Andrey Kamenov, Ph.D. Probability and Statistics
One of the most famous attempts to measure “quality of life” was made by the Economist in 2005. The journal’s internal Intelligence Unit introduced the eponymous index, which was designed based on surveys linking different objective measures to general life satisfaction. Later, the methodology was revised and the measure itself was renamed to the “Where-to-be-born index”.
The U.S. is frequently ranked somewhat lower than one may expect — usually somewhere in the 10s. Anyway, since most of our readers are probably not considering moving to Switzerland in the near future, today we will focus on comparing different parts of the U.S. using the same methodology.
One of the primary factors contributing to the final value is climate, which is reflected by two variables in the regression. First, we consider the average deviation of maximum and minimum monthly temperatures from 14 degrees Celsius (57.2 Fahrenheit). The idea is that places where extreme (too cold or too hot) weather is frequently observed might not be very comfortable to live in. While the idea itself seems appealing, the temperature may seem a bit low at first. But remember, this number is the average temperature, so it includes nightly temperatures and colder months.
The second variable deals with precipitation — the average number of months seeing less than 30mm of rainfall. There are many ways droughts negatively impact well-being. First, the risk of forest fires (a danger especially important to California residents) and related hazards, such as landslides and poor water quality, greatly increases. Droughts can also lead to a reduced drinking water supply and worsened air quality.
Unfortunately, the Economist’s study doesn’t reveal the exact weights assigned to each factor. Granted, the standard deviation in both variables we mentioned is almost exactly equal. Thus, we will use a 1:1 ratio to construct an aggregate measure, reflecting the total impact of climate on quality of life.
Here’s the map showing the distributions for both of the variables, as well as their sum for each county. As you can see, several states (like California or Texas) have wildly different ratings observed in different areas, so we use counties as the geographical unit here.
The tooltip shows the best and the worst counties for each state, as well as all three exact values for each county when zoomed.
Source(s):
About Andrey Kamenov
Andrey Kamenov, Ph.D. Probability and Statistics
Andrey Kamenov is a data scientist working for Advameg Inc. His background includes teaching statistics, stochastic processes and financial mathematics in Moscow State University and working for a hedge fund. His academic interests range from statistical data analysis to optimal stopping theory. Andrey also enjoys his hobbies of photography, reading and powerlifting.
Other posts by Andrey Kamenov: