Chapter 2: Methods
- Overview
- Hindsight Bias
- Upon hearing research findings, the tendency to believe that you knew it all along
- Applied Research
- Has clear, practical applications
- Basic Research
- Explores questions that are of interest to psychologists
- Not intended to have immediate real world applications
- Terminology
- Hypothesis
- Expresses a relationship between two variables
- Variables
- The dependent variable depends on the independent variable
- Things that can vary among the participants in the research
- Theory
- Aims to explain some phenomenon
- Allows researchers to generate testable hypotheses with the hope of collecting data that support the theory
- Operational Definitions
- Explanations of how variables will be measured
- Validity and Reliability
- Research is valid when:
- it measures what the researcher set out to measure
- it is accurate
- Research is reliable when:
- it can be replicated
- it is consistent
- Participants (Subjects)
- The individuals on which the research will be conducted
- Sampling
- The process by which participants are selected
- Sample
- The group of participants
- Population
- Includes anyone or anything that could possibly be selected in the sample
- Random Selection
- Every member of the population has an equal chance of being selected
- Increases the likelihood of a representative sample
- Allows researchers to generalize about their results
- Stratified Sampling
- Allows a researcher to ensure that the sample represents the population on some criteria (ex. race)
- Sample size uses proportions equal to that of the population
- Experimental Method
- Laboratory Experiments
- Conducted in a lab
- Advantage- highly controlled
- Field Experiments
- Conducted out in the world
- Advantage- more realistic
- Experiment
- Only way to show a cause-effect relationship
- Preferred research method
- Confounding Variables
- Any difference between the experimental and control conditions that could affect the dependent variable
- (other than the independent variable)
- Assignment
- The process by which participants are put into the experimental or control group
- Random Assignment
- Each participant has an equal chance of being placed into any group
- Limits the effect of participant-relevant confounding principles
- Group Matching
- Divide the sample into groups based on some criterion and assign half of each group to each condition
- ex: gender
- Situation-Relevant Confounding Variable
- Ex: time of day, weather, presence of others
- Each condition has to be equivalent with the exception of the independent variable
- Experimenter Bias
- A situation-relevant confounding variable
- The unconscious tendency for research members to treat members of the experimental and control groups differently to increase the chance of confirming the hypothesis
- Double-Blind Procedure
- Neither the participants nor the researcher are able to affect the outcome of the research
- Eliminates experimenter and subject bias
- Single Blind
- Only the subjects don’t know to which group they’ve been assigned
- Minimizes demand characteristics and participant bias
- Demand characteristics
- cues about the purpose of a study that affect the participants’ responses
- Response/participant bias
- the tendency for subjects to behave in certain ways
- social desirability
- the tendency to try to give politically correct answers
- Experimental Group
- Gets the treatment operationalized in the independent variable
- Control Group
- Gets none of the independent variable
- Without it, knowing the effects of the experimental treatment is impossible
- Hawthorne Effect
- Selecting a group of people on whom to experiment affects the performance of that group, regardless of what is done to them
- Placebo Effect
- Controlled by the placebo method
- giving the control group an inert drug
- Counterbalancing
- Using participants as their own control group
- To eliminate order effects, have half do one order, the other half the other, then switch
- Correlational Method
- Correlations
- Express a relationship between two variables
- Positive
- the presence of one predicts the presence of the other
- Negative
- the presence of one predicts the absence of the other
- Do not imply causation
- Ex-Post Facto Study
- Cause and effect cannot be determined
- The assignment of the independent variable is predetermined
- Controls all other aspects of the research process
- Survey Method
- Asking people to fill out surveys
- Investigates relationships, but not causation
- No independent or dependent variables
- Participant-relevant confounding variables can’t be controlled for
- Controlling for situation-relevant confounding variables
- bring all participants to one place at one time to complete the survey
- Response rate
- people who send the survey back
- Naturalistic Observation
- Naturalistic Observation
- Observe participants in their natural habitats without interacting with them
- Control is sacrificed
- Goal
- to get a realistic and rich picture of the participants’ behavior
- Disparity with Field Experiments
- In field experiments:
- manipulate independent variable
- attempt to eliminate all confounding variables
- Case Studies
- Case Study
- Used to get a full, detailed picture of one participant or a small group of participants
- Findings can’t be generalized to a larger population
- Often used to research clinical disorders
- Descriptive Statistics
- Frequency Distributions
- Can easily be turned into:
- frequency polygons
- histograms
- Y-axis represents frequency
- X-axis represents what you’re graphing
- Central Tendency
- Mean, median, mode
- Mean most common, but most affected by outliers/extreme scores
- Outliers Skew Distributions
- Positively skewed
- has high outliers
- contains more low scores
- the mean is higher than the median
- Negatively skewed
- low outliers
- the mean is less than the median
- Measures of Variability
- Depict the diversity of a distribution
- Range
- highest score minus lowest score
- Variance and standard deviation
- relate the average distance of any score in the distribution from the mean
- the higher they are, the more spread out the distribution
- the square root of the variance is the standard deviation
- Z-scores
- measure the distance of a score from the mean in units of standard deviation
- scores above the mean have a positive z-score
- 600 on SAT: z-score of +1
- Normal curve
- one standard deviation from the mean- 68% of scores
- two standard deviations- 95%
- three standard deviations- 99.7%
- Percentiles
- indicate the distance of a score from zero
- 50th percentile = z-score of 0
- Correlations
- Correlation Coefficient
- Range from -1 to +1
- -1 = perfect negative correlation
- +1 = perfect positive correlation
- 0 = weakest possible correlation
- Scatter Plot
- Correlations can be graphed using a scatter plot
- Line of best fit (regression line)
- drawn through it
- Inferential Statistics
- Purpose
- To determine whether findings can be applied to the larger population from which the sample was selected
- Sampling Error
- The extent to which the sample differs from the population
- Tests
- ANOVAs, MANOVAs, t-tests
- Consider the magnitude of difference and size of sample
- Yield a p-value
- the smaller, the more significant the results
- p = .05 is the cut off for statistically significant results
- 5% chance that results occurred by chance
- APA Ethical Guidelines
- Institutional Review Board (IRB)
- Any type of academic research must first propose the study to this ethics board
- Animal Research: Requirements for Psychological Studies
- They must have a clear scientific purpose
- research must answer a specific and important scientific question
- animals chosen must be best suited to answer it
- Must care for and house animals in a humane way
- Must acquire animal subjects legally
- purchased from accredited companies
- trapped in a humane way
- Must design experimental procedures that employ the least amount of suffering feasible
- Human Research
- Coercion
- participation must be voluntary
- Informed consent
- participants must know that they are involved in research and give consent
- no extreme deception about the nature of the study
- Anonymity/confidentiality
- identity and actions of participants can’t be revealed
- can’t identify participants as the source of any of the data
- Risk
- participants can’t be placed at significant mental/physical risk
- Debriefing procedures
- participants must be told the purpose of the study and provided with ways to contact the researchers about study results
You just finished Chapter 2: Methods. Nice work!
Previous ChapterNext Chapter
Tip: Use ← → keys to navigate!
How to cite this note (MLA)
Aboukhadijeh, Feross. "Chapter 2: Methods" StudyNotes.org. Study Notes, LLC., 12 Oct. 2013. Web. 24 Apr. 2025. <https://www.apstudynotes.org/psychology/outlines/chapter-2-methods/>.