The Seasonality Problem (Part Eight)

Not All Days Are Equal

One thing that significance will not tell you is whether the information you have just found is worth anything in the practical sense. To find that out, you have to examine and analyze your data.

Let’s revisit the table again:

Apart from the win:loss ratio, which gives you the batting average of each month, it’s also important to know the average magnitude of the returns (average wins/loss) for us to judge the worth of the results. In both cases, October outperforms the other months. Also note something: all of the months have a win:loss ratio higher than 1—meaning the number of winning trades is larger than losing trades. But what makes the winner is the reward:risk ratio—or the size of the wins vs. the size of the losses. In the case of the worst performing months (January and February), even if the number of winning trades exceeded the losing trades, the average size of the wins were smaller than the losses.

The Seasonality Problem (Part Seven)

Time and Tide

Thus, armed with our Nuts and Bolts, we can easily arrange and rearrange our data to form observations about our experiment. The first thing we can do is figure our exactly how many of our traders made money as a whole:

The Seasonality Problem (Part Six)

Nuts and Bolts

Does Seasonality exist? Can timing your purchases improve returns? Is there really a January Effect? What effect do Ghost Months Have? To answer these questions, we can possibly phrase our hypothesis as:

”Seasonality has an effect on market returns.”

However, this is still too general. One thing about being critical is an emphasis on the SPECIFIC. We want to get into as much detail as possible, so only then will we be able to leave the realm of the subjective and motherhood statements, and get into something that might be objectively useful to us. So we can rephrase our hypothesis as:

“The month at which you enter the market has an effect on market returns.”

Even better:

The Seasonality Problem (Part Five)

Asking The Right Question

In an earlier post, we described how we can never really prove anything. That fact can be depressing to an investor—who is seeking for a surefire way to beat the market. If anything, the market only serves to disprove any method you throw at it: buying on a breakout leads to a reversal, buying on positive earnings leads to a market correction, buying on rumors that insiders are buying leads to insiders selling to YOU.

You can’t prove anything. You can only disprove.

However, over the years, philosophers, scientists, and statisticians (read: people with a lot of time on their hands) well aware of this depressing fact, have figured what could possibly be a clever way around our inability to PROVE anything. The answer: DISPROVE the opposite. More than semantics, it’s a question of logic. If the opposite to your hypothesis is false, then your might have more confidence in your original hypothesis.

The Seasonality Problem (Part Four)

Introducing The Seasonality Problem

Finally, after three posts, I’m finally getting around to the real meat of my title.

I had an inkling although very little understanding of The Seasonality Problem when I took my first job as a securities representative-trainee. In our welcoming briefing, our trainer told us we were part of “Batch 4.” What I remember distinctly about those times was when one of us asked about the previous batches of recruits. To which, our trainer replied: “You’ll be meeting batch 2 when you start your trading on the floor. They’ll be your mentors—we’ll be assigning a buddy for each of you.” “What about batch 1 and 3?” “Well, not many from those batches stayed. Those batches weren’t very successful.”

The Seasonality Problem (Part Three)

What The Hell Is Your Problem

If you haven’t thought about them already, you should know about two depressing truths about finding knowledge:

1. It is impossible to know everything.
2. It is impossible to prove anything.

Imperfect knowledge and uncertainty are two main obstacles to successful decision making. Apply this to decisions about money and add emotion to this mix, and you have a deadly formula guaranteed to lose you money.

When we gather information, it is usually with the aim of finding a deeper truth or meaning behind the data being presented to us. We commonly look for proof of a statement, not evidence to the contrary. This is called the confirmation bias—we always love to look for evidence that we are right. The problem with a confirmation bias is that the presence of additional evidence supporting a theory does not really add any value to the strength of the theory.

The Seasonality Problem (Part Two)

The Alchemy Of Finance

A quick look at the FM thread for Pacifica, Inc. (PA)—a stock that has been very volatile and tradable lately—reveals the following ongoing conversation as of the time of this writing:

The Seasonality Problem (Part One)

Bull Market And The Rise of BullSh*t

With going on three “major” market crashes as of this writing, the year of 2007 has probably been a roller-coaster ride for most investors in the Philippine Stock Market. I could say the same for the Financemanila forum. Boss D can correct me if I’m fudging, but I think this year has seen a record rise in membership, a rise in EB attendance, and a rise in forum “noise”—from hyping, doomsayers, and the abundance of market “theories.”

IMHO, this is just consistent with 2007 being the 5th year(?) since the generally agreed start of the bull market from the end of 2002 and especially with the internet being a more easily accessed medium over the past few years, and the advent of internet-based investment services (Citiseconline, BPI Trade, etc.).