Have you found an interesting question through clinical care? Do you have an idea and need help understanding it’s clinical utility? Are you looking for data to support your idea? We can help with literature reviews, focus groups, knowledge generation programs, and everything else.
Once the research question is thoroughly understood, let us help you design your study. We can help you find collaborators, analyze existing data, decide what type of study to conduct, and everything else you might need.
Types of Studies
There are several different types of research study designs, all of which fall into one of two broadly defined categories: observational and experimental. Though many different variations on study design types exist, the general types are described below.
Observational (Non-Experimental) Study
In an observational study, the researcher neither manipulates nor intervenes in any way with study subjects or variables of interest. There are three primary types of observational studies:
- Cohort Study - One primary purpose of a cohort study is to examine how the incidence of an outcome of interest is related to an exposure. In a cohort study, a group of subjects is followed over a period of time to determine the occurrence of an outcome of interest. Cohort studies may either be prospective or retrospective. In a prospective cohort study, a cohort is formed before the outcome of interest has occurred and then followed from present time into the future. Conversely, in a retrospective cohort study, the outcome of interest has already occurred. Researchers will look back in time, assemble the cohort, and then follow the cohort from the past to the present time.
- Case-Control Study - The purpose of a case-control study is to determine how one or more exposure variables is related to an outcome of interest. In a case-control study, subjects with the outcome of interest (cases) and subjects without the outcome of interest (controls) are identified. The researcher will then retrospectively ascertain information related to the exposure variable for both cases and controls and measure how it is related to the outcome of interest.
- Cross-Sectional Study - The purpose of a cross-sectional study is to examine the relationship between certain explanatory variables and an outcome of interest at a single point in time. A cross-sectional study is considered to be a “snapshot” of a cohort, since information regarding explanatory variables and outcomes of interest are recorded for a singular point in time rather that across time. As such, cross-sectional studies can only measure prevalence (not incidence) of certain factors of interest.
In an experimental study, the researcher can control the study setting by manipulating subjects and variables of interest. A randomized trial is an experimental study in which subjects are randomly assigned to one or more intervention groups. Through the process of randomization, subjects have an equal chance of assignment to an intervention group, and similar baseline characteristics between treatment and control groups can be achieved, thus minimizing selection bias and confounding, respectively.
There are several different variations of study designs outside of the classical two-study parallel design (patients are randomized to either one of two treatment groups). These include cluster, cross-over, factorial, and other designs. Clinical trials can be categorized as explanatory or pragmatic. An explanatory trial is generally tightly controlled and aims at isolating a treatment effect under the controlled conditions (higher internal validity). A pragmatic trial will alternatively seek to understand how a treatment works in "real world” conditions (higher external validity).
If you’ve got a study in mind but need help making it happen, we’re here for you! We’ll help you find funding sources, getting IRB certification, understanding standard operating procedures, finding stakeholders—you name it!
Is your study done and you have a mountain of data to sort through? We love that! We can help you find tools for analysis, get in touch with statisticians at The U of U and the like.
So now that you’ve got these amazing findings, what next? We’ll help you reach out to conferences, provide guidelines for writing to a specific audience, and just help you get the word out about your awesome work!