AP Experimental Methodology

1 / 19

# AP Experimental Methodology - PowerPoint PPT Presentation

AP Experimental Methodology. Introduction. As a science, psychology uses the experimental method in order to establish a cause and effect relationship between two events (i.e. variables) The experimental method is the only way to prove that there is a cause and effect relationship.

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.

## PowerPoint Slideshow about 'AP Experimental Methodology' - taariq

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

### AP Experimental Methodology

Introduction
• As a science, psychology uses the experimental method in order to establish a cause and effect relationship between two events (i.e. variables)
• The experimental method is the only way to prove that there is a cause and effect relationship.
Experimental Method
• Step 1: The researcher gathers data through non-experimental methods (e.g. case-study, observation) that appear to indicate the possible existence of a cause and effect relationship.

Example:

Step 2
• The researcher forms an hypothesis (i.e. educated guess) concerning the possible relationship. The researcher will form at least two different hypotheses:
• Experimental hypothesis: That a cause and effect relationship exists.
• Null hypothesis: That no cause and effect relationship exists
Step 3
• Determine the independent variable(s), and dependent variable(s) within the experiment.
• The independent variable is the factor that the researcher believes will have a statistically significant impact on the dependent variable (i.e. results)
• Note: All experiments must have at least one independent variable
Step 4
• Find subjects for the experiment, and split them through random selection into at least two groups: the experimental group and the control group.

Experimental group: receives the independent variable

Control Group: does not receive the independent variable

Step 4 continued
• If research is being conducted on the entire group, that is known as a population study.
• Most populations are too big/unwieldy to study, so researchers attempt to conduct on a small segment of the population. This segment is known as a sample.
• In selecting groups for the experiment, scientists hope that the groups are representative of the population.
Important note
• In a properly conducted experiment, the groups should reflect one another except for the appearance of the independent variable. The researcher wants to demonstrate that no other factor can account for the difference between groups except that the experimental group received the independent variable. Factors that account for differences between research groups outside of the impact of the independent variable are known as confounding variables.
Step 5
• Run the experiment and gather the results.
• Experiments are ran repeatedly on large numbers of subjects. The testing of an hypothesis can last years.
Step 6
• Through statistical analysis, show that the results prove your hypothesis. Proving a series of hypotheses may lead to the construction of a theory.
Issues in experimentation
• Fraud
• Ethics/”Do no harm” (e.g. Milgram, MK-Ultra, Tuskegee Syphilis Study)
• Subject pool (does it reflect the society at large)
• Placebo effect
• Double-blind experiments: Where neither the subjects nor experimenters know which group the subject is in.
Issues in Experimentation
• Bias: Scientific research is supposed to be nature. This is made difficult when humans are involved in the research, and may accidently/purposely affect the results due to prejudices/conflicts of interest. Types of bias include:
• Hindsight
• Confirmation: focus on results that affirm preexisting beliefs
• Experimenter: conscious/unconscious leading of subjects to desired results
• Social Desirability: subjects perform as society expects, not as they truly desire
Other Research Methods
• Case-study: Intense study of an individual behavioral issue (e.g. Genie, synesthesia, Multiple Personality Disorder)
• Often done with highly unusual behaviors, or for a detailed study of a more common problem (schizophrenia)
• Can be very expensive

2) Longitudinal Study: researchers follow a group of people for a period of years (in some cases, decades), to study an aspect of their behavior (Framingham Heart Study, Hiroshima, National Children’s Study)

3)Surveys: Researchers question subjects on certain issues of interest

Example: Opinion polls

4) Correlational studies: Researchers look to see if there is a connection between two or more things.

Example: The more income you make, the more likely you will vote.

Important: correlation does not equal causation

In order to prove cause/effect relationship, the experimental method must be used

Example: People with high GPAs have high ACT scores

Negative Correlation: Increase in X is related to a decrease in Y

Example: The more television a person watches, the fewer miles they walk/run.

Are You Average?
• Mean: sum of scores within a group divided by the number of scores
• Median: midpoint of the range of scores
• Mode: most frequent score in a set of scores. This average can have more than one number.
Other Statistical Definitions
• Statistical Significance: the likelihood that the difference between the experimental group and the control group is due to the independent variable, and not to chance. Measured by value p. p=.05 means that there is no more than a 5% chance that the research findings obtained were due to chance.
• Standard Deviation: the average distance of each score in a data set from the mean.