Descriptive Research Strategy

I.                 Descriptive Research Strategy

Measuring a variable or set of variables as they exist naturally

Goal: Describe a single variable or obtain separate descriptions for each variable

Useful as preliminary research

Describes a phenomenon. Does NOT attempt to explain why the behavior occurs or the underlying causes.

Three descriptive research designs are covered in this chapter:

1) Observational research

2) Survey research

3) Case study research


II. Observational Research Techniques

Researcher observes and systematically records the behavior of individuals in order to describe the behavior 

Behavioral observation is one technique or modality for measuring variables. As a modality of measurement, behavioral observation can be used with a variety of research strategies (e.g., correlational, experimental). When studies use behavioral observation simply for descriptive purposes, this is the observational research design.

Two main measurement problems in using behavioral observation:
1) Goal is to measure natural behavior, so observer must be careful to not disrupt the naturally occurring behavior. Can conceal the observer or habituate participants to the observer's presence.
2) Measurements must be based, to some extent, on subjective judgment of the observer, we must ask if the measurements are reliable. We must prepare list of behavior categories and specify exactly which behaviors qualify as instances of each category. This provides clear operational definitions. Then must establish inter-rater reliability.

Observational designs differ with respect to

1)  Degree to which an observer intervenes

       2)  Way in which that behavior is recorded 


        A.  Naturalistic observation (nonparticipant observation)

Observation without intervention

Researcher observes and records behavior in a natural setting


**B. & C. below are Observation with intervention

Why intervene?        

         B.  Participant observation

         C.  Structured observation  (contrived observation)   


Problems in Conducting Observational Research

        Demand characteristics--cues that suggest the purpose/hypothesis of the study and may influence the participant to respond in a certain way

Reactivity --when participants modify their natural behavior because they are participating in research or because they know they are being observed and measured

        Observer/experimenter bias 

                1. expectancy effects

                2.  controlling observer bias (single-blind vs. double-blind research)    


Content Analysis and Archival Research

Content analysis uses techniques of behavioral observation

Measures the occurrence of specific events in literature, movies, television programs, or similar media presenting replicas of behaviors

Archival research looks at historical records (archives)

Measures behaviors or events that occurred in the past
Measurement follows the same rules as used for behavioral observation
Establishes behavioral categories
Uses the frequency method, the duration method, or the interval method for obtaining numerical scores
Employs multiple observers for at least part of the measurement process to obtain a measure of inter-rater reliability


III. Survey Research Design

A research study that uses a survey to obtain a description of a particular group of individuals

More on conducting surveys


IV. Case Study Design

An in-depth study and detailed description of a single individual (or very small group)...may involve an intervention or treatment administered by the researcher. When a case study does not include any treatment or intervention, it often is called a case history.

V.  Research Strategies