X Y Z
Arm—Group of participants that are given the same treatment. Many controlled trials have a treatment arm (receive experimental treatment) and a control arm (receive current standard treatment or
Association—A link between two factors such that if one changes the other changes in a predictable way. An association does not necessarily mean that one factor causes the other.
A positive association as one factor increases the other will increase.A negative association one factor increases as the other decreases. Attrittion
(loss to follow up, dropouts)—The number of participants that leave a study. Some loss is expected in any study but too much loss can decrease the reliability of the results.
Baseline Characteristics—Traits of the participants that are important to the study. They may include age, gender, race, disease severity, or clinical tests. They may be used to help determine changes that occur during the study or to help find the similarities and differences in study groups.
Bias—Actions that are accidentally introduced to the study process that can change the outcome of a study. The error can occur at any time in the study such as during the selection of patients, administration of treatment, collection of data, and interpretation of results.
(masking, concealment of allocation)—Certain aspects of the study, like who receives treatment and who receives placebo, are kept secret from the participants and/or study administrators. This helps to decrease the chance of
entering the process. When both the participant and the study administrators are blinded it is called double-blinding.
Case-Control Study—In this type of
there is no intervention on the part of the researchers. People that already have the health issue of interest are compared to a group of people without the health issue. Researchers review the histories of both groups to search for factors that may be associated with the development of the health issue. This type of study cannot prove a cause of a disease but may highlight important associations (Example: The link between smoking and lung cancer was first suggested by a case control study).
Case Series—A group of participants receive an intervention and the results are observed. There is no
so the results can not be considered evidence. It may provide important information for developing other more rigorous studies.
Causal Effect—A change in one factor causes a change in the second factor. It clearly demonstrates that changes are due to cause and effect. This type of finding can only be shown by specific studies such as some
randomized controlled studies. Causality cannot be confirmed through
Chance—Study conclusion that happens by accident not because of the intervention or because of
bias. Statistical tests are used to evaluate the possibility of a conclusion happening by chance.
Clinical Trial—Research designed to evaluate the safety and efficacy of a drug or treatment. Drug research is split into 4 phases:
Phase I is the first phase in testing a new drug in humans. This phase is done to test the safety of the drug and to confirm that the drug acts as expected. This first step is usually done on a small group of healthy volunteers without a
Phase II the second step in testing. It is done to test the drug’s ability to do what it is supposed to do. A phase II study often involves several hundred people that have the heath issue for which the drug is being developed. This part of the research may be up to two years or longer.
Randomized controlled studies
may be used here.
In Phase III, the drug is tested in large numbers of patients (sometimes hundreds of thousands). The effect of the new drug is compared to the current standard treatment. These comparisons are carried out through
randomized controlled studies.
Phase IV studies follow the drug after its release. This surveillance phase monitors the performance of the drug to identify its ability to address the problem and discover any previously unidentified problems, such as adverse effects. Cohort Study—An
that looks for outcomes from a particular exposure. A study group that has been exposed is compared to a similar control group that is not exposed. The researchers do not introduce the exposure, it happens as a result of natural circumstances or personal choice (Ex. smoking). Groups are followed over time and outcomes are compared. (Ex. Overtime people that smoke have higher risk of emphysema.)
Co-morbidity—One or more health issues are present in addition to the issue being studied. The results of the studied treatment may be affected by the other health issues. This could decrease or increase the effectiveness of the treatment and decrease the reliability of the study.
(Control Group)—Group of participants that are compared to the treatment group. These participants receive the placebo or current standard treatment to provide a comparison to the treatment being studied.
Confounder—A factor that is related to one or more of the variables being studied. Confounders can increase or decrease the apparent effectiveness of a treatment.
is designed to create equal numbers of confounding factors in all groups. This will eliminate the effect of the confounder on the study results. Non-randomized groups such as observational studies have a risk of confounders. For example, if people in the experimental group of a
are younger than those in the control group, it will be difficult to decide whether a lower risk of death in one group is due to the intervention or the difference in ages. Age is then said to be a confounder, or a confounding variable.
Controlled Clinical Trial—A research study that uses a
comparison group. The comparison or control group receives a placebo or current standard treatment. At the end of the study, results from the control group are compared to the treatment group to determine if there is a difference in outcomes. Outcomes generally include both harms and benefits of the new treatment (ie,
Randomized controlled trial).
Cross-Over Design—In this type of study there is only one group of participants. They act as both the control and the treatment group. The group starts the study with one type of treatment and then “cross over” to a different intervention.
Effectiveness—The ability of an intervention to produce the beneficial results that it is intended to deliver in everyday circumstances.
Efficacy—The ability of an intervention to produce beneficial results that it is intended to deliver within a research study.
Epidemiology—Study of factors that influence the health and disease of a population and the use of this information to study diseases and improve the health of the population.
External Validity—The ability of a study’s results to apply to the general population in real world circumstances. (Ex. A study done on participants older than 65 may not apply to those under 20.)
False Negative—A conclusion that a person does not have the disease or condition being tested, when they actually do.
False Positive—A conclusion that a person does have the disease or condition being tested, when they actually do not.
Follow-up—A period of time that study participants are observed to collect information and measure outcomes.
Gold Standard—The intervention generally believed to be the best available option. New interventions are usually compared to the gold standard.
Hypothesis—Possible explanation that forms the basis of a research study. Studies are designed to help prove or disprove a hypothesis.
Incidence—The number of new cases in a population over a given period of time (expressed as a percentage or ratio).
Intervention—The treatment or test being introduced in a study to determine its effect on the participants.
Matching—Researchers match participants in the control group with participants in the case group according to particular variables that are thought to be important, such as age and sex. Applies to case control studies.
Meta-analysis—A statistical technique in which the results of numerous studies are mathematically combined in order to improve the reliable of the results. Studies chosen for inclusion in a meta-analysis must be sufficient similar in a number characteristics in order to accurately combine their results. Combining studies in this fashion effectively increases the number of participants which increase their power and reliability.
Morbidity—Illness or harm
Observational Study—Researchers do not introduce an exposure or intervene into the lives of participants. Differences between exposed and unexposed groups are recorded. Changes or differences that occur between the two groups are recorded. Observational studies are highly prone to
are examples of observational studies.
Open Label Study—Participants and researchers are not
to the intervention.
Placebo—An inactive substance or false procedure (sham) given to participants in a comparison group as a substitution for the treatment being studied. This process is necessary to insure that participants do not which group (control or treatment) they are in.
Prevalence—The number of cases, events, or conditions in a given population (expressed as a percentage or ratio).
Randomization—The process of assigning study participants to treatment or control groups by chance. Randomly assigning participants to groups reduces the chances that
variables will affect the reliability of a study’s results.
Randomized Controlled Trial (RCT)—The study includes a treatment and a comparison group, and participants are randomly assigned to each group. The intervention is given and the groups are observed. Outcomes such as improvement or harms are noted. RCT are considered the most reliable type of study.
Recall Bias—Some studies rely on the ability of participants to remember habits or exposures. Recall from participants can be faulty due to: difficulty of tracking certain behaviors (diet, exercise), reluctance to report embarrassing behaviors (sexual, alcohol/drug abuse), and the fact that individuals who have a disease are more likely to remember exposures than those who do not.
Relative Risk (RR)—The chance of one group developing a health outcome compared to another group. It is expressed as the number of times one group may be at risk over another. (Ex. People who smoke are 10 to 20 times more likely to get lung cancer than people who do not smoke.)
Retrospective Study—A study design that looks backwards to see if an association exist between a past exposure and a health outcome. This type of study is most often a
may also rely on a retrospective approach.
Risk Factor—Something that increases the chance of developing a disease or health condition. Risk factors may be a lifestyle habit, environmental exposure, or genetic predisposition.
(Statistical Significance)—A mathematical method of defining the reliability of the study results. High statistical power means that the results of a study are less likely to be due to chance alone. Low statistical power does not necessarily mean that the results are wrong but they are considered inconclusive. The more people in a study the more reliable and the higher the power of the study.
Systematic Review—A study that assesses the results of all previous studies on a particular subject to provide a better understanding of their results, which often differ.
Treatment Group—Group of participants that receive the intervention being studied.
Last reviewed September 2008 by Richard Glickman-Simon, MD
Please be aware that this information is provided to supplement the care provided by your physician. It is neither intended nor implied to be a substitute for professional medical advice. CALL YOUR HEALTHCARE PROVIDER IMMEDIATELY IF YOU THINK YOU MAY HAVE A MEDICAL EMERGENCY. Always seek the advice of your physician or other qualified health provider prior to starting any new treatment or with any questions you may have regarding a medical condition.
Copyright © EBSCO Publishing. All rights reserved.