Seemingly cliché thoughts about causality

Consider the following three questions:

(1) What is the effect of Event X on Outcome Y?

(2) Why do you do D1 instead of D2?

(3) Why does Event Z happen?

The first question asks the causal effect of X on Y. This is a very typical question in scientific studies. The answer could be a qualitative one, such as “positive effect”, “negative effect” or “no effect”, or a quantitative one, such as “an effect of 0.5”.

The second question can be seen as asking the purpose of a person doing D1 instead of D2. Of course, there are exceptions, for example, from a psychological point of view, a person may do D1 out of impulse instead of a well-considered purpose. But let us, for the sake of this dialogue, ignore this possibility.

The third one, however, is a question much more difficult to answer. It is almost impossible to answer, because instead of seeking the effect of a cause, it essentially asks the respondent to provide causes of an event. This does not mean that we shall not try to answer this question, but usually I do not see this type of question as a well-defined scientific question, because the plausible answers to this question are not only infinite in number, but also unknown in form.

These are cliché, but only seemingly cliché. People always forgot how difficult it is to answer the third question, and have gone to extremes by blaming the scientists for not providing a satisfactory answer.

Advertisements
Post a comment or leave a trackback: Trackback URL.

Comments

  • yxysamurai  On November 24, 2012 at 5:32 am

    “the plausible answers to this question are not only infinite in number, but also unknown in form.” So it is a nonparametric problem.

    • mumamme  On November 24, 2012 at 5:58 am

      Yes, except that the estimand is “the answer”, which we do not even know whether it would be in numeric form or other forms.

    • onlylonely  On November 24, 2012 at 3:24 pm

      I like the notion “nonparametric problem”! But notice that even nonparametric problem has a well-defined class of functions (elements) to consider from.

  • onlylonely  On November 24, 2012 at 3:24 pm

    mumamme has been very productive recently!

    • mumamme  On November 24, 2012 at 3:44 pm

      Haha mumamme’s productivity is highly unpredictable…

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: