Research Designs

# Case Study

**Case****study**: brings together wide range of information on single individual or group, including interviews, observations, or test scoresBest used to study unique type of individuals

May be influences by researcher biases

Findings may not generalize

# Ethnography

**Ethnography**: participant observation of a culture or distinct social groupMix of observations, self-reports, interpretation by investigator

Results can be biased by the researcher

Findings are limited to the individuals and settings studied

# Correlation Design

**Correlational****research**: researchers gather information and look at the relationship between 2 more naturally occurring characteristics, behaviors, or ideas (ie variables)Correlation is not causation

The strength and direction of the relationship is important

**Correlation coefficient**: a number from -1 to +1 that indicates the strength and direction of the relationship between variables**Direction**: the sign +/- of the correlation coefficient indicates the direction of the relationship**Strength**: the closer the number is to +1 or -1, the more strongly related the variables**Positive****correlation**: the variables move in the same direction**Negative correlation**: the variables move in opposite directions

# Experimental Design

**Experimental design**: investigates cause and effect relationshipsManipulate variables to determine change, as well as cause and effect

Control as many aspects of the situation as possible (internal validity), in order to generalize the results (external validity)

**Independent variable**: the variable the investigator expects to cause changes in another variableWhat is being manipulated

**Dependent variable**: the variable being measuredThe outcome

# Longitudinal Design

**Longitudinal design**: gathers data from one group of individuals at several points of timeGives us the clearest picture of how the variables we’re interested in change as a function of age

One of the biggest threats is attrition

# Research Designs

# Case Study

**Case****study**: brings together wide range of information on single individual or group, including interviews, observations, or test scoresBest used to study unique type of individuals

May be influences by researcher biases

Findings may not generalize

# Ethnography

**Ethnography**: participant observation of a culture or distinct social groupMix of observations, self-reports, interpretation by investigator

Results can be biased by the researcher

Findings are limited to the individuals and settings studied

# Correlation Design

**Correlational****research**: researchers gather information and look at the relationship between 2 more naturally occurring characteristics, behaviors, or ideas (ie variables)Correlation is not causation

The strength and direction of the relationship is important

**Correlation coefficient**: a number from -1 to +1 that indicates the strength and direction of the relationship between variables**Direction**: the sign +/- of the correlation coefficient indicates the direction of the relationship**Strength**: the closer the number is to +1 or -1, the more strongly related the variables**Positive****correlation**: the variables move in the same direction**Negative correlation**: the variables move in opposite directions

# Experimental Design

**Experimental design**: investigates cause and effect relationshipsManipulate variables to determine change, as well as cause and effect

Control as many aspects of the situation as possible (internal validity), in order to generalize the results (external validity)

**Independent variable**: the variable the investigator expects to cause changes in another variableWhat is being manipulated

**Dependent variable**: the variable being measuredThe outcome

# Longitudinal Design

**Longitudinal design**: gathers data from one group of individuals at several points of timeGives us the clearest picture of how the variables we’re interested in change as a function of age

One of the biggest threats is attrition