Johns Hopkins Nursing Evidence-Based Practice Thrid Edition: Model and Guidelines

6 Evidence Appraisal: Research 109

The investigators seek to provide the who, what, where, when, and how of par-
ticular persons, places, or things. An attempt is made to describe the answers to
these questions in precisely measured terms. Statistical analysis is generally lim-
ited to frequencies and averages. Common types of descriptive designs include
univariate descriptive, descriptive comparative, descriptive correlational, and epi-
demiologic descriptive studies (prevalence and incidence). Table 6.3 on page 112
outlines the features of descriptive designs and purpose.

Univariate descriptive studies, which often use exploratory or survey designs, aim
to describe the frequency of a behavior or an occurrence. Univariate descriptive
studies are “not necessarily focused on only one variable ...there are multiple
variables ...but the primary purpose is to describe the status of each and not
to relate them to one another” (Polit & Beck, 2017). Exploratory and survey
designs are common in nursing and healthcare. When little knowledge about
the phenomenon of interest exists, these designs offer the greatest degree of flex-
ibility. Though new information is learned, the direction of the exploration may
change. With exploratory designs, the investigator does not know enough about
a phenomenon to identify variables of interest completely. Variables are observed
as they happen; there is no researcher control. When investigators know enough
about a particular phenomenon and can identify specific variables of interest, a
descriptive survey design more fully describes the phenomenon. Questionnaire
(survey) or interview techniques assess the variables of interest.

Example: Nonexperimental Descriptive Survey Design

Bourgault et al. (2014) conducted a national online survey of critical-care nurses

to examine factors that influence the adoption of the American Association of

Critical-Care Nurses practice alert on the verification of feeding tube placement

and the adoption of four clinical practices recommended in the guideline. There

was no intervention, researcher control, or randomization; the intent was to

describe existing practices.

Descriptive comparative designs look at and describe differences in variables be-
tween or among two or more groups. No attempt is made to determine causality.
Generally, descriptive statistics, such as frequency distributions and measures of