What is wrong with standard deviation?

**lzhang** Tue Jul 03, 2007 12:11 am

What is wrong with standard deviation?
It sounds quite bizarre that some so-called value investors are quite sensitive to the term of standard deviation (SD), as if it is a monster. One ridicule argument is that because EMH uses standard deviation, we should not use it. My goodness, they do not think the mean is also used by EMH professors!

Actually, mean, standard deviation, etc., are just pure statistical estimates, which have nothing to do with EMH. If I am a physicist and I have measured that a value is x+/-y, where x is the mean and y is the standard deviation. What the heck my measurement has anything to do with EMH, just because I use SD?

The argument that because EMH uses it we should not use it is very laughable. EMH uses the mean as well! Just because professors of EMH have lunches, are you going to stop eating your lunches?

**blast_investor** Tue Jul 03, 2007 1:04 am

Hi lzhang,

This forum is great place to dicuss this issue.

Standard deviation simply measure volatility, not risk.

Granted, less volatile investment is always better than non-volatile. However, for investors, risk control is more important. If a investment A is more volatile (with larger standard deviation), but with less risk, this investment A is aways better than less volatile, but more risky investment B.

Standard deviation is just a metrics of mathematics, which I learned in my first year physics class decade ago. This is nothing new to me or to others who has science or math background. Standard deviation is great statistical indicator to measure random errors in physics or other random events in sciences.

However, I have quite reserve on its use in investment or financial world, which can be considered "microeconomics". Microeconomics is not physics.

In investment, the key is risk control and measurement, not volatility or standard deviation of past stock price movement.

Of course, volatility or standard deviation of stock price is not useless indicators. It is useful in portfolio management.

However, to make a claim this Standard Deviation equals to risk, this is wrong theory. Because standard deviation (SD) does not equal to degree of risk, SD adjusted return comparison does not make sense.

**blast_investor** Tue Jul 03, 2007 1:14 am

A related concept is beta, which is claimed by academic economist as measurement of risk. Beta essential has similar math of standard deviation.

http://www.investopedia.com/articles/stocks/04/113004.asp

Beta is a measure of a stock's volatility in relation to the market. By definition, the market has a beta of 1.0, and individual stocks are ranked according to how much they deviate from the market. A stock that swings more than the market over time has a beta above 1.0. If a stock moves less than the market, the stock's beta is less than 1.0. High-beta stocks are supposed to be riskier but provide a potential for higher returns; low-beta stocks pose less risk but also lower returns.

**blast_investor** Tue Jul 03, 2007 1:18 am

Standard deviation on past stock price movement is essentially a measurement of volatility on a stock. This is similar concept to beta.

Here is Warren Buffett and Charles Munger comments on the risk verses volatility in 2001 Berkshire Hathaway Annual Meeting
documented by Whitney Tilson:

http://www.tilsonfunds.com/motley_berkshire_brkmtg01notes.php3

--------start -----------------
Risk

"We regard using [a stock's] volatility as a measure of risk is nuts.
Risk to us is 1) the risk of permanent loss of capital, or 2) the risk of inadequate return. Some great businesses have very volatile returns -- for example, See's usually loses money in two quarters of each year -- and some terrible businesses can have steady results.

Munger: "How can professors spread this? I've been waiting for this craziness to end for decades. It's been dented, but it's still out there."

Buffett: "If someone starts talking to you about beta, zip up your pocketbook."

-------end---------------------

**lzhang** Thu Jul 12, 2007 1:29 pm

Hi,

I was trying to answer most of the questions in post http://forum.blastinvest.com/viewtopic.php?t=1589

At least for one thing about See's Candy, I do not think what Mr. Buffetts was talking about is relevant to the issue (beta, risk, or whatever name you call it)

It might sound reasonable to require high return for high beta stock, but if the expectation (high return with high beta) can be materialized or not is a different question. Some EMH believers may be confused with the two different questions.

blast_investor wrote: Standard deviation on past stock price movement is essentially a measurement of volatility on a stock. This is similar concept to beta.

Here is Warren Buffett and Charles Munger comments on the risk verses volatility in 2001 Berkshire Hathaway Annual Meeting
documented by Whitney Tilson:

http://www.tilsonfunds.com/motley_berkshire_brkmtg01notes.php3

--------start -----------------
Risk

"We regard using [a stock's] volatility as a measure of risk is nuts.
Risk to us is 1) the risk of permanent loss of capital, or 2) the risk of inadequate return. Some great businesses have very volatile returns -- for example, See's usually loses money in two quarters of each year -- and some terrible businesses can have steady results.

Munger: "How can professors spread this? I've been waiting for this craziness to end for decades. It's been dented, but it's still out there."

Buffett: "If someone starts talking to you about beta, zip up your pocketbook."

-------end---------------------