Skip to Main Content

CHAPTER OBJECTIVES

  • Discuss commonly used other observational study designs

  • Describe and interpret studies using other observational study designs

  • Examine the potential strengths and limitations of other observational designs

  • Understand strategies to strengthen other observational study designs

KEY TERMINOLOGY

  • Convenience sample

  • Cross-sectional studies

  • Ecological fallacy

  • Ecological study

  • Generalizability

  • Nonequivalent comparison group

  • Pre and postobservational designs

  • Purposive sample

  • Random sample

  • Sampling

  • Stratified random sampling

  • Time-series design

INTRODUCTION

Previous chapters provided compelling evidence in support of the advantages of randomized-controlled trials (RCTs) and cohort and case-control study designs to evaluate causal relationships between an intervention or an exposure and an outcome. However, often times it is neither practical, nor useful for researchers to conduct randomized trials or epidemiologic studies. In such instances, other observational study designs may be considered. These study designs, although useful for their ­specific purpose, are less formal than traditional cohort or case-control studies and often lack important design features that may threaten internal validity of the study. In this chapter, a number of unique observational study designs are described including cross-sectional studies, pre and postobservational studies, ecological studies, and time-series evaluations.

CROSS-SECTIONAL STUDIES

As the name implies, cross-sectional studies examine population characteristics at a cross-section (one point) in time. These studies are most often used descriptively to capture information about a population such as disease prevalence but may also be used to examine associations between an independent (exposure) and a dependent (outcome) variable. As will become clear, causality between an exposure and outcome cannot be established from a cross-sectional study.

Study Design

Although the nomenclature “cross-sectional study” may sound complicated, it is one of the more common types of studies used in research. Have you ever been asked by someone to answer to a questionnaire about who you are or maybe your preferences, experiences, or beliefs on certain topics? This may have been over the telephone, as part of a government census, through the mail, or maybe after being approached by someone in person to assess your experiences while participating in an activity. If you answered yes, then you have actually participated in a type of cross-sectional study called a survey.

Surveys are standardized questionnaire used to describe a population at a given point in time. These studies are generally conducted to characterize a population and may be useful to pharmacists in understanding the populations they serve. Consider an example of a community pharmacy owner deciding whether to purchase a bone densitometer for their pharmacy. Before committing resources to the purchase of this densitometer, the owner may be interested in the number of patients who might use this service, the amount patients would be willing to pay for this service, and the underlying risk of osteoporosis in their patient population. To better understand the need for this service, the owner may ...

Pop-up div Successfully Displayed

This div only appears when the trigger link is hovered over. Otherwise it is hidden from view.