Difference between revisions of "Causal association"
Jump to navigation
Jump to search
(Added source information for text) |
DavidB4-bot (talk | contribs) (→top: HTTP --> HTTPS #3, replaced: http://www.cdc.gov → https://www.cdc.gov) |
||
| (8 intermediate revisions by 5 users not shown) | |||
| Line 1: | Line 1: | ||
| − | Causal association is the presence or absence of a variable (e.g. smoking) is responsible for an increase or decrease in another variable (e.g. cancer). A change in exposure leads to a change in the outcome of interest.<ref> | + | '''Causal association''' is an association between variables in which the presence or absence of a variable (e.g. [[smoking]]) is [[cause and effect|responsible]] for an increase or decrease in another variable (e.g. [[cancer]]). A change in exposure leads to a change in the outcome of interest.<ref>https://www.cdc.gov/vaccines/about/terms/glossary.htm#c</ref> |
| + | |||
| + | It is important to bear in mind that [[correlation is not causation]], or in other words that the change in one variable is not automatically the cause of the change in the other variable. There could be other relationships at work instead, e.g., a common underlying cause for both, a reversal of cause and effect, or coincidence. It is also important not to commit the [[Logical fallacy#Post hoc ergo propter hoc|''post hoc'' fallacy]]. | ||
| + | |||
| + | ==See also== | ||
| + | *[[Cause and effect]] | ||
==References== | ==References== | ||
| Line 5: | Line 10: | ||
[[Category:Medicine]] | [[Category:Medicine]] | ||
| + | [[Category:Statistics]] | ||
Latest revision as of 06:27, April 9, 2019
Causal association is an association between variables in which the presence or absence of a variable (e.g. smoking) is responsible for an increase or decrease in another variable (e.g. cancer). A change in exposure leads to a change in the outcome of interest.[1]
It is important to bear in mind that correlation is not causation, or in other words that the change in one variable is not automatically the cause of the change in the other variable. There could be other relationships at work instead, e.g., a common underlying cause for both, a reversal of cause and effect, or coincidence. It is also important not to commit the post hoc fallacy.