PUB 540 Differentiate between association and causation using the causal guidelines
PUB 540 Differentiate between association and causation using the causal guidelines
PUB 540 Differentiate between association and causation using the causal guidelines
Association and causation describe epidemiological events, albeit to different degrees. Specifically, association implies that two variables may have a relationship. For instance, smoking may be associated with respiratory illnesses. In a way, the association points to the direction of a relationship without describing its defined attributes. Conversely, causation identifies specific factors that lead to a defined outcome. For example, a patient presenting a bruised leg will identify a biking accident as the cause. Both the cause and effect are apparent here, suggesting that one event will lead to another or an ultimate outcome. These descriptions illustrate association as a subset of causation, Health Knowledge (n.d.) noting that association does not imply causation. These differences are made apparent by the various criteria of causation. For instance, the first and second criteria require strength and consistency to illustrate how one event leads to another (Fedak et al., 2015). The most challenging criterion is criterion three, which necessitates specificity between variables. Accomplishing these requirements is hard because one effect can have several causes.
The criteria offer an excellent depiction of various forms of causal relationships. In the first case, the specificity criterion, as Fedak et al. (2015) defined, leads to the necessary and sufficient association. In this case, a single variable always leads to a defined result. For example, unprotected sex with a person suffering from an STI leads to the development of an STI. The second form is sufficient but not necessary, which explains a situation where a variable leads to an effect. However, other causes exist. An excellent example is how smoking can cause respiratory illnesses but is not the only causative agent. Thirdly, the necessary but insufficient form explains how one factor is among the elements that lead to an outcome. However, other factors are necessary. The not necessary or sufficient type explains a situation where a cause does not lead to a cause. Besides, the cause is not the only factor resulting in an outcome also. For example, a leg injury does not necessarily lead to cancer, nor is it the only factor that leads to cancer.
References
Fedak, K. M., Bernal, A., Capshaw, Z. A., & Gross, S. (2015). Applying the Bradford Hill criteria in the 21st century: how data integration has changed causal inference in molecular epidemiology. Emerging Themes in Epidemiology, 12(1). DOI: 10.1186/s12982-015-0037-4.
Health Knowledge. (n.d.). Causation in epidemiology: Association and causation. Retrieved April 25, 2022, from https://www.healthknowledge.org.uk/e-learning/epidemiology/practitioners/causation-epidemiology-association-causation.
Click here to ORDER an A++ paper from our Verified MASTERS and DOCTORATE WRITERS PUB 540 Differentiate between association and causation using the causal guidelines:
We all would like to know the cause of a disease, if we can determine the cause, then we have a better chance at knowing how to cure or slow it down. Kumar (2022) states that most causes are determined by observational study rather than experimental. There are several plausible explanations from observed associations that come from multiple sources. And, before cause and affect can be attributed to something the evidence from these multiple sources has to be strong enough that the conclusion isn’t merely a chance finding or by accident.
Friis & Sellers (2020) states that fully understanding the cause of a disease is not needed to treat it. The wheel model is a good example of showing the association of causality. The host is at the center, surrounded by an environment that consists of components that are biologic, social and physical. At the very center of the wheel is the genetic makeup of a person. We can substitute events that may represent the cause and association of disease when it comes to disease. This may be the easier of ways to illustrate the relationship between association and causality. The guides to this association are: plausibility, consistency, and temporality.
Reference
Kumar (2022, May 16) Causation in epidemiology: association and causation. Epidemiology for Practitioners. https://www.healthknowledge.org.uk/e-learning/epidemiology/practitioners/causation-epidemiology-association-causation
Friis, R. H., & Sellers, T. (2020). Epidemiology for public health practice (6th ed.). Jones & Bartlett Learning.
There is this saying that “association is not causation”. I never knew before public health classes what that really meant. Association isn’t always causation but it’s possible in various aspects of the four types of causation relationships. In public health, we need to study the exposed population as well as the unexposed within the same population to see if there is any statistical significance. There isn’t a way to create an experiment of how exposures, people and risk factors to get an outcome. Osborne and Shakir (2021) explained the reason why exposures may appear to be associated with an event due to confounding factors, bias, and and probability. We need to differiate between actual evidence or a signal of a causal or observed association. That is why we need to measure how statistically significant various risk factors are to an exposure.
References:
Osborne, V., & Shakir, S. (2021). What Is the Difference Between Observed Association and Causal Association, Signals and Evidence? Examples Related to COVID-19. Frontiers in pharmacology, 11, 569189. https://doi.org/10.3389/fphar.2020.569189
Understanding the similarities and differences between the terms association and causation is crucial when you examine the link between exposures and health outcomes. Association refers to a health outcome that is more likely to occur with indvuals with a particular exposure. In association knowing one variable provides insight on values of other variables. Simply, put is statistical relationship between two variables. Whereas causation is simply where the exposure causes the effect. In laments terms its where one variable affects the other.
According to Firis and Sellers there are 4 types of Casual Relationships:
1.) Necessary and sufficient: without the factor or variable the disease never develops. For example inhalation of crystalline silica dust is need in order to develop silicosis.
2.) Necessary but not sufficient: both factors are needed but alone they would not be able to cause the disease. An example is an individual must have HIV in order to develop AIDS.
3.) Sufficient but not necessary: the presence of one variable is not indicative to the presence of the other variable. For example lung cancer may develop from smoking but not all smokers develop lung cancer. Therefore, smoking is no a sufficient cause by itself.
4.) Neither sufficient nor necessary: factors are not essential in the development of the disease. An example is gonorrhea is not needed in order to cause pelvic inflammatory disease (PID). Simply someone can have gonorrhea and never develop PID.
References:
Friis, R. H., & Sellers, T. A. (2021). Epidemiology for public health practice (6th ed.). Jones and Bartlett Learning. ISBN-13: 9781284175431
Wakeford R. (2015). Association and causation in epidemiology – half a century since the publication of Bradford Hill’s interpretational guidance. Journal of the Royal Society of Medicine, 108(1), 4–6. https://doi.org/10.1177/0141076814562713
Hills Criteria of Causation is an outline that provides the minimal conditions that are needed to establish a causal relationship between two items. Original presented by Austin Bradford Hill, a statistician, was established to determine if there is a causal link between risk factors and a disease. These criteria that is use today form the basis of modern epidemiological research.
1. Temporal relationships
2. Strength
3. Dose-Response Relationship
4. Consistency
5. Plausibility
6. Consideration of Alternate Explanations
7. Experiment
8. Specificity
9. Coherence
In epidemiology the goal is to assess the cause in diseases and studies are completed by observation rather than experimental . In Casual guidelines the following criteria are used to guide casual association: Parascandola & Weed Suggest (2022) “ Plausibility (reasonable pathway to link outcome to exposure) Consistency (same results if repeat in different time, place person) Temporality (exposure precedes outcome) Strength (with or without a dose response relationship) Specificity (causal factor relates only to the outcome in question – not often) Change in risk factor (i.e. incidence drops if risk factor removed)” . Association and causation have some differences , in association it measures the relationship between the time of exposure and disease within groups . In causation the focus is on the production effect and relation to the cause effect. Some epidemiologist relay on experimental sciences which require that cause be defined to described and active agents producing change. Perhaps , one of the most difficult casual guidelines to establish would be Consistency, as with many things in general with consistency, requires coloration and correspondence. Afterall, accomplishing consistency allows for a closer contact between observational studies and inferences about actions based on those studies.
Firis & Sellers (2021) suggest “In Causal relationships there are 4 types “ Which are listed below:
Necessary and Sufficient: Both A & B are interdependent variables because A is needed to cause B. An example : uncontrolled diabetes causes kidney failure.
Necessary, but not sufficient: A may or may not be the direct cause of B because there are other factors to look at. An example : An individual with HIV must be infected with the virus before they can develop AIDS.
Sufficient, but not necessary: A is required to be present with B but B is not required to be present with A. A is the causation of B but opposite for vice versa. B is not a causation for A. An example : Smoking cigarettes can lead to cancer development, but may not cause cancer, other factors can contribute to the cancer rather then smoking alone.
Neither sufficient or necessary: A may or may not be present with B to create causation. An example : Having a past medical history of Gonorrhea is neither necessary or sufficient to cause PID . An individual can have PID without ever being diagnose with Gonorrhea.
References
Parascandola, M &Weed,D( 2022). Causation in Epidemiology. Rederived from https://jech.bmj.com/content/55/12/905
Rehkopf, D. H., Glymour, M. M., & Osypuk, T. L. (2016). The Consistency Assumption for Causal Inference in Social Epidemiology. Retrieved from epidemiology reports, 3(1), 63–71. https://doi.org/10.1007/s40471-016-0069-5
Friis, R. H., & Sellers, T. A. (2021). Epidemiology for public health practice (6th ed.). Jones and Bartlett Learning. ISBN-13: 9781284175431