Research Methods in Social Psychology
∙ The scientific method, a repeating cycle, is used by social psychologists:
-A theory explains many of the relationships between variables within a specific domain of inquiry; they allow predictions to be made that can then be tested using the scientific method. Don't forget about the age old question of How can you tell if a graph is a polynomial function?
-A theory can’t be proven. However, a good theory will lead to a good, specific hypothesis that will lead to a successful experiment.
-Experiments are used by social psychologists to investigate how manipulation of one factor causes change in another factor.
-They are controlled by the researcher.
-Most times experiments are randomly assigned. Random assignment evens the playing field, allowing chance to determine which group will be the control and which group will receive the treatment.
-A Quasi-experiment lacks the element of random assignment to the control and treatment groups.
∙ Lab Experiments:
-Take place in a lab
-High level control
-Low in experimental realism: the participants in the experiment forget that they are part of an experiment due to getting caught up in the procedures.
Don't forget about the age old question of What is the difference between objective and subjective factors?
-Low in mundane realism: the setting of the lab does not resemble the real world. ∙ Field Experiments: Don't forget about the age old question of What is basic arithmetic math?
-Take place in the real world
-Low level of control due to nature and factors researchers can’t control
-High in experimental realism: the participants sometimes forget they are part of an experiment, which means their behavior is not influenced as much by the fact that they are in it.
-High in mundane realism: the experiment occurs in a natural setting, which IS the real world.
*It is best to use both lab and field experiments, as it replicates over findings and allows the researcher to see if the findings from one context hold in another.
-External validity: this is high if the findings from the experiment will likely generalize to other people and other settings; in determining external validity, experimental realism is more important than mundane realism because behavior is not influenced by knowledge of the experiment…people behave naturally.
-Internal validity: confidence that the independent variable caused change in the dependent variable; internal validity is increased by stimulus sampling, maximizing experimental control, and eliminating or controlling confounding (unwanted) variables.
-Independent variable: constant
-Dependent variable: dependent upon the independent variable
*For example, let’s say an experiment is taking place to determine what mood high school students are typically in during every hour they are in school. In this case the independent variable is each hour, and the dependent variable is the student’s mood because it’s dependent upon the hour of the day. If you want to learn more check out How do you find the maximum and minimum of a quadratic function?
-A correlation is a relationship between two variables. Studying correlations means determining whether an increase or decrease in one variable corresponds to an increase or decrease in the other variable.
-Range from 0.0 to 1.0, 0.0 being the weakest correlation and 1.0 being the strongest correlation We also discuss several other topics like What is the difference between a behavioral and physical adaptation?
-Can be positive or negative
∙ Survey Research:
-This type of research involves asking questions of respondents and analyzing the responses given.
-Factors than can cause survey research to fail: random sampling not being used, who responded versus who was given the survey; the survey not being reliable or valid
*Reliability: gives consistent results
*Validity: measures what research purports to measure; the 3 different types of validity are convergent validity, divergent validity, and face validity… Convergent validity tests that constructs that are expected to be related are, in fact related; divergent validity tests that constructs that should have no relationship do, in fact, not have any relationship; last, face validity tests the degree to which a procedure appears effective in terms of its stated aims. If you want to learn more check out What other psychological problems do people with anorexia often display?
∙ Longitudinal Research:
-Survey research that uses multiple survey time periods
-This type of research is useful in studying change in psychological constructs over time. ∙ Naturalistic Observation:
-This type of research involves observing and recording behavior from animals in the wild to self-seating patterns in a multiracial school lunch room; observing and recording these behaviors constitute naturalistic observation.
∙ Descriptive Statistics:
-Summarizes a given data set, which can either be a representation of the entire population or a sample; the measures used to describe the data set are measures of central tendency and measures of dispersion.
-Measures of central tendency: mean, median, mode
-Measures of dispersion: range, variance, standard deviation
∙ Inferential Statistics:
-Makes inferences or estimates about differences or relationships
-Some examples of these tests: Analysis of Variance (ANOVA), t-test, correlation, regression, and structural equation modeling