Glossary

A | B | C | D | E | F | G | H | I | L | M | N | O | P | Q | R | S | T | V |
A
Absolute risk The percentage of subjects in a group that experiences a discrete outcome.
Absolute risk (rate) reduction (ARR) The difference in rates of outcomes between the control group and the experimental or exposed group. An efficacious therapy serves to reduce that risk. For example, if 15% of the placebo group died and 10% of the treatment group died, ARR or the absolute reduction in the risk of death is 5%.
Absolute Risk Increase (ARI) The absolute arithmetic difference in rates of harmful outcomes between experimental (EER) and control groups (CER), calculated as rate of harmful outcome in experimental group minus rate of harmful outcome in control group (EER–CER). Typically used with a harmful exposure.
Absolute Risk Reduction (ARR) The absolute arithmetic difference (risk difference) in rates of harmful outcomes between experimental (EER) and control groups (CER), calculated as the rate of harmful outcome in the control group minus the rate of harmful outcome in the experimental group (CER–EER). Use restricted to a beneficial exposure or intervention.
ACP Journal Club ACP Journal Club (ACP) is a component of OVID’s Evidence Based Medicine Reviews. The ACP Journal Club Collection consists of two journals: ACP Journal Club, a publication of the American College of Physicians; and Evidence-Based Medicine, a joint publication with the British Medical Journal Group. The editors of ACP Journal Club screen the top clinical journals on a regular basis and identify studies that are both methodologically sound and clinically relevant. They write an enhanced abstract of the chosen articles and provide a commentary on the value of the article for clinical practice
Adjusted Analysis An adjusted analysis takes into account differences in prognostic factors (or baseline characteristics) between groups that may influence the outcome. For instance, in a comparison between an experimental intervention and control, if the experimental group is on average older, and thus at higher risk of an adverse outcome than the control group, the adjusted analysis will show a larger treatment effect than the unadjusted analysis.
Adjustment Changing the probability of disease as a result of additional information such as additional history, physical exam, diagnostic test of some kind or demographic charactericstic.
Alpha Level The probability of erroneously concluding there is a difference between comparison groups when there is in fact no difference (type I error). Typically, investigators decide on the chance of a false-positive result they are willing to accept when they plan the sample size for a study (e.g., investigators often set alpha level at 0.05).
Alternative hypothesis In hypothesis testing, the alternative is the contradictory statement to the null hypothesis.
B
Bar graph Graph depicting nominal, sometimes ordinal data. The height of each bar = frequency. Bars DO NOT touch for categories.
Bayes' theorem What we know after doing a test equals what we knew before doing the test times a modifier (based on the test results). Post-test odds = pretest odds x likelihood ratio.
Benefit vs. Harm see harm vs. benefit
Beta The probability of a type II error is denoted by the Greek letter (beta). By definition, power = 1 - when the null hypothesis is false.
Bias Any factor other than the experimental therapy that could change the study results in a non-random way. The direction of bias offset may be unpredictable. The validity of a study is integrally related to the degree to which the results could have been affected by biased factors. (Mayer) A systematic error in the design, conduct or interpretation of a study that may cause a systematic deviation from the underlying truth. 1. Channeling effect or Channeling bias: Tendency of clinicians to prescribe treatment based on a patient’s prognosis. As a result of the behavior, in observational studies, treated patients are more likely to be high-risk patients than untreated patients, leading to biased estimate of treatment effect. 2. Data completeness bias: Using a computer decision support system (CDSS) to log episodes in the intervention group and using a manual system in the non-CDSS control group can create variation in the completeness of data. 3. Detection bias: Tendency to look more carefully for an outcome in one of the comparison groups. 4. Expectation bias: In data collection, an interviewer has information that influences her expectation of finding the exposure or outcome. In clinical practice, a clinician's assessment may be influenced by prior knowledge of the presence or absence of a disorder. 5. Incorporation bias: Occurs when investigators study a diagnostic test that incorporates features of the target outcome. 6. Interviewer bias: Greater probing by an interviewer in one of the groups being compared. 7. Publication bias: Occurs when the publication of research depends on the direction of the study results and whether they are statistically significant. 8. Recall bias: Occurs when patients who experience an adverse outcome have a different likelihood of recalling an exposure than patients who do not experience the adverse outcome independent of the true extent of exposure. 9. Social desirability bias: Study participants misrepresent their responses in the direction of answers consistent with prevailing social norms or socially desirable behavior. 10. Surveillance bias: Synonymous with detection bias, the tendency to look more carefully for an outcome in one of the comparison groups. 11. Verification Bias: Results of a diagnostic test influence whether patients are assigned to intervention group (sometimes called Work-up bias).
Binary data/outcome A variable that can take one of two discrete values rather than values incrementally placed along a continuum (e.g., male or female, pregnant or not pregnant, dead or alive).
Biostatistics Biostatistics The use of numerical techniques to extract information from data. The discipline focuses on the variation in sets of data, that occurs either because of some intervention or from the effect of other variables linked to the data. Biostatistical tests frequently look at the comparison between an observed effect, or a difference, and the anticipated results of random variation. Some have stated that biostatistics is the study of variability or uncertainty.
C
Case Series A study design that reports data on a series of consecutive patients with the same diagnosis. It is crucial that a rigorous case definition be used to insure all actually are members of the same group. There is NO control group.
Categorical data (aka Nominal) Categorical/Nominal Data Data that fits into a qualitative category but cannot be ordered, for example race, religion or country of birth.
Causality The relationship between cause and effect. A fundamental concept in epidemiology. A given cause may be necessary, sufficient, neither or both. A "necessary" cause must always precede an effect. A "sufficient" cause inevitably initiates an effect but is not the only necessary cause for a given effect.
Causation (of disease) The following factors can be differentiated (but are not mutually exclusive): 1) predisposing factors, 2) enabling factors, 3) precipitating factors, and 4) reinforcing factors.
Central Tendency Measures of Central Tendency The center of a set of variables or data. There are 3 measures of central tendency: mean, median and mode.
Chi-square Test A nonparametric test of statistical significance used to compare the distribution of categorical outcomes in two or more groups, the null hypothesis of which is that the underlying distributions are identical.
Clinical Decision Making A complex cognitive process made in the context of a patient’s care and the patient’s clinical problems. Best accomplished by clinicians who have highly competent basic clinical skills, use the best evidence available to support sound reasoning and patient preferences
Clinical Epidemiology A discipline that describes quantifies and postulates causal mechanisms for health phenomena in populations.
Clinical significance Results that make enough difference to you and your patient to justify changing your way of doing things. For example, a drug which is found in a mega trial of 50000 adults with acute asthma to increase FEV1 by only 0.5% (P < 0.0001) would fail this test of significance. The findings must have practical importance as well as statistical importance. (See statistical Significance.)
Clinical Trial Also known as a "Randomized Clinical Trial" or "Controlled Trial." See definition for "Randomized Clinical Trial" and "Clinical trial, types or phases"
Clinical trial, types or phases Interventional clinical trials are conducted in phases. The trials at each phase have a different purpose and help answer different questions. PHASE I TRIALS: Initial studies to determine the metabolism and pharmacologic actions of drugs in humans, the side effects associated with increasing doses, and to gain early evidence of effectiveness; may include healthy participants and/or patients. PHASE II TRIALS: Controlled clinical studies conducted to evaluate the effectiveness of the drug for a particular indication or indications in patients with the disease or condition under study and to determine the common short-term side effects and risks. PHASE III TRIALS: Expanded controlled and uncontrolled trials after preliminary evidence suggesting effectiveness of the drug has been obtained, and are intended to gather additional information to evaluate the overall benefit-risk relationship of the drug and provide and adequate basis for physician labeling. PHASE IV TRIALS: Post-marketing studies to delineate additional information including the drug's risks, benefits, and optimal use.
Cochrane Database of Systematic Reviews (COCH) Produced by the Cochrane Collaboration, the Cochrane Database of Systematic Reviews (COCH) is one of the premiere EBM databases. It includes the full text of the regularly updated systematic reviews of the effects of healthcare prepared by The Cochrane Collaboration. The reviews are presented in two types: Complete reviews - Regularly updated Cochrane Reviews, prepared and maintained by Collaborative Review Groups; and Protocols - Protocols for reviews currently being prepared (all include an expected date of completion). Protocols are the background, objectives and methods of reviews in preparation.
Composite outcome (or composite endpoint) An outcome based upon two or more individual outcomes (or endpoints). May be indentified in the results sections of the medical literature by the use of the boolean operator "or" found between two individual outcomes (or endpoints). Frequently used as a summary measure in clinical trails. Substantial risk, however, is associated with composite outcomes as the effects or associations reported may be falsely presumed to be related to all of the individual components.
Conditional Probabilities The probability of a particular state, given another state (i.e., the probability of A, given B).
Confidence Interval (CI) Range between two values within which it is probable that the true value lies for the whole population of patients from which the study patients were selected. It is the interval around an observed parameter guaranteed to include the true value to some level of confidence (usually 95%). The true value can be expected to be within that interval with 95% confidence.
Confounder (or Confounding Variable) Confounding A factor that distorts the true relationship of the study variable of interest by virtue of also being related to the outcome of interest. Confounders are often unequally distributed among the groups being compared. Randomized studies are less likely to have their results distorted by confounders than are observational studies.
Construct Validity A construct is a theoretically derived notion of the domain(s) we wish to measure. An understanding of the construct will lead to expectations about how an instrument should behave if it is valid. Construct validity therefore involves comparisons between measures, and examination of the logical relationships, which should exist between a measure and characteristics of patients and patient groups. Essentially, does the study aptly measure what it proposes to measure? In social science and psychometrics, construct validity refers to whether a scale measures the unobservable social construct (such as "fluid intelligence") that it purports to measure. It is determined after studies show correlation between the measure itself and the characteristics it is aimed at.
Continuous test results A test resulting in an infinite number of possible outcome values.
Continuous Variable A variable that can theoretically take any value and in practice can take a large number of values with small differences between them (e.g., height).
Correlation The magnitude of the relationship between two different variables or phenomena.
Correlation Coefficient A numerical expression of the magnitude and direction of the relationship between two variables, which can take values from –1.0 (perfect negative relationship) to 0 (no relationship) to 1.0 (perfect positive relationship).
Critical appraisal The process of assessing and interpreting evidence systematically, considering its validity, results, and relevance.
Critical Value The critical value for a hypothesis test is a threshold to which the value of the test statistic in a sample is compared to determine whether or not the null hypothesis is rejected.
D
DARE (Database of Absstracts of Reviews of Effectiveness) The Database of Abstracts of Reviews of Effectiveness (DARE) is part of Ovid's collection of Evidence Based Medicine Reviews. It is a full-text database containing critical assessments of systematic reviews from a variety of medical journals. Critically appraised by reviewers at the (U.K.) National Health Service Centre for Reviews and Dissemination at the University of York, England. Included reviews have met strict quality criteria and have to be about the effects of interventions
Database Collection of data or information organized for rapid search and retrieval, especially by a computer. Databases are structured to facilitate storage, retrieval, modification, and deletion of data in conjunction with various data-processing operations. A database consists of a file or set of files that can be broken down into records, each of which consists of one or more fields. Fields are the basic units of data storage. Users retrieve database information primarily through queries. Using keywords and sorting commands, users can rapidly search, rearrange, group, and select the field in many records to retrieve or create reports on particular aggregates of data according to the rules of the database management system being used. (Encyclopedia Britannica).
Decision analysis Systematic way in which the components of decision making can be incorporated to make the best possible clinical decision using a mathematical model. Also known as Expected values decision making. It involves identifying all available alternatives and estimating the probabilities of potential outcomes associated with each alternative, valuing each outcome, and, on the basis of the probabilities and values, arriving at a quantitative estimate of the relative merit of the alternatives.
Dependent Variable (or Outcome) The target variable of interest. The variable that is hypothesized to depend on or be caused by another variable, the independent variable.
Descriptive statistics Measures intended to describe the distribution of data, without claiming to conclude causality. Can be used to measure risks and generate hypothesis for future studies.
Diagnostic tests Modalities which can be used to increase the accuracy of a clinical assessment by helping to narrow the list of possible diseases that a patient can have.
Diagnostic trials Refers to trials that are are conducted to find better tests or procedures for diagnosing a particular disease or condition. Diagnostic trials usually include people who have signs or symptoms of the disease or condition being studied. (See Clinical trial and Randomized Controlled Trial)
Dichotomous Variable Dichotomous/Binary Data A variable that can take one of two discrete values rather than values incrementally placed along a continuum (e.g., male or female, pregnant or not pregnant, dead or alive).
Differential diagnosis A list of possible diseases that your patient can have in descending order of clinical probability.
Discrete data (aka ordinal) Interval/Discrete Data Data that can be arranged into naturally occurring or even arbitrary groups, such as the number of decayed teeth, in contrast to continuous data, that has no logical breaks.
Distribution The complete summary of the values, measures or categories made of a group. The distribution tells either how many or what proportion of the group was found to have each value (or range of values).
Dose-Response The relationship of observed responses (outcomes) in a population to differing levels of a harmful (or protective) agent such as an environmental contaminant or exposure. Commonly displayed as a graph with important aspects such as 1) the rate at zero dose (baseline or control), 2) presence (or absence) or a threshold dose, 3) presence of a mathematical relationship (linear, logarithmic, etc.) between the dose and response.
E
Economic Analysis A set of formal, quantitative methods used to compare two or more treatments, programs, or strategies with respect to their resource use and their expected outcomes.
Effect Size The difference in outcomes between the intervention and control groups divided by some measure of variability, typically the standard deviation.
End Point Health event or outcome that leads to completion or termination of followup of an individual in a trial or cohort study, for example, death or major morbidity.
Evidence-Based Decision Making (EBDM) The name of the curricular thread at the University of Arizona College of Medicine that integrates Evidende -Based Medicine (EBM) and decision-making content.
Evidence-Based Medicine (EBM) The conscientious, explicit, and judicious use of current best evidence in making decisions about the care of individual patients. Evidence-based clinical practice requires integration of individual clinical expertise and patient preferences with the best available external clinical evidence from systematic research, and consideration of available resources.
Evidence-Based Practice (EBP) The conscientious, explicit, and judicious use of current best evidence in making decisions about the care of individual patients. Evidence-based clinical practice requires integration of individual clinical expertise and patient preferences with the best available external clinical evidence from systematic research, and consideration of available resources.
Expert Opinion Opinions, not critically-appraised by a structured scientific method, voiced or communicated by an individual. The level of clinical expertise of the individual certainly holds merit so the level of strength of opinion does as well.
Explanatory research - experimental Study in which the independent variable (usually a treatment) is changed by the researcher who then observes the effect of this change on the dependent variable (usually an outcome). The key here is the willful manipulation of the two variables.
Explanatory research - observational Study looking for possible causes of disease (dependent variable) based upon exposure to one or more risk factors (independent variable) in the population.
External validity The same as "Applicability" (The degree to which the results of a study are likely to hold true in your practice setting. Also called external validity, generalizability, particularizability, relevance.) Are the patients in the study similar to the patients you might apply the evidence to?
F
False Negative Those who have the target disorder but the test incorrectly identifies them as not having it.
False Positive Those who do not have the target disorder, but the test incorrectly identifies them as having it.
G
Gender Specific Medicine A discipline of medicine and medical research that focuses on variation in health and healthcare related to gender.
Gold Standard (or Reference Standard or Criterion Standard) The reference standard for evaluation of a measurement or diagnostic test. The "gold-standard" test is assumed to correctly identify the presence or absence of disease 100% of the time. Essentially, a method having established or widely accepted accuracy for determining a diagnosis that provides a standard to which a new screening or diagnostic test can be compared. The method need not be a single or simple procedure but could include follow-up of patients to observe the evolution of their conditions or the consensus of an expert panel of clinicians.
H
Harm Adverse consequences of exposure to a stimulus.
Harm vs. benefit An accounting of the positive and negative aspects of an exposure (positive or negative) on the outcomes of a study.
Hierarchy of evidence A system that grades evidence or published information related to healthcare, according to the strength of scientific merit that produced the evidence. The model used by ArizonaMed EBDM places Level 1 evidence at the top. Level 1 evidence is typically the result of Systematic Reviews or very large RCTs. Level 2 evidence is typically the result of Prospective Observational Studies, e.g., prospective cohort study. Level 3 evidence is typically the result of Retrospective Observational Studies, e.g., case-control study. Level 4 evidence is typically the result of a Case Series. Level 5 evidence is typically found in Textbooks or Expert Opinion that have not been critically-appraised.
Histogram Histogram A graph that displays the frequency distribution of discrete or continuous data. The horizontal axis displays the various intervals and the vertical axis displays either the true frequency or the relative frequency of observations within each interval.
Hypothesis An educated guess on the nature of the patient's illness, usually obtained by selecting those diseases having the same history or physical examination characteristics as the patient
Hypothesis Testing Hypothesis testing is the foundational scientific method. Thought to be a product of the renaissance (Roger Bacon - 14th century). Knowledge, beliefs and theories are tested to determine their truth and validity. Depends upon a pre-experiment assumption of the probability of error.
I
Incidence The rate at which an event occurs in a defined population over time. The number of new cases (or other events of interest) divided by the total population at risk.
Inferential statistics The development of generalizations from sample data, usually reported with calculated degrees of uncertainty.
Internal validity The study design performance at measuring differences, if they exist, between groups, eg, intervention and control, that are due only to the hypothesized effect.
Interquartile range The difference between the 25th and 75th percentile values.
L
Level of significance (confidence level) Describes the probability of incorrectly rejecting the null hypothesis and concluding that there is a difference when in fact none exists (i.e., probability of Type I error). Many times this probability is 0.01, 0.05, or 0.10. For medical studies it is most commonly set at 0.05.
Life Long Learning A behavior that includes the commitment to continuous enhancement of knowledge and clinical practice throughout one’s career. This can be accomplished by a commitment to EBDM as the clinician becomes exposed to the best evidence in the literature for common clinical problems on a frequent basis.
M
Mean A measusre of central tendency which can be obtaiined by adding up all the values and dividing by the total number of values. Also known as the "classic average" (see median).
Measurement The application of an instrument or method to collect data systematically. What the use of the instrument tells us, e.g., temperature, blood pressure, results of dietary survey, etc.
Median A measure of central tendency in which half of the values are above and half are below. Also known as the 50th percentile (see mean).
Medical Informatics A discipline that includes the development and application of Information Technology systems to problems in healthcare, research and medical education. Three major domains include 1. Communication, e.g., email; 2. Knowledge Management, e.g., evidence-based databases and the Electronic Health Record; 3. Decision Support, e.g., computerized order entry.
Meta-analysis A systematic review of a focused clinical question following rigorous methodological criteria and employing statistical techniques to combine data from multiple independently performed studies on that question. essentially, a statistical technique for quantitatively combining the results of multiple studies, that measure the same outcome, into a single pooled or summary estimate.
Mode A measure of central tendency which is the value tha occurs the most frequently.
N
National Guideline Clearinghouse-Guideline.gov Health care professionals can use this database to find evidence-based clinical practice guidelines and related abstract, summary, and comparison materials. The clearinghouse is sponsored by the Agency for Healthcare Research and Quality (AHRQ).
Negative predictive value (NPV) Probability of no disease after a negative test result.
Nominal data (aka Categorical) Categorical/Nominal Data Data that fits into a qualitative category but cannot be ordered, for example race, religion or country of birth.
Normal distribution Normal Distribution A normal distribution or Gaussian distribution of variables, the bell-shaped curve. (2) A value of a diagnostic test which defines patients who are not diseased.
NPV (Negative Predictive Value) Probability of no disease after a negative test result.
Null hypothesis The assumption that there is no difference between groups or no association between predictor and outcome variables.In the hypothesis-testing framework, the starting hypothesis
O
Observational Study, Prospective Observational Studies A research study design planned and conducted with outcome data acquired in a prospective fashion, i.e., after the study has started. Example: prospective cohort study. A strength of this design is that incidence rates can be compared in groups that differ by levels of exposure.
Observational Study, Retrospective Observational Studies A research study design planned and conducted with outcome data that has already occurred in the past, i.e., before the study has started. Example: case control study.
Odds Ratio (or Cross-Product Ratio or Relative Odds) A ratio of the odds of an event in an exposed group to the odds of the same event in a group that is not exposed. An odds ratio of 1 indicates that the condition or event under study is equally likely in both groups. An odds ratio greater than 1 indicates that the condition or event is more likely in the first group. And an odds ratio less than 1 indicates that the condition or event is less likely in the first group. For example, suppose that in a sample of 100 men, 90 have drunk beer in the previous week, while in a sample of 100 women only 20 have drunk beer in the same period. The odds of a man drinking beer are 90 to 10, or 9:1, while the odds of a woman drinking beer are only 20 to 80, or 1:4 = 0.25:1. Now, 9/0.25 = 36, so the odds ratio is 36, showing that men are much more likely to drink beer than women.
One-sided (tailed) test Used when the alternative hypothesis is directional (I.e., specifies a particular direction of the difference between the groups.)
Ordinal data Ordinal Data Data that has distinct order but the categories are qualitative, for example social class I, II and III.
Ordinal data (aka discrete) Ordinal Data Data that can be arranged into naturally occurring or even arbitrary groups, such as the number of decayed teeth, in contrast to continuous data, that has no logical breaks.
Outcome (or Dependent Variable) The target variable of interest. The variable that is hypothesized to depend on or be caused by another variable, the independent variable
Outcomes study The outcome of an intervention, exposure, or diagnosis measured over a period of time.
P
P value The probability that the difference(s) observed between two or more groups in a study occurred by chance if there really was no difference between the groups.(Mayer) .The probability that results as or more extreme than those observed would occur if the null hypothesis were true and the experiment were repeated over and over. A P value < 0.05 means that there is a less than 1 in 20 probability of the result occurring by chance alone if the null hypothesis were true.
Parameter Value summarizing characteristic of population; are constants; use Greek letters to represent
Patient Values Patient Values are subjective, vary across people and cultures and are in many ways aligned with belief and belief systems. They are the underlying foundation for preferences or an indvidual's choices about health care.
Population Samples and Populations The group of people who meet the criteria for entry into a study (whether they actually participated in the study or not). The group of people to whom the study results can be generalized.
Positive predictive value (PPV) Probability of disease after the occurrence of a positive test result.
Power The probability that an experimental study will correctly observe a statistically significant difference between the study groups when that difference actually exists. Also ,the ability of a study to reject a null hypothesis when it is false (and should be rejected). It is linked to the adequacy of the sample size; if a sample size is too small, the study will have insufficient power to detect differences between groups, if differences exist.
PPV (Positive Predictive Value Probability of disease after the occurrence of a positive test result.
Precision The measurement is nearly the same value each time it is measured. Measure of random variation or error, or a small standard deviation of the measurement across multiple measurements.
Prevalence The proportion of people in a defined group who have a disease, condition, or injury. The numbers affected by a condition divided by the population at risk. In the context of diagnosis, this is also called “pretest probability." Prevalence rates obtained from high-quality studies can inform pretest probabilities.
Prevention trial Refers to trials to find better ways to prevent disease in people who have never had the disease or to prevent a disease from returning. These approaches may include medicines, vitamins, vaccines, minerals, or lifestyle changes. (See Clinical trial and Randomized Controlled Trial)
Probability Chance or frequency of a random event occurring (Frequentist). Also, the quantitative estimate of the likelihood of a condition existing (as in diagnosis) or of subsequent events (such as in an intervention study) given some assumed situation or patient scenario (Conditional/Bayesean).
Prognosis The possible outcomes for a given disease and the length of time to those outcomes.
Prospective Study (or Cohort Study or Longitudinal Study) Any study done forwards in time. Important in studies on therapy, prognosis, or harm, where retrospective studies make hidden biases more likely. When used to study potential causes of a disorder, it is a prospective investigation in which a cohort of individuals who do not have evidence of an outcome of interest but who are exposed to the putative cause are compared with a concurrent cohort who are also free of the outcome but not exposed to the putative cause. Both cohorts are then followed forward in time to compare the incidence of the outcome of interest. When used to study the effectiveness of an intervention, it is a prospective investigation in which a cohort of individuals who receive the intervention are compared with a concurrent cohort who do not receive the intervention. Both cohorts are then followed forward in time to compare the incidence of the outcome of interest.
Publication bias The possibility that studies with conflicting results (most often negative studies) are less likely to be published. Occurs when the publication of research depends on the direction of the study results and whether they are statistically significant.
Q
Quality of Life trials Refers to trials that explore ways to improve comfort and quality of life for individuals with a chronic illness.
R
Random selection or assignment Selection process of a sample of the population such that every subject in the population has an equal chance of being selected for each arm of the study.
Randomized clinical trial or Randomized controlled trial (RCT) An interventional study in which the patients are randomly selected or assigned either to a group which gets the intervention or to a control group. Essentially an experiment in which individuals are randomly allocated to receive or not receive an experimental preventive, therapeutic, or diagnostic procedure and then followed to determine the effect of the intervention
Range The difference between the largest and the smallest values in the distribution.
Ranked data Data that can be arranged in meaningful order, for example numerical order or degree of severity.
RCT (Randomized Clinical or Randomized Controlled Trial) An interventional study in which the patients are randomly selected or assigned either to a group which gets the intervention or to a control group. Essentially an experiment in which individuals are randomly allocated to receive or not receive an experimental preventive, therapeutic, or diagnostic procedure and then followed to determine the effect of the intervention
Receiver operating characteristic (ROC) curve A plot of sensitivity versus one minus specificity (true-positive rate versus false-positive rate) can give the quality of a diagnostic test and determine which is the best cutoff point.
Retrospective study Any study in which the outcomes have already occurred before the study and collection of data has begun.
S
Sample Samples and Populations That part of the population selected to be studied. The group specifically included in the actual study.
Screening Looking for disease among asymptomatic patients. Screening services, designed to detect people at high risk of suffering from a condition associated with a modifiable adverse outcome, offered to persons who have neither symptoms of, nor risk factors (other than age or gender) for, a target condition.
Screening trial Refers to trials which test the best way to detect certain diseases or health conditions. (See Clinical trial and Randomized Controlled Trial)
Search Engine An informatics technology that, because of the existence of digital organized databases, allows extremely rapid computer-assisted searching for information. Searches typically begin with keywords or concepts that are entered alone or in combinations.
Sensitivity The ability of a test to identify patients who have disease. True-positive rate.
Specificity The ability of a test to identify patients without the disease when it is negative. True-negative rate.
Standard Deviation A measure of variation of a frequency distribution. It is a summary of how widely dispersed the values are around the center of the distribution.
Statistic Value summarizing characteristic of a sample; are variable; use Roman letters to represent
Statistical Bias See both definitions for bias
Statistical Inference Statistical methodologies to make deductions about underlying truth. There are two principle functions: (1) To predict or estimate a population parameter from a sample statistic, and (2) to test statistically based hypotheses.
Statistical Measurement (Measurement) The application of an instrument or method to collect data systematically. What the use of the instrument tells us, e.g., temperature, blood pressure, results of dietary survey, etc.
Statistical Power See Power
Statistical significance Statistical Significance A measure of how confidently an observed difference between two or more groups can be attributed to the study interventions rather than chance alone.When statistically significant, the probability of the observed results, given the null hypothesis, falls below a specified level of probability (most often P < 0.05).Describes the probability of incorrectly rejecting the null hypothesis and concluding that there is a difference when in fact none exists (i.e., probability of Type I error). Many times this probability is 0.01, 0.05, or 0.10. For medical studies it is most commonly set at 0.05.
Statistical Tests Mathematical tests used to discriminate differences in data and outcomes.
Statistical Validity (Validity) The extent to which an instrument measures what it is intended to measure.
Studies or Study Design The way a study is organized or constructed. Examples of Therapy studies: a) Phase I Studies: Studies that investigate a drug’s physiological effect or ensure that it does not manifest unacceptable early toxicity, often conducted in normal volunteers. b) Phase II Studies: Initial studies on patients, which provide preliminary evidence of possible drug effectiveness. c) Phase III Studies: Randomized control trials designed to definitively establish the magnitude of drug benefit. d) Phase IV Studies or Post marketing Surveillance Studies: Studies conducted after the effectiveness of a drug has been established and the drug marketed, typically to establish the frequency of unusual toxic effects.
Systematic Review A formal review of a focused clinical question based on a comprehensive search strategy and structured critical appraisal of all relevant studies.
Systematic ReviewTextbook A publication that reviews a certain body of knowledge. Useful to provide foundational or background knowledge on given topics. Although there are editors, and the supporting scientific-literature is referenced, the material is not typically critically-appraised. Various levels of evidence are therefore commonly intertwined leaving the reader, enlightened to critical-appraisal, wondering about the strength of the information.
T
Treatment trial Refers to trials which test new treatments, new combinations of drugs, or new approaches to surgery or radiation therapy. (See Clinical Trial and Randomized Controlled Trial)
True Negative Those who do not have the target disorder and the test correctly identifies them as not having it.
True Positive Those who have the target disorder and the test correctly identifies them as having it.
Two-sided (tailed) test Used when alternative hypothesis is non-directional and there is no specification of the direction of differences between the groups.
Type I error Error made by rejecting the null hypothesis when it is true and accepting the alternative hypothesis when it isn't true.
Type II error Error made by not rejecting the null hypothesis when it is false and the alternative hypothesis is true.
V
Validity (Statistical Validity) The extent to which an instrument measures what it is intended to measure. Construct validity is the extent to which the measurement corresponds to theoretical concepts (constructs) concerning the phenomena being studied. Content validity is the extent to which the measurement incorporates all of the domain of the phenomena. Criterion validity is the extent to which the measurement correlates with an external criterion of the phenomena.
Validity (Study Validity) The degree to which the inference drawn from a study is warranted. Internal validity refers to the quality of study design that minimizes any effects other than those hypothesized and under investigation. External validity (generalizability) refers to the extent to which the inferences drawn from the study subjects can be generalized or applied to the external population.
Variabililty Variability See variance
Variance (Variability) The technical term for the statistical estimate of the variability in results. Essentially, a measure of the spread of values around the mean. Statistically defined as the sum of the squares of deviation from the mean, divided by the number of degrees of freedom.