6 Evidence Appraisal: Research 113
Time-Dimensional Designs
Time-dimensional designs answer questions such as, “Were the data for the de-
pendent and independent variables collected at a single point in time, or across
a certain period, or did data already exist?” An EBP team should understand the
concepts of retrospective, prospective, and longitudinal with respect to examining
a phenomenon over time. In retrospective studies, the investigator looks at pro-
posed causes, and the effects that have already happened, to learn from the past.
In contrast, prospective studies examine causes that may have occurred in the
past and then look forward in time to observe the presumed effects. Longitudinal
studies look at changes in the same subjects over a long period. The basic ques-
tion asked in longitudinal (present) and prospective (future) research is, “What
are the differences in a variable or variables over time, going from the present to
the future?” The basic question in retrospective studies is, “What differences in
a variable or variables existed in the past that may explain present differences in
these variables?”
Three common types of descriptive or observational studies that have a time
component are case-control, cohort, and cross-sectional. Because unfamiliar
terminology can divert the reviewer’s attention from review of a study, an un-
derstanding of these terms should minimize confusion. Table 6.4 outlines time-
dimensional designs and purposes.
Case-control studies, which are used in epidemiologic research, examine possible
relationships between exposure and disease occurrence. “The hallmark of the
case control study is that it begins with people with the disease (cases) and com-
pares them to people without the disease (controls)” (Gordis, 2009, p. 179). The
basic question asked in case-control studies is, “Is there a relationship between
being exposed to particular phenomena and contracting a specific disease?”
Case-control studies compare the proportion of cases that have a particular con-
dition or outcome with the proportion of cases that do not have the condition
or outcome (Lu, 2009). This proportion is expressed as an odds ratio, which is a
way of comparing whether the probability of a certain condition or outcome oc-
curring is the same as the probability of the condition or outcome not occurring.
An illustration of a case-control study (see Figure 6.2) considers body mass index
(BMI) as a determinant of obesity in the population of interest.
