Chappy 2: Research Methods Flashcards
define confounding variables
Two variables are linked together in a way that makes it difficult to sort out their specific effects
extraneous + IV = researcher cannot figure out which impacted DV
Correlation
degree to which two variables relate - does not imply causation
Correlation coefficient
Numerical index of the degree of relationship between two variables, positive and negative and how strong
Positive: co-vary in the same direction
negative: vary in opposing directions (has - sign)
coefficient can vary between 0 and +1 (+) or 0 and -1 (-)
Descriptive Stats
used to organize/summarize data
Mean - average
Median - middle number
Mode - most frequently occurring
Variability
how much scores deviate from each other and the mean
standard deviation:
62- 1sd
95 - 2sd
99- 3sd
Normal distribution
symmetrical/bell shaped curve - pattern in which human characteristics are dispersed in society
Very important for wide range of inferential stats
Response set
tendency to respond in a particular way
Halo effect
overall evaluation spill over to influence more specific ratings
Statistical significance
There is a small probability that the observed findings are due to chance
Three criteria to establish cause
third variable problem
Two variables must be associated
One variable must obviously proceed the other (cause comes before effect)
No other variable may cause the effect
Third variable problem: IV + DV and ?, ex: children’s/vocabulary and age
inferential statistics
Deals with methods for making appropriate inferences about populations on basis of samples
Allow researchers to calculate precisely the probability of making a mistake
Case studies
In depth study of exceptional individuals/groups, ex: shereshevsky - synesthesia
Naturalistic observation
Careful observation of behaviour w/out intervention, ex: collett + marsh - collision avoidance on a pedestrian crossing
Reactivity: subjects’ behaviour is altered by observer
Survey Research
questionnaires/interviews to gather info
