See previous comments when this was posted yesterday.
https://news.ycombinator.com/item?id=41111236 (data)
https://news.ycombinator.com/item?id=41111416 (conclusions)
> Dr. Yonat Zwebner, Arison School of Business, Reichman University says
First, this isn't even a scientist who makes these conclusions, which explains why there's no scientific method. There needs to be a null hypothesis which is ruled out statistically. Why not have survey participants try to guess the name from a pool of random names drawn from within the same generation and socio-economic group, and then see if they do any better than chance.
Second, even if the data were trustworthy, the obvious explanation here is that the popularity of certain names changes over time, and those distributions correlate with social class. A middle-class woman born in 1980 will probably have one of the names typically given to middle-class girls in 1980. Survey participants are, consciously or unconsciously, weighing the probability of a name, given these factors. Facial attributes simply have nothing to do with it. The idea that facial attributes change to suit a name is preposterous, given the number of other, much simpler explanations.
But may be, some names really provoke a change in style and appearance. In the country I living in, the name Kevin is sometimes used to call people slow-brainer. So if you're a Kevin and if you're in mid school, then the possibilities are high, that you'll be laughed by others. With such young personalities, it's devastating for the self esteem. So this people find their social refuge within a similar group of people. And usually, a group of people also have similar clothes and appearance in common.
So, there's sure a correlation . The question is, how to do a study on that
"For Study 1: Adult Perceivers, a power analysis based on previous effects (5) indicated a desired sample size of 120 participants. We had 117 students (62% women, age range: 18 to 30 y, M 24.7, SD 2.1; participants were recruited by the online university panel...All had a similar demographic background...We discarded two data points (out of 1,872)"