Conducting Research in Psychology. Research designs

Experimental research

A research method where the researcher manipulates one variable and measures its effect on another, allowing causal conclusions. The researcher keeps everything under control (constant) and manipulates, in its simplest form, just that variable in which she is interested in knowing what effect it may have (based on hypothesis).

Dependent variable

The variable the researcher measures but does not manipulate in an experiment. Not manipulated.

Independent variable

The variable the researcher manipulates and controls in an experiment. Manipulated.

Experimental condition

Group that receives the manipulation.

Control condition

Comparison group that does not receive it (or receives baseline/placebo condition).

Random assignment

Assigning participants to receive different conditions of an experiment by chance.

Placebo condition

Control condition in an experiment where participants receive a treatment that has no real active effect, but is designed to look like the real treatment, so that expectations are controlled.

Placebo effect

When people improve or change because they believe they are receiving a treatment, even if it has no real effect. A change in a participant’s behavior, feelings, or outcomes caused by their belief that they are receiving a treatment, even though the treatment itself has no real active ingredient.

 

 

Confounding variable

:= Confounds are extra variables that interfere with the ability to make clear causal conclusions in an experiment (i.e., they threaten internal validity).

Confounds

:  Factors that undermine the ability to draw causal inferences from an experiment.

Participant demand

: When participants behave in a way that they think the experimenter wants them to behave.

Researcher bias

is when a researcher unintentionally influences the outcome of a study because their expectations affect how they behave toward participants or how they interpret results.

Expectancy bias

Expectancy bias is a specific type of researcher bias where a researcher’s expectations about how participants should perform actually change the participants’ performance.

Double-blind procedure

: A procedure where neither participants nor researchers know which condition participants are in, preventing bias and expectancy effects.

The Pygmalion effect

is the phenomenon where higher expectations lead to improved performance.

Correlation

:  Measures the association between two variables, or how they go together./ A statistical measure of how two variables are related or go together, without implying causation.

Correlational designs

: A research method where researchers observe variables without manipulating them, identifying relationships but not cause-and-effect

Qualitative designs

=. Research methods that use non-numerical data such as observations, interviews, case studies, and narratives to understand meaning and experience.

Naturalistic Observation

A research method in which researchers observe people or animals in their natural environment without interfering or manipulating the situation.

Cognitive dissonance

predicts people will change behavior to reduce discomfort.

Prosopagnosia

is a condition in which a person has difficulty recognizing faces, even though their vision is otherwise normal.

Quasi-experimental design

: An experiment that does not require random assignment to conditions.

     Longitudinal designs

=. Research designs that track the same individuals over time.

  Longitudinal study:

A study that follows the same group of individuals over time.

Selective drop-out

occurs when some participants leave a study, and the people who leave are systematically different from those who stay.

This is especially important in longitudinal studies, where researchers follow the same people over time.

 Surveys

=.  A method of collecting data using questionnaires to gather information from many people quickly and cheaply. a technique mainly used in descriptive and correlational research

• but can also be experimental

• typically involves seeking people’s responses to a prepared set of

verbal or written items

Social desirability

is the tendency for people to give answers or behave in ways that make them look good, acceptable, or socially approved, rather than being completely honest.

A response-order effect

occurs when a participant's answer to a question is influenced by the order in which questions are asked.