data analysis

data analysis,

(in research) the phase of a study that includes classifying, coding, and tabulating information needed to perform quantitative or qualitative analyses according to the research design and appropriate to the data. Data analysis follows collection of information and precedes its interpretation or application.

---

analysis [ah-nal´ĭ-sis] (pl. anal´yses)

separation into component parts.

psychoanalysis. adj., adj analyt´ic.

activity analysis the breaking down of an activity into its smallest components for the purpose of assessment.

bivariate analysis statistical procedures that involve the comparison of summary values from two groups on the same variable or of two variables within a group.

blood gas analysis see blood gas analysis.

chromosome analysis see chromosome.

concept analysis examination of the attributes of a concept as it occurs in ordinary usage in order to identify the meanings attached to the concept.

content analysis a systematic procedure for the quantification and objective examination of qualitative data, such as written or oral messages, by the classification and evaluation of terms, themes, or ideas; for example, the measurement of frequency, order, or intensity of occurrence of the words, phrases, or sentences in a communication in order to determine their meaning or effect.

correlational analysis a statistical procedure to determine the direction of a relationship (positive or negative correlation) between two variables and the strength of the relationship (ranging from perfect correlation through no correlation to perfect inverse correlation and expressed by the absolute value of the correlation coefficient).

analysis of covariance (ANCOVA) a variation of analysis of variance that adjusts for confounding by continuous variables.

data analysis the reduction and organization of a body of data to produce results that can be interpreted by the researcher; a variety of quantitative and qualitative methods may be used, depending upon the nature of the data to be analyzed and the design of the study.

ego analysis in psychoanalytic treatment, the analysis of the strengths and weaknesses of the ego, especially its defense mechanisms against unacceptable unconscious impulses.

gait analysis see gait analysis.

gastric analysis see gastric analysis.

multiple-locus variable number of tandem repeat analysis (MLVA) a laboratory tool designed to recognize tandem repeats and other qualities in the genome of an individual to provide a high resolution DNA fingerprint for the purpose of identification.

multivariate analysis statistical techniques used to examine more than two variables at the same time.

power analysis a statistical procedure that is used to determine the number of required subjects in a study in order to show a significant difference at a predetermined level of significance and size of effect; it is also used to determine the power of a test from the sample size, size of effect, and level of significance in order to determine the risk of Type II error when the null hypothesis is accepted.

qualitative analysis the determination of the nature of the constituents of a compound or a mixture of compounds.

quantitative analysis determination of the proportionate quantities of the constituents of a compound or mixture.

SNP analysis analysis of single nucleotide polymorphisms to assess artificially produced genetic modifications or identify different strains of an organism.

transactional analysis a type of psychotherapy based on an understanding of the interactions (transactions) between patient and therapist and between patient and others in the environment; see also transactional analysis.

analysis of variance ANOVA; a statistical test used to examine differences among two or more groups by comparing the variability between the groups with the variability within the groups.

variance analysis the identification of patient or family needs that are not anticipated and the actions related to these needs in a system of managed care. There are four kinds of origin for the variance: patient-family origin, system-institutional origin, community origin, and clinician origin.

vector analysis analysis of a moving force to determine both its magnitude and its direction, e.g., analysis of the scalar electrocardiogram to determine the magnitude and direction of the electromotive force for one complete cycle of the heart.

---

data

plural of datum. A collection of information or facts. See also information.

---

data adjustment

for useful results data often need to be modified before analysis; for example for age, for sex or for difficulty or for number of attempts.

data analysis

submission of data to statistical analysis; includes sorting into categories and determining relationships between variables.

data capture

a mechanism for collecting specified segments or categories of data from a stream of automatically recorded data some of which may be irrelevant for the specific purpose.

categorical data

are qualitative and suited to classification into categories. Further divisible into nominal (names), ordinal (levels of quality, development), dichotomized (mutually exclusive).

continuous data

data which have an infinite number of possible values.

diagnostic data

lists of diagnoses and data of clinical signs, clinical pathology results and pathology lesions used in the making of diagnoses.

dimensional data

numerical or quantitative data. May be explicit and therefore continuous, or grouped into approximate groups, e.g. nearest whole number, i.e. discrete data.

discrete data

data that have finite (usually whole integer) value and therefore fall naturally into groups of similar values; opposite to continuous data.

incidence data

data related to the occurrence of specific disease incidents.

non-normal data

data whose frequency distribution is markedly different to that of normal data (see below).

normal data

data which manifests graphically as a bell-shaped curve distributed symmetrically about the peak value.

ordinal data

a type of data containing limited categories with a ranking from the lowest to the highest, e.g. very mild, moderate, severe.

paired data

see paired data.

passive data

data acquired from records collected for some other purpose.

pre-existing data

data in existence before the commencement of a study. Of limited value unless they are exactly the data required, have been collected adequately, and a group of pre-existing controls with their corresponding data can be identified.

prevalence data

disease occurrences are recorded against the size of the population at risk at the time.

raw data

data as they are collected and before any calculation, ordering, etc. has been done.

screening data

data obtained by periodic diagnostic testing of randomly selected samples of a population.

secondary data

the use of data for purposes other than that for which it was intended.

sentinel data

data collected from sentinel animals or other recording units.