Skip to main content

Posts

Showing posts from October, 2020

S&P 500 2015/Y-4

One Year Return Two Year Return Three Year Retun Four Year Return Year Two Return Year Three Return Year Four Return Group 9 had two stocks and group 8 had four. Here are the results if I combine 8 and 9. One Year Return Two Year Return Three Year Return Four Year Return Year Two Return Year Three Return Year Four Return

STARTING AGAIN S&P 500 2013/Y-6

I'm starting over. I saw  good results when I did a quick and dirty test on the model using S&P constituents over the various years.  I'm going to start this time by putting all that down.   This one is the S&P500 that existed in 2013 edited for companies that don't work with this model (financials primarily).  I run the model on that group as if it was early 2014, just after most of the companies have issued their 2013 results.  The model predicts the best performing stocks.  I'll then graph the actual results over various time frames. This was the genesis that started this testing.  I'm going back to the beginning and recording those results. Note: the edited S&P500 portfolio has 315 stocks in it. One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Six Year Return Year Two Return Year Three Return Year Four Return Year Five Return Year Six Return Observations:  These results are different for the S&P500 Y

BACK-TESTING EP Y-5 LARGE CAP SCR

One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Year Two Return Year Three Return Year Four Return Year Five Return Observations: This is crap.  This is not working.  I'm not continuing with this.  I'll try something else.

BACK-TESTING EP Y-5 SMALL CAP ISC

One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Year Two Return Year Three Return Year Four Return Year Five Return Observations This blows. These couldn't be worse, well except for Year Four and Year Five. ISC is perhaps not a good combination.

BACK-TESTING EP Y-5 LARGE CAP ISC

As I was building out the performance graphs I realized this is different from Y-6. In Y-6 I removed companies that had any R. I didn't do that this time. I made sure they all had I, S, and C, but they could have R. I almost stopped work on the performance graph, but I decided to continue on. Remember, I'm trying to figure something out.  One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Year Two Return Year Three Return Year Four Return Year Five Return

BACK-TESTING EP Y-5 S&P 500 Y-5 Part 2

 I'm just going to check this out... One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Year Two Return Year Three Return Year Four Return Year Five Return Observations Similar to the last one, it looks like the EP results last about 3 years.

BACK-TESTING EP Y-5 S&P 500 Y-5

 I'm so pleased to be starting a new year of testing. Starting with the S&P500 constituents from 2014, and after editing for analysis, there were 330 stocks  to analyze.  Some of the remaining companies don't do R&D. One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Year Two Return Year Three Return Year Four Return Year Five Return Observations: One thing I've been thinking about for a while is to combine at least the two top group together.  In this case 7 and 8. 8 was another smaller group and therefore subject to extremes.   That may become another test, larger groups - a top, middle and bottom, for example.  The top group would be 7, 8 and 9.  The middle would be 4, 5, and 6 and the bottom 1, 2, and 3.  With this grouping I might not have to run the I,C, R/S,C,R etc.analyses.

BACK-TESTING EP Y-6 ALL CAPS: C, R & I, S

There were 3 stocks for large caps with C, R and 11 small cap stocks.  Even if I combine the two groups 14 is too small.   There were 0 stocks for all caps with I, S, they all had C. So that's it for Y-6!  Tomorrow I move to Y-5.  Yay.  I'll start with the S&P 500 analysis.  It's good to remember why I'm doing this.

BACK-TESTING EP Y-6 LARGE CAP S, C, R

One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Six Year Return Year Two Return Year Three Return Year Four Return Year Five Return Year Six Return Observations: This was a small portfolio - 45 securities, so it's results will be impacted by small groups.  Group 8, the highest possible portfolio did not perform as projected.  However group 7, the next highest, did perform reasonably well.

BACK-TESTING EP Y-6 SMALL CAP I, C, R

 Small cap is defined as $1 to $5 B.  Eight is the maximum score. "Y-6" means the analysis was run using data six years prior to the most current financial statement. One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Six Year Return Year Two Return Year Three Return Year Four Return Year Five Return Year Six Return Observations: Good. Will get more into the results when more tests are compete.

BACK-TESTING EP Y-6 LARGE CAP: I, C, R

 I had slated a back-test on I, S, R with no C, but not surprisingly, when you think about it, you don't have R without C.  So removing the C's removed everything, so it was a null group. This test groups companies with I, C and R but no S. Large cap is defined as greater than $5B. The highest score is 8. One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Six Year Return Year Two Return Year Three Return Year Four Return Year Five Return Year Six Return   Observations: This was a good grouping, especially for 8.   Results look a little random, but I do notice that 8 does cumulatively better than average.

BACK-TESTING EP Y-6 SMALL CAP: I, S, C

This test series works looks at small cap companies (defined for this test as having a market cap between $1b and $6B) that do not have a value for R but do for I, S, and C. The maximum score is eight. One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Six Year Return Year Two Return Year Three Return Year Four Return Year Five Return Year Six Return Observations There's no clear advantage to group 8 and group 1 performs much better than the model predicts.

BACK-TESTING EP Y-6 LARGE CAP: I, S, C

This test series works looks at large cap companies (defined for this test as greater than $6B) that do not have a value for R but do for I, S, and C. The maximum score is eight. One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Six Year Return Year Two Return Year Three Return Year Four Return Year Five Return Year Six Return Observations:  I need to point out that group 8 only had one company in it. Cumulative returns are good, especially a long 8 and short 1.  Year to year returns more erratic.

BACK-TESTING EP Y-6 SMALL CAP: I, S, C, R

The small cap/large cap runs from $1B to $10B and greater than $10B, respectively. One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Six Year Return Year Two Return Year Three Return Year Four Return Year Five Return Year Six Return Observations: This is good.  Strong performance by the highest score group.

BACK-TESTING EP Y-6 LARGE CAP: I, S, C, R

I'm trying something different. There are benefits to sorting by sectors and perhaps I'll come back to it, but now I'm sorting by the available analysis elements.  Without getting into a lot of detail, this model looks at several different fundamentals (a maximum of nine) which results in a score, the higher the score the better.  However, not every fundamental is present in every company.  This method of organizing splits out those companies that have all four of the inconsistent measures, or three, or two.  I don't expect there will be companies that only have one of the inconsistent measures, but we'll see. I also want to state that there will be a difference between the methods used in testing and the method used in operations, if I can successfully prove out this model.  When this model is in operation, I will be looking for companies who have just released their financials and looking at their score for possible inclusion or removal from the investment portfol

BACK-TESTING EP Y-6 S&P 500 Y-6

It's going to take some time for me to get my portfolios in order, but I feel good about this decision.  It's going to be more work, but these small portfolios are giving inaccurate results. I thought it would be useful to remind myself why I'm doing this in the first place.  This started because I wanted to get an idea of whether my EP model was predictive.  I did a quick and dirty test against a somewhat current S&P 500 portfolio I had in my list.  We have to start somewhere right?  Seemed like a good choice. The results were very encouraging.  Encouraging enough for me to go further with the testing.  Specifically to refine it, remove biases and isolate other factors that could be responsible for the results. I purchased a list of S&P constituent members that went back years and years.  It was very well done, it shows all the ins and outs of members each quarter.  They're called Siblis Research , for anyone who's interested.  I used this to build S&P

BACK-TESTING EP MODEL Y-6 for NON-ENERGY MINERALS

 One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Six Year Return Return for Year Two Return for Year Three Return for Year Four Return for Year Five Return for Year Six Observations: Again, a small portfolio leading to some groupings with only one or two stocks in it.  As I move ahead in time, each of these portfolios will naturally get more companies but I think I should also combine similar sectors.   Because I'm so process oriented, I feel the need to continue on this path, but maybe I should stop and implement these improvements now.  I have 14 more sectors to go and with the way things are going, that'll take two weeks.  OK, decision.  I'm going to start combining sectors.  I would like to have at least 200 stocks per sector and each sector should be similar - not only from a service perspective, but from a financial statement perspective - they have similar line items. My next entry will outline the sectors.  

NOTES TO SELF

 Two methods to improve the results: 1) Combine smaller portfolios that make sense to combine - for example retail trade could be paired with consumer non-durables.  I will continue Y-6 with the portfolios as planned however, and then evaluate which ones could or should be combined. 2) Combine small groups together.  For example, if one group only has one or two companies, move it to a higher or lower group. Combined portfolio Candidates: - Producer Mfg & Process Industries.

BACK-TESTING EP MODEL Y-6 for PRODUCER MANUFACTURES

 One Year Return Two Year Return Three Year Return Four Year Return Five Year Return Six Year Return Return for Year Two Return for Year Three Return for Year Four Return for Year Five Return for Year Six Observations: These are more like the results I was hoping for and expecting - I did have a reason for this.  I saw tremendous results when I ran this against the S&P constituents.  That was a large portfolio and so is this one - larger than the others so far.  I think that is part of it - when the portfolio is smaller outliers can take over.  It's important to remember, nothing bats 1000 all the time.  What we're looking for is a good, strong average over time, and across industries. As the testing moves forward in time, the data will get more consistent as well.  I therefore put more stock in more recent years. Other notes - there is only one company in Group 2, pointing this out as it had the highest placement in Return for Year Three and Five.