The Death of Statistical Significance: Deirdre McCloskey
17 Aug 2014 Leave a comment
in econometerics Tags: Deirdre McCloskey, empirical testing, methodology of econometrics, methodology of economics, the cult of statistical significance
Examples of Spurious Relationships
17 Jun 2014 2 Comments
in econometerics, economics Tags: data mining, spurious relationships
| Observed Spurious Relationship | Reason for Relationship (the Third Variable) |
| Amount of ice cream sold and deaths by drownings (Moore, 1993) | Season: Ice cream sales and drownings tend to be high during the warm months of the year |
| Ministers’ salaries and price of vodka | Area (i.e., urban or rural): In urban areas, prices and salaries tend to be higher. |
| Shoe size and reading performance for elementary school children | Age: Older children have larger shoe sizes and read better. |
| Number of doctors in region and number of people dying from disease | Population density: In highly dense areas, there are more doctors and more people die. |
| Number of doctors in region and number of people dying from disease | Population density: In highly dense areas, there are more police officers and more crimes. |
| Number of police officers and number of crimes (Glass & Hopkins, 1996) | Population density: In highly dense areas, there are more homicides and more churches. |
| Number of homicides and number of churches | Time: Both variables were increasing over time |
| Number of storks sighted and the population of Oldenburg, Germany, over a six-year period (Box, Hunter, & Hunter, 1978) | Time: Both were increasing during the 1970s. |
| Number of public libraries and the amount of drug use | Time: Both tend to increase over time. |
| Teachers’ salaries and the price of liquor (Moore and McCabe, 1993) | Time: Both tend to increase over time. |
| Tea drinking and lung cancer | Smoking: Tea drinkers have a lower risk only because they smoke less |
Halpern (2003) identified correlations that are often used to erroneously infer causality: illusory correlations, spurious correlations, and accidental correlations.
Illusory correlations are based on an individual’s preconceived notions or beliefs which lead one to look for associations between variables that confirm those.
Accidental correlations have no logical connection between them.
Finally, spurious correlations are correlations between two variables that are actually caused by a third variable.
The con in econometrics
07 May 2014 Leave a comment
in econometerics, history of economic thought Tags: data mining, publication bias
A mathematician, an economist and an econometrician apply for the same job.
The interviewer calls in the mathematician and asks
What do two plus two equal?
The mathematician replies
Four.
The interviewer asks
Four, exactly?
The mathematician looks at the interviewer incredulously and says
Yes, four, exactly.
Then the interviewer calls in the economist and asks the same question
What do two plus two equal?
The economist says
On average, four – give or take ten per cent, but on average, four.
Then the interviewer calls in the econometrician and poses the same question “What do two plus two equal?”
The econometrician gets up, locks the door, closes the shade, sits down next to the interviewer and says,
What do you want it to equal?
Three econometricians went out hunting, and came across a large deer.
The first econometrician fired, but missed, by a meter to the left.
The second econometrician fired, but also missed, by a meter to the right.
The third econometrician didn’t fire, but shouted in triumph,
We got it! We got it!
Utopia, you are standing in it! 
Recent Comments