[ad_1]
In a new study, researchers at Temple University used machine learning to better understand the human qualities most likely to predict financial success.
Although education and occupation are the best predictors, researchers found that a person's ability to delay instant gratification was also among the most important determinants of wealth.
The results, published in the journal Frontiers in Psychology, suggest that interventions to improve the control of gratification could have literal spin-offs in terms of higher incomes.
Many factors can affect how much a person will earn, including age, occupation, education, gender, ethnicity, and even size. Behavioral variables are also involved, such as the trait relating to the famous "marshmallow test". This original "time-delayed" study, or how valuable a person is to future rewards, has revealed that children's control was more likely to have higher wages later in life.
The lead author of the study, Dr. William Hampton, currently at the University of St. Gallen in Switzerland, said that more traditional methods of data analysis have failed to determine which of these factors are more important than others.
"All kinds of things predict income. We knew that this behavioral variable, discounting delays, was also predictive, but we were really curious about how it would compare to more sensible predictors such as education and age.
"Using machine learning, our study was the first to create a validated ranking by age, occupation, education, geographic location, gender, race,
The traditional approaches used by psychologists, such as correlations and regression, do not allow for a simultaneous comparison of different factors related to the wealth of an individual.
The new study collected a large amount of data – from over 2,500 different participants – and divided them into a set of training and a set of tests. The test set was set aside as the training set produced the model results. The researchers then returned to the set of tests to test the accuracy of their results.
Not surprisingly, the models indicated that occupation and education were the main predictors of high income, followed by location (determined by postal code) and sex, men earning more than women. Delaying the discounts was the next most important factor, more predictive than age, race, ethnicity or size.
"It was incredible because it allowed us to verify our findings and reproduce them, giving us greater confidence in their accuracy," Hampton said.
"This is particularly important given the recent wave of scientific discoveries that do not seem to be happening again. Using this method of machine learning could lead to more research that replicates, and we hope this will encourage the use of more sophisticated analytical approaches in general. "
The researchers warned that the data sample was intentionally limited to the United States, and it is possible that the ranking of variables that predict pay differs from one country to another. Hampton says that he is eager to study this analytical approach in a broader context.
"I would like to see a replica of this study in another culture. I would also be very interested in future studies to reduce discount times. There is a lot of debate about whether discounting deadlines is a stable feature or whether it is malleable – longitudinal studies could help to solve this problem.
Finally, Hampton advises parents, "If you want your child to grow up to earn a good salary, consider emphasizing the importance of delivering smaller, immediate rewards for the larger ones they have to wait."
Source: Borders
Related Articles
Source link
