field research—applies to a variety of research methods from high to low contstraint

naturalistic observation—direct observation of events as they occur in natural settings

archival research—studying information from already existing records made in natural settings

surveys—asking direct questions of persons in natural settings

case study—making extensive observations of a single group or a person

program evaluation—conducting evaluations of applied procedures in natural settings

field experiments—conducting experiments in natural settings where causal inferences are sought

low constraint research—investigator imposes few, if any, controls or constraints on subject’s behavior (constraints are on the researcher)

--classic example—Charles Darwin—5 years aboard HMS Beagle

gathered specimens and compiled descriptive data to develop theory of evolution

--Jane Goodall’s study of chimpanzees in their natural habitat Tanzania

--Dian Fossey—studied mountain gorilla in Africa

--anthropologists who live among people of different cultures

--Levine’s (1982) study of Love Canal

--is naturalistic observation but with some mild constraints imposed on the procedures

--not typically carried out in natural environments, setting usually selected by researcher

--typically focused on individuals

--typically looks at limited classes of behavior rather than the total context and natural flow of behavior

--example, work of Sigmund Freud

--example, work of Jean Piaget on the cognitive development of children

--when question concerns natural flow of behavior in natural settings

--at the beginning stages of research in a new area (generate ideas for higher constraint research)

--to familiarize researchers with subjects or settings that are new to them (though not a new research area)

--demonstrate a new research for treatment technique (question is whether technique is feasible)

--test the generalizability of the theories developed or refined on the basis of laboratory techniques

--new, descriptive information

--negate a general proposition (but cannot establish one)

--causal inferences cannot be made but can obtain useful information about relations between variables (contingency relations—based on probability)

--focused on identifying contingencies (i.e., what variables seem to go together)

--often general or vague, and become more focused as research progresses

--planning is less formal and plans are much more fluid

--data is gathered using either unobtrusive observation or participant observation

--if using participant observation, can manipulate own behavior to create situations in which to test hypotheses

--unobtrusive measures need not be visual (e.g., museum tiles, trip photography)

--sampling of subjects may not be under researcher’s control (cannot guarantee representativeness of sample)

--sampling of situations may be limited (should try to get as many as possible)

Evaluating and Interpreting Data

-data can be codes

-can run frequencies, or limited statistical analysis

--poor representativeness

--cannot generalize beyond those studied

--difficult to replicate unless procedures have been very explicit

--cannot draw causal inferences—may lead to fallacious ex post facto reasoning

--potential for experimenter reactivity or experimenter bias is higher

Survey Research

--is not single research design—discussed here because data collected in natural environments

--major goal is to learn about ideas, knowledge, feelings, opinions, attitudes, beliefs, values, and self-reported behavior

Steps

1. Determine what area of information is to be sought
2. Define the population to be studied
3. Decide how the survey is to be administered
4. Construct the first draft of the survey instrument; edit and refine the draft
5. Pretest it with a subsample; refine it further
6. Develop a sampling frame and draw a representative sample
7. Administer the form of the instrument to the sample
8. Analyze, interpret, and communicate the results

Form of the Survey Instrument

3 types—mail, telephone, interview

instrument should have clear focus

**survey research is not well suited to early exploratory research because researcher must have clear focus

concepts of population/sample

sampling considerations

sampling procedures

nonprobability sampling—research objects/participants are not selected randomly

probability sampling—each population element has some known, specifiable probability of being included in the sample

--simple random sampling—every member of the identified population has an equal chance of being selected

--sampling frame—list of potential participants (ideally, should equal the target population, in practice, seldom does)

--stratified random sample—used to ensure that subgroups within a population are adequately represented, samples drawn proportionately from each of the subgroups

sampling size and confidence intervals—[make distinction clear between power of statistical test and confidence interval of a sample]

cross-sectional survey—one time administration of a survey to a sample (point-in-time)

repeated surveys of independent respondents over time is still cross-sectional

longitudinal (panel design)—same group or panel of subjects is surveyed successively at different times