Study Designs
- Experimental Design
- Correlation Design
- Quasi-Experimental
- Observational
Correlational Design
Research procedure in which subjects scores on two variables are measured without manipulation of either variable, to determine whether there is a relationship. It cannot determine a cause-and-effect relationship.
Experimental Design
Research procedure in which the independent variable is activelty changed or manipulated, the scores on another variable (dependent variable) are measured, and all other variables are held constant to determine whether there is relationship. It can also determine a cause-and-effect relationship between two variables.
Quasi-Experimental
Research procedure in which the researcher does not directly manipulate the independent variable and/or the researcher does not randomly assign subjects to treatment conditions. It examines differences between preexisting groups of subjects or differences between preexisting conditions (aka subjects variables). The variable that is used to differentiate the groups is called the quasi-independent varaible, and the score obtained for each individual is the dependent variable.
Observational Designs
Research method where a researcher observes and records data about individuals or phenonmenon without interferring or manipulating any variables. Within this there are cohort design, case control, cross-sectional (which can also include surveys within this design)
Groups within Experimental Research
- Experimental or Treatment Group
- Control Group
Experimental or Treatment Group
Group that receives the experimental treatment, manipulation, or is different from the control group on the variable under the study treatment.
Control Group
Group is used to produce comparisons as compared to the experimental ot treatment group.
Pretest
Measurements given to participants at the onset of the study, prior to their being given a treatment (or placebo or nontreatment if in the placebo group)
Post-test
Measurement given to participants at the end of the study, after the treatment has been administered; compared with the pre-test performance to determine change on a particular variable.
Design 1
Experimental Group: Pretest—>treatment—> Posttest
Control Group: Prestest—>treatment—>Posttest
Design 2
Experimental Group: Pretest—>treatment—> Posttest
Solomon Four Group Design
Helps rule out human memory component
Solomon Four Group Design Advantages
- Control common threats to internal validity
- Controls for Practice or Pretest effects
Solomon Four Groups Design Disadvantages
- Needs more subjects because they are more groups
- More costly
Four types of valilidity
- Measurement Validity
- Internal Validity
- Statistical Conclusion Validity
- External Validity
Internal Validity
Degree to which the experiement is methodologically sound and free of confounding variables so that casual conclusions can be warranted (e.g., can a casual relationship be observed between the independent and dependent variable?) CASUAL
External Validity
Degree to which research findings can be generalized beyond the specific context of the experiment being conducted. (Can the study be generalized and used in different populations or contexts?) GENERALIZABLE
Statistical Conclusion Validity
Extent to which researchers uses statistics properly to draw correct conclusions.
Threats to Internal Validity
- History Threat
- Maturation Threat
- Testing Threat
- Intrumentation Threat
- Mortatility or Attrition Threat
- Statisitical Regression to the mean Threat
History Threat
External event that occurs the same time as the study and influences the dependent variable.
Maturation Threat
Natural changes that occur as a result of the normal passage of time such as aging
Testing Threat
When you take a pretest leading you to become aware of what to look out for later future test (posttest)
Instrumentation Threat
Issue when the instrument changes from pre and posttest that can make it where you are not comparing apples but rather potentially apples to oranges.
