Comment Posted Online to “Quantitative Strategies for Selecting Stocks,” by Richard Tortoriello, May 2010 AAII Journal:
We need more articles like this on quantitative methodologies, assumptions and results.
Tortoriello requires a linear relationship in his quintiles. Sometimes both the low and high values may have the best (or worst) performance. By dividing into deciles and using decision-tree software, one can discover relationships other than linear relationships. Even in a linear relationship, one would want to know the best cut-off value.
Just because I don’t predict or understand a given relationship is not to say that the relationship does not exist and is predictive. We are easily seduced and blinded by our assumptions. One can mine the data and explore many more possibilities while still guarding against over-fitting by testing and protecting with statistical measures.
The linear relationships confirmed for the four variables don’t say anything about how they would perform in combination. One needs to test for the interaction effect.
Comments Posted Online regarding “The First Cut: Tortiello’s Quantitative Strategies,” by John Bajkowski, May 2010 AAII Journal:
The May 2010 issue of the AAII Journal includes an article on Tortoriello’s Quantitative Strategies as well as a First Cut screen. How do you set up the ratio of enterprise value to EBITDA and the cash ROIC in Stock Screener Pro? I’d appreciate any help.
I was attempting to create the Tortoriello screen described in this May 2010’s First Cut column. Clearly, this can be done, since the article’s author says he actually used Stock Investor Pro to generate the results shown.
Before I go reinventing the wheel, has anyone made this screen already? Or does AAII have the screening criteria used in the actual article available as a download, or at least a text file listing the fields used?
Frankly, I got stuck at the first screening criterion mentioned by Tortoriello—namely, enterprise value. There seems to be no predefined field in Stock Investor Pro that encapsulates this calculation (or, if there is, the search function is no help in finding it).
AAII Editors respond:
Click here a text file with the Tortoriello First Cut custom fields for use with Stock Investor Pro.
Comment Posted Online to “Using Sell Signals to Improve Results,” by Kate Stalter, June 2010 AAII Journal:
In “Using Sell Signals to Improve Results,” Kate Stalter advises selling if a loss is 7%—clearly sensible if the market is stable but the stock is not. But what is her advice if the whole market is correcting, a la recent intraday gyrations? I would think that if one wants to stay generally invested through short-term fluctuations (I am an investor, not a trader) and the problem isn’t with the stock, then it shouldn’t necessarily be sold. Would Stalter agree?
Argentcedar From Washington
Kate Stalter responds:
The short answer: no. These rules apply in any type of market.
But this is a great question, and it speaks directly to Investor’s Business Daily’s rule about avoiding new buys in a market downturn. Not only did the market become especially volatile in May and June, but for much of that time, the market itself was in a correction. Any new purchases made during that time would have been especially prone to sudden downdrafts. Along with those market pullbacks, many individual stocks fell 7% or more below their purchase prices.
When the market is in a confirmed uptrend, when heavy-volume days of selling are scarce, it’s less likely you’ll see as many sharp pullbacks within individual stocks. It’s always wise to use caution and respect the market’s trends. Three-fourths of stocks follow the general trend, either up or down. Making new buys in a downturn is playing a risky game.