O

OBJECTIVE

  1. (n.) The precisely stated end to which efforts are directed, specifying the population outcome, variable(s) to be measured, etc. See also goal; target.
  2. (adj.) A perspective or method that is free of prejudice, bias, favoritism, special interest. Some authors believe that such perspectives do not exist in reality and that at best an objective view is simply an ideal to strive for.

OBSERVATIONAL EPIDEMIOLOGY The application of epidemiological reasoning, knowledge and methods to studies, and activities that are nonexperimental. Epidemiological studies and programs (e.g., surveillance) in which main conditions (e.g., expo- sures) are not under the direct control of the epidemiologist.

OBSERVATIONAL STUDY (Syn: nonexperimental study) A study that does not involve any intervention (experimental or otherwise) on the part of the investigator.8–12,31,81,97 A study with random allocation is inherently experimental or nonobservational. Observations are not just a haphazard collection of facts; in their own way, observational studies must apply the same rigor as experiments.61,95 Many important epidemiological, clinical, and microbiological studies are completely observational or have large observational components. See also case reports; clinical study.

OBSERVATIONAL EPIDEMIOLOGICAL STUDY Epidemiological study that does not involve any intervention (experimental or otherwise) on the part of the investigator; e.g., a population study in which changes in health status are studied in relation to changes in other characteristics. Most analytical epidemiological designs (e.g, case- control and cohort studies) are properly called observational because investigators observe without intervention other than to record, classify, count, and statistically analyze results.

OBSERVER BIAS Systematic difference between a true value and the value actually observed due to observer variation.

OBSERVER VARIATION (ERROR) Variation (or error) due to failure of the observer to measure or to identify a phenomenon accurately. Observer variation erodes sci- entific credibility whenever it appears. Sir Thomas Browne, in Pseudodoxia Epi- demica (1646), subtitled “Enquiries into very many commonly received tenents and presumed truths,” recognized several sources of error: “the common infirmity of human nature, the erroneous disposition of the people, misapprehension, fallacy or false deduction, credulity, obstinate adherence to authority, the belief in popular conceits, the endeavours of Satan.”

OBJECTIVE All observations are subject to variation. Discrepancies between repeated observations by the same observer and between different observers are to be expected; these can be diminished but probably never absolutely eliminated.

Variation may arise from several sources. The observer may miss an abnormality or think that one has been found where none is present; a measurement or a test may give incorrect results due to faulty technique or incorrect reading and recording of the results; or the observer may misinterpret the information. Two varieties of observer variation are interobserver variation (the amount observers vary from one another when reporting on the same material) and intraobserver variation (the amount one observer varies between observations in reporting more than once on the same material).

OCCAM’S RAZOR The philosophical principle of scientific parsimony (parsimony is used here in the sense of unwillingness to use unnecessary resources, frugality, austerity). An ancient principle often attributed the philosopher and Franciscan friar William of Occam (c.1285–1349), who said: Entia non sunt multiplicanda praeter necessitatem (i.e., assumptions to explain a phenomenon must not be multiplied beyond necessity). In The Grammar of Science (1892), Karl Pearson called this the most important canon in the whole field of logical thought. This maxim does not contradict the conclusion that multiple causes may operate in a system. The number of possible causes implicated depends upon the frame of reference of the investigator and the scope of the inquiry. The principle is also important in multivariate analysis (i.e., models should not be com- plicated beyond necessity).20,93,97 Its primacy in statistics has been challenged by modern computing developments, in which highly complex models, augmented by computer- intensive fitting and validation methods (such as cross-validation, shrinkage, and the bootstrap), can greatly outperform parsimonious methods developed in the precomputer era when many variables are available for the analysis. See also overfitting.

OCCUPATIONAL EPIDEMIOLOGY The study of the effects of workplace exposures on the frequency and distribution of diseases and injuries in the population. The application of epidemiological knowledge to populations of workers. Occupational epidemiological research studies workers under a variety of working conditions, including exposure to psychosocial, chemical, biological, or physical (e.g., noise, heat, radiation) agents to determine if the exposures cause adverse health outcomes.266,299

OCCUPATIONAL HEALTH The specialized practice of medicine, public health, and other health professions in an occupational setting or with a focus on the work determinants of health. Its aims are to promote health as well as to prevent occupationally related diseases and injuries and the impairments arising therefrom — and, when work-related injury or illness occurs, to treat these conditions. This field combines preventive and therapeutic health services and, as the numbers of persons in many occupations are known fairly precisely, provides good opportunities for epidemiological studies.300 Bernadino Ramazzini (1633–1714) is regarded as the “father of occupation medicine,” having published De Morbis Artificum (On the Diseases of Workers) in 1700.

OCCURRENCE In epidemiology, a general term describing the frequency of a disease or other attribute or event in a population; it does not distinguish between incidence and prevalence. The term is also used to allude to processes that lead to disease or that influence the incidence of disease.

ODA See Official Development Assistance.

ODDS The ratio of the probability of occurrence of an event to that of nonoccurrence, or the ratio of the probability that something is one way to the probability that it is another way. If 60% of smokers develop a chronic cough and 40% do not, the odds among smokers in favor of developing a cough are 60 to 40, or 1.5; this may be con- trasted with the probability or risk that smokers will develop a cough, which is 60 over 100 or 0.6. See also logit.

ODDS RATIO (Syn: cross-product ratio, relative odds) The ratio of two odds. The term odds is defined differently according to the situation under discussion. Consider the fol- lowing notation for the distribution of a binary exposure and a disease in a population or a sample:

The odds ratio (cross-product ratio) is ad/bc.


The exposure-odds ratio for a set of case-control or cross-sectional data is the ratio of the odds in favor of exposure among the cases (a/b) to the odds in favor of exposure among noncases (c/d). This reduces to ad/bc. In a case-control study with incident cases, unbiased subject selection, and a “rare” (uncommon) disease, ad/bc is an approximate estimate of the risk ratio; the accuracy of this approximation is proportional to the cumulative incidence of the disease. With incident cases, unbiased subject selection, and density sampling of controls, ad/bc is an estimate of the ratio of the person- time incidence rates (force of morbidity) in the exposed and unexposed (no rarity assumption is required for this).

The disease-odds ratio for a cohort or cross-sectional study is the ratio of the odds in favor of disease among the exposed (a/c) to the odds in favor of disease among the unexposed (b/d). This reduces to ad/bc and hence is equal to the exposure-odds ratio for the cohort or cross section.

The prevalence-odds ratio refers to an odds ratio derived cross-sectionally, as, for example, an odds ratio derived from studies of prevalent (rather than incident) cases.

The risk-odds ratio is the ratio of the odds in favor of getting disease if exposed to the odds in favor of getting disease if not exposed. The odds ratio derived from a cohort study is an estimate of this ratio. See also case-control study; rare-disease assumption.

OECD Organization for Economic Co-operation and Development (www.oecd.org).

OFFICE OF POPULATION CENSUSES AND SURVEYS (OPCS) (United Kingdom) Now the Office for National Statistics (www.gro.gov.uk).

OFFICIAL DEVELOPMENT ASSISTANCE (ODA) The term used by international development agencies for material and financial support provided by governments in highincome countries to those in low-income countries.

ONCOGENE A gene that can cause neoplastic transformation of a cell; oncogenes are slightly transformed equivalents of normal genes.

ONE-TAILED TEST A statistical test based on the assumption that only one direction of departure from the test hypothesis is of interest.

ONTOLOGY The study of what is the form and nature of reality and what can be known about it. The set of things whose existence is acknowledged by a particular theory or system of thought; it is in this sense that some experts speak of the ontology of a theory. The natural sciences embody implicit ontological schemes that cannot be wholly justi- fied on purely empirical grounds and can engender theoretical perplexities.301 See also epistemology.

OPCS See Office of Population Censuses and Surveys.

OPEN-ENDED QUESTION A question that allows respondents to answer in their own words rather than according to a predetermined set of possible responses, i.e., a closed-ended question. Open-ended questions can be difficult to code and classify for statistical analysis.

OPERATIONAL DEFINITION A definition embodying criteria used to identify and classify individual members of a set or concept to facilitate classification and counting.

OPERATIONAL RESEARCH The systematic study, by observation and experiment, of the working of a system (e.g., health services), with a view to improvement.

OPERATIONS RESEARCH

  1. The fitting of models to data or the designing of models
  2. Synonym for operational research

OPPORTUNISTIC INFECTION Infection with organism(s) that are normally innocuous (e.g., commensals in the human) but become pathogenic when the body’s immunological defenses are compromised, as in the acquired immunodeficiency syndrome (AIDS).

OPPORTUNITY COST The benefit foregone, or value of opportunities lost, by engaging resources in a service; usually quantified by considering the benefit that would accrue by investing the same resources in the best alternative manner. The concept of opportunity cost derives from the notion of scarcity of resources.

ORDINAL SCALE See measurement scale.

ORDINATE The distance of a point, P, from the horizontal or x axis of a graph, measured along the vertical or y axis. See also abscissa; graph; axis.

OUTBREAK An epidemic limited to localized increase in the incidence of a disease, e.g., in a village, town, or closed institution; upsurge is sometimes used as a euphemism for outbreak.

OUTCOME RESEARCH Research on outcomes of interventions. This is a large part of the work of clinical epidemiologists and epidemiologists involved in health services research.

OUTCOMES All the possible results that may stem from exposure to a causal factor or from preventive or therapeutic interventions. All identified changes in health status arising as a consequence of the handling of a health problem. See also causality; causation of disease, factors in; dependent variable.

OUTLIERS Observations differing so widely from the rest of the data as to lead one to suspect that a gross error may have been committed, or suggesting that these values come from a population different from that giving rise to the bulk of the observations.

OUTPUT The immediate result of professional or institutional health care activities, usually expressed as units of service (e.g., patient hospital days, outpatient visits, laboratory tests performed).

OVERADJUSTMENT Statistical adjustment by an excessive number of variables or parameters, uninformed by substantive knowledge (e.g., lacking coherence with bio- logical, clinical, epidemiological, or social knowledge). It can obscure a true effect or create an apparent effect when none exists. See also causal diagram; confounding bias; confounding, negative; overmatching.

OVERCROWDING This sociodemographic term is variously defined. The UK Office of Population Censuses and Surveys (OPCS) uses an index of overcrowding, defined as the number of persons in private households living at a density greater than one person per room as a proportion of all persons in private households.

OVERFITTING Fitting a statistical model with a large number of parameters relative to the amount of data available and the fitting method used. It contradicts the principle of scientific parsimony, or Occam’s razor. Chance error produced when large numbers of potential predictors are used to discriminate among a small number of outcome events and discrimination cannot be reproduced in a different sample. Genomic-based diagnostic research has been seen to be particularly prone to this type of error.192 Statistical methods such as cross-validation, empirical-bayes methods, and shrinkage can be used to address this problem without oversimplifying the model. See also cross validation; data dredging.

OVERMATCHING An undesirable result from matching comparison groups too closely or on too many variables. Several varieties can be distinguished:

  1. The matching procedure partially or completely obscures evidence of a true causal
    association between the independent and dependent variables. Overmatching may occur if the matching variable is involved in—or is closely connected with—the mechanism whereby the independent variable affects the dependent variable. The matching variable may be an intermediate cause in the causal chain under study, or it may be strongly affected by such an intermediate cause or a consequence of it.
  2. The matching procedure uses one or more unnecessary matching variables (e.g., variables that have no causal effect or influence on the dependent variable) and hence cannot confound the relationship between the independent and dependent variables but reduces precision.
  3. The matching process is unduly elaborate, involving the use of numerous matching variables and/or insisting on very close similarity with respect to specific matching variables. This leads to difficulty in finding suitable controls. See also matching.

OVERVIEW See meta–analysis; systematic review.

OVERWINTERING See vector-borne infection.

Close Menu
error: Content is protected !!
%d bloggers like this: