However, later, controlled studies showed that there is no such connection between them. ► According to a 1991 observational study, hormone replacement therapy, apart from treating menopause symptoms, had a potential to reduce risks of a coronary heart disease. If obesity is a risk factor of type 2 diabetes, then type 2 diabetes is a risk factor of obesity. We might confuse the “risk factor” in the sentence as a “cause” however, it is means that both the factors are correlated to each other. For example, obesity is a risk factor for type 2 diabetes. The correlation between the two variables may be a pure coincidence. ► In some other cases, there might be no connection between the two things. This third factor is called confounding factor or confounding variable. That is the reason he forgot to take his shoes off, and that is the reason he had a headache the next morning.
Every time that person goes to bed with his shoes on, he might be drunk. However, there might be a third hidden factor that he chose to ignore. As that person had slept wearing shoes before experiencing a headache the next morning, he might believe that wearing shoes to his bed caused the headache. It may happen that both the things happened simultaneously more than once in a person’s life. Let us take the previously discussed example of sleeping with your shoes on and having a headache the next morning. ► In some cases, there might be a third factor apart from the original two variables that contributes in the effect. The causal relationship can go in a circular fashion where A is the cause of B and B is the cause of A. A and B both might be the consequences of some unknown factor. Secondly, B can be the cause of A in a reverse relationship. EAT ENOUGH CHOCOLATE AND YOULL WIN A NOBEL. If we consider “A” and “B” as two variables, then first and foremost, there can be a direct relationship where A causes B to occur. It’s a scientist’s mantra: Correlation does not imply causation. ► There are several possibilities of a causation vs. Researchers test to calculate correlation between two variables and the true causal relationship between them.
Even though with the logical fallacies, the way to find the cause behind its effect is false, the result itself is usually not. The phrase correlation does not imply causation is used to emphasize the fact that if there is a correlation between two things, that does not imply that one is necessarily the cause of the other. In addition, if a particular thing occurred after another, it is an effect of the previous one. Those phrases are cum hoc ergo propter hoc, meaning “with this, therefore because of this” and post hoc ergo propter hoc, meaning “after this, therefore because of this.” These are logical fallacies that convince us that if two things are happening simultaneously, there is a causal relationship between them. There are two Latin phrases that are used to support this type of cause-and-effect relation between two things. The problem of deducing causal information from correlations in observational data is a substantial research area, the simple maxim that correlation does not imply causation having been superseded by methods such as those set out in earlier work (Pearl, 2000, Spirtes et al., 2001), and in shorter form (Pearl, 2009).
0 kommentar(er)
