Research Methods Flashcards
Theory
An idea designed to explain existing facts and make predictions about yet to be discovered facts
Empirical Research
Theory testing and generate hypothesis
Null Hypothesis
The hypothesis that there is no significant difference between specified populations, any observed difference being due to sampling or experimental error.
Research hypothesis
x causes y
Scientific Method
Process of basing one’s confidence in a idea on systematic, direct observations, usually with research studies
Theory-Data cycle
Scientific method cycle. Allows the collection of data to either confirm or disconfirm a theory.
Hypothesis
Specific prediction about a variable’s behaviour in a study if correct
Replication
Repeating the essence of a research study, usually with different participants in different situations, to see whether the basic finding extends to other participants and circumstances
To conclude causation…
- Two variables must be correlated
- One variable must come before the other
- No other reasonable alternative explanation
Confounds
Factors that undermine the ability to draw causal inferences from an experiment.
Random Assignment
Assigning participants to experimental and control conditions by chance, thus minimizing preexisting differences between those assigned to the different groups
* Combats confounds
Within-subjects Research Design
Same group does multiple conditions
Between-subjects Research Design
Different groups do multiple conditions
Bias
When the data is skewed because of influence
Demand Characteristics
Cues form experimenter or context that tell participants how to behave
Reducing bias
- Inform participants how data will be used
- Single-blind study/double-blind study
Manipulated variable
A researcher controls the levels a participant is exposed to
Descriptive Research
Describes the typical
* One measured variable at a time
* Often self-report or observational
Correlational Research
How two or more variables relate to each other
Operationalizing
How was the variable measured?
Experimental Research
Can support causal claims
* Manipulating the variable and assessing the result
Random sampling
Every person in the population has an equal chance of being selected
Validity
The accuracy of a claim
Checking validity
- How well did the researchers operationalize the variable?
- Is the sample representative of the population?
- Can we rule out the most plausible alternate explanations?
External Validity
If the study is representative of the population
Internal validity
Are there no other explanations?
Construct validity
If the variables were operationalized accurately
Correlation coefficient
Indicates strength of relationship
Effect size
The magnitude of a relationship between two or more variables, written as d = (average 1) - (average 2)
Inferential Statistics
Inferring about the population based on a sample
Statistical significance testing
Estimates whether the results were likely to come from a sample in a particular population (p)
* low p: significant
* high p: insignificant
HARKing
Hypothesizing after results are known
p-hacking
Doesn’t accurately represent the data collected (extreme scores removed, etc)
Underreporting
Only reporting variables that showed strong effects
Autonomy
Must have informed consent
Beneficence
Must be worth the risks
Justice
The participants’ population must be the population that will benefit from the research
Replacement
Find alternatives for animals if possible
Refinement
Minimize animal distress
Reduction
Minimize number of animals needed
Hawthorne Effect
When participants are told what the researchers are studying, their behaviour changes