Chapter 9 - Causality

causal inference

A conclusion about the presence of a health-related state or event and reasons for its existence

method of agreement

A single factor is common to a number of circumstances where the disease occurs at a high frequency.

biological plausibility

a causal association is consistent with existing medical knowledge

analogy

a comparison between two things with similarities for the purpose of explanation or clarification

experimental evidence

a criterion in causal inference wherein an experimental study design has the greatest potential for supporting cause-effect relationships because of control over measurements and monitoring, the ability to establish a time sequence of events, and the ability to control for bias by employing an appropriate sample, random assignment, and blinding

coherence

a criterion in causal inference wherein there is consistency with known epidemiologic patterns of disease

decision tree

a decision tool that uses a graph or model of decisions and their possible consequences

strength of association

a factor considered in causal inference; a strong association provides greater evidence of there being a casual association because it is more likely to be real (valid)

chance

a factor to consider when establishing the validity of a statistical association; an association may appear to exist merely because of the luck of the draw

p value

a function of sample data (a statistic) that helps determine the statistical significance of a result

confidence interval

a range of reasonable values in which a population parameter lies, based on a random sample from the population

sample

a subset of items that have been selected from the population

hypothesis

a suggested explanation for an observed phenomenon or a reasoned proposal predicting a possible causal association among multiple phenomena

at-risk behavior

an activity performed by a person that puts him or her at greater risk of developing a health-related state or event

specificity

an exposure is associated with only one disease, or the disease is associated with only one exposure

systematic error

an incorrect result because of bias or a source of variation distort that alters the result in one direction

random error

an incorrect result because of chance; sources of variation that are equally likely to incorrectly alter the results in one direction or the other

biologic gradient

an increasing risk of disease occurs with greater exposure

statistical inference

an inference or conclusion made about a population based on sampled data

risk factor

an inherent human characteristic, a behavior, or an environmental exposure that is associated with an increased probability of experiencing a health-related state or event

confounding

an outside influence (extraneous factor) that causes a misleading impression of the association between an exposure and outcome variable

precipitating factors

factors essential to the development of diseases, conditions, injuries, disabilities, and death

enabling factors

factors or conditions that allow or assist the health-related state or event to begin and run its course

reinforcing factors

factors that support the production and transmission of disease or conditions, or that support and improve a population's health status and help control diseases and conditions

Koch's postulates

four criteria formulated by Robert Koch and Friedrich Loeffler in 1884 and refined and published by Koch in 1890 to establish a causal relationship between a causative microbe and a disease

web of causation

graphic, pictorial, or paradigm representations of complex sets of events or conditions caused by an array of activities connected to a common core or common experience or event

direct causal association

has no intermediate factor and is more easily understood

indirect causal association

involves one or more intervening factors and is often much more complicated and difficult to understand than a direct causal association

method of difference

involves recognizing that if the frequency of a disease differs between two locations, it may be because a particular factor varies between those two places

inductive reasoning

moving from specific observations to broader generalizations and theories

multifactorial etiology

of or arising from many factors

fishbone diagram

provides a visual display of all possible causes that could potentially contribute to the disease, disorder, or condition under study

bias

the deviation of the results from the truth; can explain an observed association between exposure and outcome variables that is not real

method of concomitant variation

the frequency or strength of a risk factor varies in proportion to the frequency of the disease or condition

power

the power of a statistical test measures the test's ability to reject the null hypothesis when it is actually false; directly associated with sample size; equal to 1-beta

consistency of association

the relationship between an exposure and outcome variable is replicated by different investigators in different settings with different methods

etiology

the science and study of the causes of disease and their modes of operation

temporality

the time sequence of events that provide insight into causal processes

predisposing factors

those existing factors or conditions that produce a susceptibility or disposition in a host to a disease or condition without actually causing it; precede the direct cause

type II error

when the null hypothesis (H₀) is not rejected, but H₀ is false

type I error

when the null hypothesis (H₀) is rejected, but H₀ is true