Home
Browse
Create
Search
Log in
Sign up
Upgrade to remove ads
Only $2.99/month
Chapter 5-1
STUDY
Flashcards
Learn
Write
Spell
Test
PLAY
Match
Gravity
Association and Causality
Terms in this set (42)
Variable
- Any quantity that varies
- Any attribute, phenomenon, or event that can have different values
Association
Refers to a linkage between or among variables; variables that are associated with one another can be positively or negatively related
Positive Association
Means that if the value of one variable increases, the value of the other variable increases as well
Negative Association
Means that if the value of one variable increases, the value of the other variable decreases
Pearson Correlation Coefficient
- Measure of association used with continuous variables
- Varies from -1 to 0 to +1
- The value 0 means no association
- As r approaches either -1 or +1, the association between two variables becomes stronger
- When r is negative, the association is inverse
Continuous Variable
- A type of variable that can have an infinite number of values within a specified range
- Ex: height and weight
Types of Associations
- Some possible relationships between variable X
(exposure factor) and variable Y (outcome):
- No association (X is unrelated to Y)
- Associated (X is related to Y):
- Noncausally (X does not cause Y)
- Causally (X causes Y)
Hypothetical Examples of Associations
- Sugar consumption (exposure variable) and type 2 diabetes (health outcome)
- Possible associations between exposure and outcome:
- No association (independence) between dietary sugar consumption and occurrence of diabetes
- Positive association between dietary sugar and diabetes:
- Noncausal: A third factor may be related to both preference for dietary sugar and occurrence of diabetes.
- Causal: High dietary sugar intake "causes" diabetes.
- Negative association between dietary sugar consumption and diabetes
Scatter Plot
- A scatter diagram plots two variables, one on the X axis (horizontal) and one on the Y axis (vertical)
- The measurements for each case are plotted as a single data point
- The closer the points lie with respect to the straight line of best fit through them (called the regression line), the stronger the association between variable X and variable Y
Examples of Scatter PlotsX Versus Y
- Perfect direct linear association
- Perfect inverse linear association
- No association
- Positive relationship (e.g., r = 0.7)
- Curvilinear (inverted U-shaped)
Concepts of Association
- Dose-response curve
- Multimodal curve
- Epidemic curve
Dose-Response Curve
- The plot of a dose-response relationship, which is a type of correlative association between an exposure and an effect
- Ex: dose-response relationship between the number of cigarettes smoked daily and mortality from lung cancer
Threshold
Threshold refers to the lowest dose at which a particular response occurs
Multimodal Curve
- One that has several peaks in the frequency of a condition
- Possible reasons for multimodal distributions of health outcomes:
- Changes in lifestyle and immune status of the host
- Latency effects (Latency refers to the time period between initial exposure and a measurable response
Mode
Defined as the category in a frequency distribution that has the highest frequency of cases
Epidemic Curve
- A graphic plotting of the distribution of cases by time of onset
- Aids in identifying the cause of a disease outbreak
Contingency Table
- Another method for demonstrating associations
- A type of table that tabulates data according to two dimensions
Column and row totals are known as marginal totals
- In a generic contingency table:
- A = exposure is present and disease is present
- B = exposure is present and disease is absent
- C =exposure is absent and disease is present
- D = exposure is absent and disease is absent
Epidemiologic Research Strategies
- Epidemiologists ask whether a particular exposure is causally associated with a given outcome
- Investigators:
- Examine existing facts and hypotheses
- Formulate a new or more specific hypothesis
- Obtain additional facts to test the acceptability of the new hypothesis
- Hypothesis
- Method of difference
- Method of concomitant variation
- Operationalization
Hypothesis
- Defined as any conjecture cast in a form that will allow it to be tested and refuted
- One of the most common types is the null hypothesis
- An example would be to hypothesize that there is no difference between smokers and nonsmokers in the occurrence of lung cancer
Where Do Hypotheses Come From
- Method of difference
- Method of concomitant variation
Method of Difference
- All of the factors in two or more domains are the same except for a single factor, which is hypothesized to be the "cause" of a disease
- Ex: differences in coronary heart disease rates between sedentary and nonsedentary workers
Method of Concomitant Variation
- A type of association in which the frequency of an outcome increases with the frequency of exposure to a factor, the hypothesized cause of the outcome
- Ex: Dose-response relationship between number of cigarettes smoked and mortality from lung cancer
Operationalization
- Refers to the process of defining measurement procedures for the variables used in a study
- Ex: In a study of the association between tobacco use and lung disease, the variables might be the number of cigarettes smoked and the occurrence of asthma
Causality in Epidemiologic Studies
- One of the central concerns of epidemiology is to be able to assert that a causal association exists between an exposure factor and disease in the host
- Ex: Is there a causal relationship between smoking and lung cancer?
- Causality is a complex issue
- Several criteria of causality must be satisfied in order to assert that a causal association exists
- The assertion of causality is similar to a trial in court
- Smoking and Health, 1964 - Surgeon General's report:
presented several criteria for evaluation of a causal association
A.B. Hill's Criteria of Causality
- An expanded list of causal criteria
- Strength
- Consistency
- Specificity
- Temporality
- Biological gradient
- Plausibility
- Coherence
- Analogy
Strength
Strong associations give support to a causal relationship between factor and disease
Consistency
An association has been observed repeatedly
Specificity
Association is constrained to a particular disease-exposure relationship
Temporality
The cause must be observed before the effect
Biological Gradient
Also known as a dose-response curve; shows a linear trend in the association between exposure and disease
Plausibility
The association must be biologically plausible from the standpoint of contemporary biological knowledge
Coherence
The cause-and-effect interpretation of our data should not seriously conflict with the generally known facts of the natural history and biology of the disease
Analogy
- Relates to the correspondence between known associations and one that is being evaluated for causality
- Ex: thalidomide and rubella
Multifactorial (Multiple) Causality
- Many types of causal relationships that are involved with the etiology of diseases involve more than one causal factor
- Examples of multiple causal factors in the etiology of many chronic diseases include:
Specific exposures (e.g., smoking), family history, lifestyle characteristics, environmental influences
- Two models of multifactorial causality are the web of causation and the epidemiologic triangle
Defining the Role of Chance in Associations
Epidemiologists employ statistical procedures to assess the degree to which chance may have accounted for observed associations
Field of Inferential Statistics
Inference is the process of passing from observations and axioms to generalizations
Sample Versus Population
- Parent population
- Sample: a subset of the population
- A goal of inference is to draw conclusions about a parent population from sample-based data
Terminology of Inference
- Point estimate
- Confidence interval estimate
- Statistical power
Point Estimate
- The value for the population is referred to as a parameter and the corresponding value for the sample is a statistic
- A point estimate is a single value (sample-based) chosen to represent the population parameter
Confidence Interval Estimate
- A range of values that with a certain degree of probability contain the population parameter
- Used as an alternative to point estimate
Power
- In statistics, power is "...the ability of a study to demonstrate an association if one exists."
- Related to sample size and effect size
- Effect size is related to the strength of the association that has been observed
Conclusion
- The issue of causality in epidemiology is complex and involves the application of several causal criteria
- The epidemiologist must rule out chance, which may account for observed associations
YOU MIGHT ALSO LIKE...
Chapter 5
37 terms
Ch 5 Terms
31 terms
Chapter 5: Key Terms
37 terms
Association and Casuality ( CH 5)
28 terms
OTHER SETS BY THIS CREATOR
Chapter 10
38 terms
Chapter 7 0.2
48 terms
Chapter 6-1
41 terms
Epidemiologic Data Sources and Meaures o…
34 terms