Inference #2 – Cause

Note – this series started 9/26/2008 (or 350 B.C.E., in as much as it is a continuation of work started then).
The first of the six inferences was covered last week, when we started with the strongest inference – Inference of Example. It is the strongest because examples are in the real world. The next strongest inference is this week’s topic – Inference of Cause (or causal inference).

Causal inference indicates that one event has influence over another. It also indicated that the influence cannot be directly observed.
Causal inferences are used to:
- Predict events (Reducing the number of nuclear weapons causes a reduction in the likelihood that they will be used)
- Relate means to ends (Studying causes good grades)
- Explain paradoxes (What causes a candidate to get twice as many electoral votes as another if they only get 2% more of the popular vote?)
- Assign responsibility (What causes the proposition we thought would win to actually lose?)

For the sake of this article, I am not going to include the statistical methods that are available to explain causation, except in simple terms. They are powerful, and you should know them and use them if they are appropriate for the case with which you are concerned. There are many sources for that information and not many for the following, so I will devote this space to the lesser-known ways.

Let’s start with a work example: You claim “Well, I can expect to start having trouble with Sharon. “ Your co-worker asks “Why do you say that?” You answer “I just criticized her work.” And the co-worker asks “So why is that a problem?” and you say “Criticizing people’s work causes them to start trouble for you.”

In the case I created above, my claim (I expect trouble with Sharon) is supported by evidence (my criticism of her work) and connected via a causal inference (criticism of co-workers causes trouble). I am using it to predict future events. If my audience believes that criticism of co-workers usually causes trouble, they will accept my claim; if they don’t, they won’t accept the claim and I will have to convince them. Let’s explore how causal inferences should be evaluated, both before it is made and after. What are the reasonable evaluations for causal inferences like the following:
- Stock prices dropped because America is no longer an economic power.
- The river overran its banks due to the rain.
- Low birth weight reduces the likelihood of college admission.

Statistical approaches would have us experiment. We would hold all factors in two samples the same, and then vary one of them. If the output varies, then the factor we varied could be said to cause the variance. This is a method popularized by John Stuart Mills and is a great approach in a laboratory, but becomes impractical as we start to look at many business issues.

Rhetorical approaches would have us (in a first step) identify how some factor COULD be the cause and, in a second step, have us explain why it SHOULD BE CONSIDERED the cause. In the law, the first step is used to show means and opportunity, and the second step to show motive.

In testing casual inferences, it is critical to determine that one thing indeed influences another, and isn’t merely being attributed. For instance, the stock price question that I raised above is too complex to be so simply explained away. Stock prices rise and fall based on many things, and there most certainly are many factors that can cause price fluctuations. In fact, a strong argument can be made that stock prices frequently drop after a period when there has been too much speculation and the market needs to “normalize” in order to get healthy. So if you plan on attributing lowered stock prices to a single cause, then you need to prepare more than a single reason and bring lots of evidence.

One must evaluate whether there are multiple causes and not just one. For instance, while it is true that rain can cause a river to overrun its banks, so can a dam. If a car drove off the road and into the river on a rainy night, it may not be the rain that caused the river to overrun its banks. One must also remember that one cause can have multiple effects, for instance turning off the water main in order to stop a pipe from leaking and spilling water on the floor. It will work because there is certainly a causal relationship between the presence of water in the leaky pipe and water on the floor, but there are other effects that shutting the water main has that are perhaps unwanted.

One must evaluate whether there are common causes underlying the supposed cause and effect relationship. For example, I recently read that American babies with low birth weight tend not to grow up to go to college. Reading this, I immediately thought that a common cause underlying both conditions (low birth weight and failure to go to college) is poverty. In checking, I found that the author had misinterpreted some statistics and “bent them” to try to show why it is important for mother’s to try to achieve higher birth weights!

One must evaluate whether one is confusing temporality with causality. In other words, just because something happens BEFORE something else, doesn’t mean it is the CAUSE of it. Just because I correct someone’s work and later I start having trouble with them on the job doesn’t mean that the two events are causally related. It could be that, once I correct them, my attitude changes about them and they pick up my attitude. Or that the reason I am correcting them is that they are overwhelmed by the work and they would rather work somewhere else and eventually this starts to manifest as “trouble” to me.

There are many fallacies associated with causal inference. Here are two:
- The Post Hoc fallacy – (if something occurs BEFORE an event, then it means it CAUSED the event.) This fallacious thinking is used all the time. When you hear it, question it.
- Appeal from Ignorance – (Well, if the rain DIDN’T cause the river to overrun its banks, then what did?) This appeal is meant to put the listener in a position of either offering an alternate explanation or accepting the one offered. Remember there is a third choice – that something else caused the event and you don’t know what it is. You needn’t ever buckle to the appeal from ignorance.

Insist on great business results! Go to Pathfinder Communication