Trend Strength Index (TSI) Results Summary
This post is a follow up to the previous on the Trend Strength Index (TSI) by Frank Hassler of Engineering Returns: https://cssanalytics.wordpress.com/2010/06/28/trend-strength-index-tsi/ I will have more to follow on the TSI later this week, but first a peek at the results of some tests that Frank ran on the Nasdaq 100 stocks using TSI. You can see that depending on a stock’s TSI value, there is a pronounced difference in how it responds to different short term trend strategies. High values of TSI are highly desirable (above 1.8 or 2) for short-term trend strategies, while low levels of TSI are quite poor. The opposite is true for mean-reversion strategies, where stocks with TSI values at or less than 1.5 tend to do extremely well with short-term mean reversion. In contract, high TSI stocks do very poorly —in fact in our own testing, they bankrupted the starting account balance, which is a first! In nearly every case the TSI is superior to the ADX–which is the standard trend filter used by most traders. Traders would be well advised to consider the TSI of a stock before they make a decision on how they plan to trade it. Deciding otherwise could be quite costly. Making the right decision can mean a substantial improvement in your trading results.
CSSA 
hi David,
i am curious.. would not autocorrelation of returns be a measure of trend vs mean-reversion ? and therefore TSI be somewhat like autocorrelation ?
i.e autocorrelation of 1-day returns compared to autocorrelation of 2-day returns would show the relative trendiness on a 1-day as compared to a 2-day timeframe.
Anyway, i guess when the TSI calculation is out there, it will be good to see.
thanks !
Hi David.
The results suggest that trend following entries on low TSI stocks do poorly and from this, we assume that mean reverting strategies would do well on these low TSI stocks.
But maybe instead of assuming this, we could really test for ourselves using mean reverting entries? I noticed that all the entries you used in the study were trend following.
I figured that instead of drawing the conclusion from the fact that trend following entries doing poorly on low TSI stocks, we could just test whether mean reverting strategies indeed did well on low TSI stocks.
Thanks and cheers! Great site. I learned a lot.
Thank Science Engineering
I have one question.For a given stock in a given time how often is occurence of M size move compared to 2M size move.My studies over 20 years conclude that M size move should be 4 times more common than 2M size move—based on square root of time principal for option pricing/odds of move of a given size in the underlying in the BLACK SCHOLES formula. BLACK SCHOLES may not be perfect–but the fact remains that trillion dollars of derivatives are traded each day based on this formula & option market makers make money year after year & laugh all the way to the BANK.Similar to relationship between price of one month option versus price of 4 month option,If it takes one month to get M move, it would take 4 months for 2M move in the same stock in the same time period.This tells me that if human brain is kept out of the equation & in SYSTAMATIC(automated) investing in stocks, take profit be 1/2 the size of stop loss( & we already know that markets are RANDOM) then over thosands of RUNS investor shall make a whole lot of money.Out of four trials one makes one dollar 3 times & loses 2 dollars one time with net profit of one dollar–all one has to do is that when take profit is HIT, cancell the unfilled stop loss order & repeat the process over & over.Investor stays direction neutral at all times with no bias long/short.This is not just a theoretical question–if you spend few hours pondering this question I bet your next 5 generations can make tons of money over the next 500 years,just clicking on the LAP TOP & would never have to look for A JOB.Any criticism would be appreciated.Thank you for your help in advance.
Dr Prem Nath MD cell# 845 641 6778 email indus68@gmail.com
David,
I’ve become really interested in the TSI. I’ve even blogged a bit about it at http://www.nonrandomwalk.com. I’m trying to replicate your results on a broader set of stocks. Could you please let me know the time frame for the above study?
Alex