Anecdotes=examining a few cases with no systematic comparison

Available Data=data gathered from previous studies

Variable of interest: Characteristic changing from unit to unit

Examples: Student opinion, intelligence level, heart rate, gas mileage

• How will I measure the variable?

Instruments:

• Who should I measure?

Population: The collection of objects for which you want information

All 93 million households

Census: Obtain measurements for every unit in the population

Drawbacks:

Sample: A part or subset of the population

Examples:

Key Idea: Use sample to gain information about entire population.

Units: Individual members of the population

Sampling Frame: A list of all units in the population

Example A newspaper article about an opinion poll says that"43% of Americans approve of the president's overall job performance". Toward the end of the article, you read: "The poll is based on telephone interviews with 1210 adults from around the United States, excluding Alaska and Hawaii.

Variable= Population=

• How should I conduct the study?

Observational Study: Passive, record the data without interfering with the subjects (intervention occurs naturally)

Survey: Trying to assess the subjects' opinions

Experiment: Active, you change one variable controlling the others, and observe what happens because of the change (impose a treatment)

Example Lee Salk knew that hypothalamus was largely responsible for emotions. Still, our society seems to say the heart is. Thus, he is interested in the heart's role in our emotions.

Observational Study -

Survey -

Experiment -

Terminology:

Explanatory Variable/Factor (EV)- The variable we actively change

Levels = Possible settings of the factor

Treatment = Specific experimental condition

Response Variable (RV) =The response that we observe

Extraneous Variable =Other variables that might have an effect on the response

Example In 1940, to study the effect of propaganda on attitude of American students toward German government, students read German propaganda for several months and were then retested to see if their attitudes had changed.

Type of study?

Explanatory variable =

Response variable =

What conclusions can be drawn?

Extraneous variable=Germany conquered France during the study

Confounding= unable to separate the effects of the two variable

Comparative Experiment - Have at least two groups to compare e.g., treatment group (propaganda) and a control group (no propaganda). Sketch this experimental design. Why is this better? Always?