Research in Psychology
Alicia Beauvais, Laura Ebraico, Courtney LeBlanc
The research methods most commonly used by psychologists are case studies, surveys, and experiments. Each of these methods draws upon a different aspect of research, ranging from description to correlational to manipulating scenarios in order to study the effects. Researchers typically follow the scientific method, which explains through an integrated set of principles that organizes observations and predicts behaviors of events.
Useful Terms for Researching Research
- Mean- the arithmetic average of a distribution, obtained by adding the scores and then dividing by the number of scores.
- Median- the middle score in a distribution.
- Range- the difference between the highest and lowest scores in a distribution.
- Standard Deviation- a computed measure of how much scores vary around the mean score.
- Stastical Significance- a statistical statement of how likely it is that an obtained result occurred by chance.
Observing and Describing Behavior
Psychologists begin their research by observing and describing the behaviors of different people in order to draw psychological conclusions. This can be done systematically through a specific process, or through simpler methods.
The Case Study
A case study is an in-depth examination of an individual in hopes of revealing things that are true to all people. It is one of the oldest research methods in psychology, but it does have its benefits and downfalls:
- Pros: Case studies can direct psychologists in directions for further studies and show what may happen.
- Cons: Case studies are very specific to an individual, so if the individual being studied is atypical, the resulting research gathered may be misleading, causing people to cast mistaken judgments based on the results of the study.
A survey is a method that provides a less in-depth examination of many cases. Surveys are typically used by researchers to estimate attitudes or behaviors of a much larger population.
Surveys typically utilize random sampling, which offers a sample that fairly represents a population (all the cases in a group being studied from which samples may be drawn) because each member has an equal chance of inclusion.
- Pros: The results of a survey can be more accurate than those of a case study since they are gathering information from a larger group of people.
- Cons: Surveys can be expensive to conduct, limiting their use in research. Additionally, surveys conducted without random sampling, the results may be misleading. You cannot compensate for an unrepresentative sample by adding more people to the population.
A correlation is a measure of the extent to which two factors vary together, and thus of how well either factor predicts the other. The correlation coefficient is a statistical index of the relationship between two things, thus helping experimenters figure out how closely two things vary together and how well either one predicts the other. A correlation is negative if two sets of scores relate inversely. A weak correlation, indicating little relationship, has a coefficient near zero. A correlation is positive if two sets of scores rise and fall together. Illusory correlations are random events that we see and falsely assume are related.
Scatterplots are useful to show correlation, as they are a graphed cluster of dots, each of which represents the values of two variables. The slope of the points suggests the direction of the relationship between the two variables. The amount of scatter suggests the strength of the correlation.
- Pros: Correlational studies work well with large groups of data and can be used in place of experiments with ethical restrictions.
- Cons: These studies do not specify cause and effect, nor do they prove causation. In the case of illusory correlations, people tend to assume that random events are related, which may mislead us towards drawing false conclusions.
An experiment is a research method in which an investigator manipulates one or more independent variables in order to observe the effect on some behavior or mental process. Randon assignment, or assigning participants to an experiment and control groups by chance, helps the researcher to control other relevant factors.
The experimental group is the group exposed to the treatment, or one version of the independent variable, while the control group is the group that remains unexposed to the independent variable.
- Pros: Experiments specify cause and effect.
- Cons: Experiments are not always feasible or ethical, which limits their ability. They may not generalize to all contexts.
Experiments involving people must follow a strict set of ethical guidelines laid out by the American Psychological Association. These guidelines include:
- Obtaining informed consent of potential participants, or informing them enough about the experiment so they can choose whether they wish to participate
- Protect participants from any harm and discomfort
- Maintain the participants' confidentiality - this includes in any publications of the experiment results
- Debrief participants after the experiment is over, which includes explaining the research afterwards
To prevent ethical complications, many experiment proposals at major colleges and universities are pre-screened by an ethics committee to ensure that the procedures will follow the ethical guidelines.