learning outcome, it had been forseen by one
- (i knew it all along)
when people can easily imagine something as common sense…
their hindsight bias allows them to believe the statement’s true
over confidence
when you think you know more than you do
hindsight bias, overconfidence, and our tendency to find patterns
leaves us vulnerable to overestimating “common sense”
theories explain behavior or events by…
offering ideas that organize observations
scientific method
a self-correcting process for evaluating and analyzing theories
1. develop a hypothesis
2. perform controlled test
3. gather objective data (direct observation)
4. analyze results
5. publish, criticize, replicate results
hypothesis
testable predictions that specify what supports the theory and what doesn’t
operational definition
carefully worded statement of exact procedures used in research study
a theory is useful if it…
-organizes observations
-implies predictions
-stimulates further research
3 categories of research methods
descriptive methods, correlation methods, experimental methods
descriptive methods
behavior is described through case studies, surveys, and naturalistic observation
correlational methods
associate different factors and variables
experimental methods
manipulation variables to discover their effects
case study
in depth study and analyses of individuals or groups with the goal of revealing a universal truth
naturalistic observations
recording the natural behavior of many individuals without trying to manipulate the situation
surveys
questioning a representative and random sample of the group to obtain self reported attitudes or behaviors of a particular group
naturalistic observations and case studies cannot…
explain behavior but they can describe it
sampling bias
a flawed sampling process that produces an unrepresentative sample
population
all those in a group being studied, from which samples may be drawn
random sample
a sample that fairy represents a population because each member has an equal change of inclusion
wording effects
even subtle changes in the order or wording can have major effects on how participants will answer questions
correlation
a measure of the extent to which two factors vary together, and thus of how well either factor predicts the other
correlation coefficient
a statistical measure of the relationship between two things from -1.00 to +1.00
variable
anything that can vary and is feasible and ethical to measure
scatterplot
a graphed cluster of dots, each of which represents the values of two variables]
perfect negative correlation
r = -1.00
no correlation/relationship
r = 0.00