
Analysis of Variance (ANOVAO)
Statistical procedures for analysis of data that contain a continuous dependent variable and more than one nominal independent variable. ANOVA procedures include oneway and factorial ANOVA.

Bias
A condition that produced results which depart from the true values in a consistent direction. (syn: systematic error)

Case Control (retrospective) study
A study that begins by identifying individuals with a disease (cases) and individuals with a disease (controls). The cases and controls are identified without knowledge of an individuals's exposure or non exposure to factors being investigated. These factors are determined from existing information (syn: retrospective).

Chi square distribution
A standard mathematical distribution that can be sued to calculate the P values and confidence intervals in a variety of statistical procedures for nominal dependent variables.

Control group
A group of persons used for comparison with a study group. Ideally, the control group is identical to the study group except that it does not possess the characteristic or has not been exposed to the treatment under study (syn: reference group).

Correlation
A statistic used for studying the strength of an association between two variables, each of which has been sampled using a representative or naturalistic method from a population of interest.

Correlation coefficient
An estimate of the strength of the association between a dependent variable and an independent variable when both are obtained using naturalistic sampling.

Crossoverstudy
A type of paired design in which the same individual receives a study and a control therapy and an outcome is assessed for each therapy.

Dependent variable
Generally, the outcome variable of interest in any type of research study. The outcome that one intends to explain or estimate.

Distribution
Frequencies or relative frequencies of all possible values of a characteristic. Population and sample distribution can be described graphically or mathematically. One of the purposes of statics is to estimate parameters of population distributions.

Efficacy
The extent to which a treatment produces a beneficial effect when assessed under the ideal conditions of an investigation. Efficacy is to therapy what contributory cause is to etiology of disease.

Extrapolation
Conclusions drawn about the meaning of the study for a target population that includes types of individuals or data not represented in the study sample.

False Negative
An individual whose result on a test is negative but who has the disease or condition as determined by the gold standard.

False Positive
An individual whose result on a test is positive but who does not have the disease or condition as determined by the gold standard.

Gaussian (normal) distribution
A distribution of data assumed in many statistical procedures.The Gaussian distribution is a symmetrical, continuous, bellshaped curve with its mean value corresponding to the highest point on the curve (syn: normal distribution).

Incidence
The rate at which new cases of disease occur per unit of time. the incidence rate is theoretically calculated as the number of individuals who develop the disease over a period of time divided by the total personyears of observation (syn: hazard).

Independent variable
Variable(s) being measured to determine the corresponding measurement of the dependent variable in any type of research study. Independent variables define the conditions under which the dependent variable is to be examined.

Intention to treat
A method for data analysis in a randomized clinical trial in which individual outcomes are analyzed according to the group to which they have been randomized even if they never received the treatment which they were assigned.

Interaction
Interaction occurs when the relationship between variables is altered by the value of another variable (syn: synergy).

Metaanalysis
A series of methods for systematically combing information from more than one investigation in order to draw a conclusion which could not be drawn solely on the basis of the single investigations.

Null hypothesis
The assertion that no true association of difference between variables exists in the larger population from which the study samples are obtained.

Predictive value of a positive test
The proportion of those with a positive test who actually have the condition or disease as measured by the Gold Standard. This measure incorporates the prevalence of the condition or disease. Clinically, the predictive value of a positive test is the probability that an individual has the disease if the test is positive.

Primary/secondary endpoint
Used to refer to the outcome measurement in a study which is used to calculate the sample's size. It should be a frequently occurring and biologically important end point. (Secondary End Point  An end point which is of interest and importance, such as death, but which occurs too infrequently to use to calculate the sample's size.)

Reliability of a test
The degree to which a test gives the same result when the same entity is measured twice (or more).

Risk factor
A characteristic or factor that has been shown to be associated with an increased probability of developing a condition or disease. A risk factor does not necessarily imply a cause and effect relationship. A risk factor implies that at least an association has been established on an individual level.

Runin Period
Preinvestigation observation of patients usually designed to ensure that they are appropriate candidate for entrance into a randomized clinical trail, especially with regard to their adherence to therapy.

Sample
A subset of a larger population obtained for investigation to draw conclusions or make estimates about the larger population.

Sampling error
An error introduced by chance differences between the estimate obtained in a sample and the true value in the larger population from which the sample was drawn. Sampling error is inherent in the use of sampling methods and is measured by the standard error.

Scientific method
The principles and procedures used tin the systematic pursuit of knowledge. It involves the recognition and formulation of a problem, the collection of data through observation or experiment, the formulation of a hypothesis and the testing and confirmation of the hypothesis.

Selection bias
A bias in assignment that occurs when the study and control groups are chosen so that they differ from each other by one r more factors that affect the outcome of the study. A special type of confounding variable that results from study design rather than chance.

Statistical significance test
A statistical technique for determining the probability that the data observed in a sample or more extreme data could occur by chance if there is no such difference or association in the larger population (syn: inference, hypothesis testing).

Study hypothesis
An assertion that an association or difference exists between two or more variables in the population sampled. A study hypothesis can be onetailed, considering associations or differences in one direction only, or twotailed, not specifying the direction of the association or difference.

Validity of test
A test is valid if it is appropriate for the question being asked and is accurate and precise.

