Three Levels of Causation
When seeking to establish a causal relationship, researchers distinguish among three levels of causation: Absolute Causality, Conditional Causality, and Contributory Causality.
Absolute Causality: Absolute causality means that the cause is necessary and sufficient to bring about the effect. We typically find absolute causation in the physical sciences. Here is an example of absolute causality. When temperatures fall below 32º F, unsalted water begins to freeze. In the social sciences—marketing research, of course, is a social science—it is very unlikely that absolute causality can be established. A researcher might find a strong causal relationship between reducing retail price and increasing retail sales. But, if a researcher finds just one incidence of a price reduction that does not result in increased retail sales, an inference of absolute causality cannot be supported. So while marketing researchers cannot establish absolute causality, they still seek to prove less strenuous versions of causality: Conditional and Contributory Causality.
Conditional Causality: Conditional causality means that a cause is necessary, but not sufficient to bring about an effect. Here is an example of conditional causality from biology: Engaging in sexual intercourse without contraceptives is a necessary but not sufficient cause of pregnancy. In addition to unprotected sexual intercourse other variables must be present: Both partners must be fertile and the sex act must occur while the woman is ovulating. It is very difficult to establish conditional causality. Let's say that the researcher is studying the links between advertising spending and retail sales. It is nearly impossible to establish a conditional causal link between increased advertising spending and increased retail sales. While there is probably a strong correlation between advertising spending levels and retail sales, as a former advertising executive I can attest that there are occasions when increased advertising spending may result in reduced retail sales. And, there are times when sales increase when a brand lacks advertising support. We could not, therefore, demonstrate conditional causality because advertising is not a necessary condition for retail sales.
Contributory Causality: Contributory causality is the weakest form of causality. Contributory causality is when the cause is neither necessary nor sufficient to bring about the effect. With contributory causality a change in the cause is associated with a change in the effect. Contributory causality does not require all variables that experience the cause to demonstrate the effect. The cause, therefore, is neither necessary nor sufficient, but it does contribute to the effect.[i] With contributory causality lurking variables that
cause both the independent and dependent variables must be ruled out. Causal marketing research can establish contributory causality. Researchers could probably establish a contributory causal link between advertising spending and retail sales.
With causal statements, the researchers must avoid a post hoc fallacy. A post hoc fallacy is based on the Latin expression
post hoc, ergo propter hoc, after this, therefore because of this. This fallacy is based on the hasty conclusions that there is a causal relationship between two variables merely because the presumed cause precedes the effect. Here is an example of a post hoc fallacy. Maria is 70-years-old and drinks a glass of Tropicana Orange Juice everyday at breakfast. Maria does not have cancer. Therefore, drinking Tropicana Orange Juice is an effective part of a cancer prevention regime.
[i] http://www.ncbi.nlm.nih.gov/pubmed/450828
toc | return to top | previous page | next page
Date last modified: August 22, 2015.
Created by Edward Volchok, PhD
