10.23.2024 Bahar Gidwani
By Bahar Gidwani
When people start using our ratings of corporate social responsibility and sustainability, they often ask us, “What does a difference in scores mean and how much chance is there that the difference is wrong?”
Our scores range from a low of zero to a high of 100, in one-point steps. Each company’s score depends on the personal preference profile of the person who is viewing it. A person who values community relationships above governance will get different scores from one who values environmental performance overall.
If you are a regular user of our site, you should register and build your own personal profile. Then, you can click on a link at the bottom of your profile page and see how your personal profile affects the distribution of company ratings. The graph below shows the distribution for the average profile for the CSRHUB community. You can see that the peak in the overall ratings is at around 50 (actually at 49); the minimum score is 15, and the maximum score is 74.
As you change your profile, it is possible that your curve will have a different peak, maximum and/or minimum. However, the general shape of the curve should remain the same. The formula that best fits this curve is called a Beta distribution and is somewhat different in shape from the better-known Normal distribution. The top of a beta peak is flatter than the peak for a normal distribution and the tail tends to be shorter. For those who care, our curve closely fits a beta formula of alpha = 23.3 and beta = 24.2, with a lower bound of zero and an upper bound of 100. The Chi Squared for the errors between our actual curve and this formula is 43.7, which strongly suggests an excellent fit to the beta shape.
The distribution of ratings within a particular country, industry, or among the companies rated by a data source may look quite different from the overall distribution. For instance, it is common for an industry to have several very high rated companies (leaders on CSR), a large but dispersed group of medium-rated companies (followers), and then a long tail of weaker performers (laggards). This curve from the 74 companies we rate in the Electronic Equipment industry illustrates this pattern.
Because we are dealing with a curve, rather than a straight line, a five point difference in overall score matters less at the edges than in the middle. For instance, a company that scores 60 in the CSRHUB community profile is at the 93rd percentile (7 percent from the top). One that scores 55 is at the 79th percentile, or 14 percent worse. On the other hand, a company with a score of 50 is at the 48th percentile, or 31 percent worse than the company that scored a 55.
As a result, the answer to the question, “What does a score difference mean?” is “it depends.” The exact importance is influenced by your personal profile settings, the industry or region you are examining, and which part of the ratings curve you are looking at.
If you have survived this quick primer in non-linear scoring, you are ready to tackle the second part of the question we started with—how accurate are our overall ratings? We will discuss this in our next post.
Bahar Gidwani
is a Cofounder and CEO of CSRHUB. Formerly, he was the CEO of New York-based Index Stock Imagery, Inc, from 1991 through its sale in 2006. He has built and run large technology-based businesses and has experience building a multi-million visitor Web site. Bahar holds a CFA, was a partner at Kidder, Peabody & Co., and worked at McKinsey & Co. Bahar has consulted to both large companies such as Citibank, GE, and Acxiom and a number of smaller software and Web-based companies. He has an MBA (Baker Scholar) from Harvard Business School and a BS in Astronomy and Physics (magna cum laude) from Amherst College. Bahar races sailboats, plays competitive bridge, and is based in New York City.
