Question on Statistics

[moeniogt]

Is anyone running stats on the funds...if so, can you explain what stats are significant to explaining the market (standard deviation, skewness, kurtosis, etc) and what the stats mean? I am running a spreadsheet that tracks the funds (changes - or +) but I would like to build in other stats if they are helpful.

 

[JTH]

I run stats on the funds, but it's just the 5 & 10 day price performance in percentage form, not the items you mentioned. I'm not familar with the applied application of the stats you mentioned, what is it you're seeking to accomplish?

 

[RealMoneyIssues]

Is anyone running stats on the funds...if so, can you explain what stats are significant to explaining the market (standard deviation, skewness, kurtosis, etc) and what the stats mean? I am running a spreadsheet that tracks the funds (changes - or +) but I would like to build in other stats if they are helpful.

http://statistics.berkeley.edu/~stark/SticiGui/Text/gloss.htm

http://www.investopedia.com/dictionary

i.e.
http://www.investopedia.com/terms/b/bollingerbands.asp
20 day average +2 standard deviations, -2 standard deviations (see excel help on formula for stddev)

You should be able to find what you need (if you know what you are looking for) from a quick Google search.

Now, if you are looking for WHAT we look at for TA, that is a different question...

 

[moeniogt]

I am trying to understand with my own statistics how the funds are going to behave by having visuals of funds going up or down plus statistical analysis as predictors on short term (maybe longterm?). I know everyone talks about signals, and I would like to learn how to read them. I am hoping that if I statistically track data (monthly and throughout the year) I can better manage how I allocate to maximize buying power. Also might be able to predict to move allocations as well. Standard deviation is a statistical measurement that sheds light on historical volatility. For example, a volatile stock will have a high standard deviation while the deviation of a stable blue chip stock will be lower. A large dispersion tells us how much the return on the fund is deviating from the expected normal returns. Variance measures the variability (volatility) from an average. Volatility is a measure of risk, so this statistic can help determine the risk an investor might take on when purchasing a specific security. Skewness is extremely important to finance and investing. Most sets of data, including stock prices and asset returns, have either positive or negative skew rather than following the balanced normal distribution (which has a skewness of zero). By knowing which way data is skewed, one can better estimate whether a given (or future) data point will be more or less than the mean. Most advanced economic analysis models study data for skewness and incorporate this into their calculations. Skewness risk is the risk that a model assumes a normal distribution of data when in fact data is skewed to the left or right of the mean. Kurtosis is a measure of the likelihood that an event occurring is extreme in relation to a given distribution. Excess kurtosis is an important consideration to take when examining historical returns from a stock or portfolio, for example. The higher the kurtosis coefficient is above the "normal level", the more likely that future returns will be either extremely large or extremely small. Kurtosis is often referred to the "volatility of volatility".

 

[moeniogt]

Yes, true..I can Google....but I am trying to do Specific TSP funds (G,F,C,S,I)....mainly C,S,I...the best to make money off...but also the most volatile. I guess I am a control freak...lol

 

[RealMoneyIssues]

Yes, true..I can Google....but I am trying to do Specific TSP funds (G,F,C,S,I)....mainly C,S,I...the best to make money off...but also the most volatile. I guess I am a control freak...lol

Stable - C
Big moves - S
Most volatile - I

Done

 

[moeniogt]

Stable - C
Big moves - S
Most volatile - I

Done

lol...true. But how about:

For January I Fund shows 9 downs, and 8 ups. The fund went down 5 consecutive times before this las day when it slightly went up. Probably explained if you read financial Global news. However as an entry point to the I fund you are buying in 0.5010 above the average Jan price. Skewness is positive that predicts it will keep moving positively from the average in the short run. Kurtosis doesnt predict anything out of the ordinary in the short run. The standard deviation shows that it will be within 0.4244 from the mean in the short run...the more the year progresses this will change and it will become a better value. And the risk of buying into this fund is 0.1801 right now,based on the Variance from January.

 

[nnuut]

Why would any body invest in Europe when they are falling through their $$s? If you had more IFTs OK but it changes every day it's like we are marionettes of the EURO, ridiculous!

 

[moeniogt]

Why would any body invest in Europe when they are falling through their $$s? If you had more IFTs OK but it changes every day it's like we are marionettes of the EURO, ridiculous!

Well, something sparked some confidence between yesterday and today. But I wouldnt buy into the I...you are buying a little high above the average. Skewness doesnt predict it will trend up...it just says it will be above the mean. The Standard deviation shows a lot of volatility in January. The variance shows you are risking close to 0.2 on the short run..makes sense because if you lose 0.2 if you buy right now..you are still above the mean. You just need to read the statistics correct.

 

[RealMoneyIssues]

lol...true. But how about:

For January I Fund shows 9 downs, and 8 ups. The fund went down 5 consecutive times before this las day when it slightly went up. Probably explained if you read financial Global news. However as an entry point to the I fund you are buying in 0.5010 above the average Jan price. Skewness is positive that predicts it will keep moving positively from the average in the short run. Kurtosis doesnt predict anything out of the ordinary in the short run. The standard deviation shows that it will be within 0.4244 from the mean in the short run...the more the year progresses this will change and it will become a better value. And the risk of buying into this fund is 0.1801 right now,based on the Variance from January.

I don't believe raw statistics will provide a successful trading model. If that were the case, there would be a lot more people making a ton of money...

Take into account sentiment, macro patterns, micro patterns, volume, et al. when trying to understand what is going on. Prediction is difficult, just ask around

 

[moeniogt]

I don't believe raw statistics will provide a successful trading model. If that were the case, there would be a lot more people making a ton of money...

Take into account sentiment, macro patterns, micro patterns, volume, et al. when trying to understand what is going on. Prediction is difficult, just ask around

Yes I know, by no means is this a way to predict. My amount of shares is miniscule probably in comparison to you guys because I just started. I am just looking at maximizing my purchase power into the funds. Not ITFs. When I get enough....hopefully I will have learned from you guys on do's and dont's on IFT's.......but I hope the statistical analysis have a high correlation to what happens in the market. And if it doesnt I hope to learn why and what to look for in the news or signals.

 

[moeniogt]

let me enlighten you with a quote from someone at work today..."

If you use statistics and guess right, you can say..."hey, numbers dont lie"...if you are wrong, you can say "hey, ...thats why probability is expressed in percentage... and 1-100% is a dang broad range buddy!"...​

:laugh:

 

[RealMoneyIssues]

let me enlighten you with a quote from someone at work today..."

If you use statistics and guess right, you can say..."hey, numbers dont lie"...if you are wrong, you can say "hey, ...thats why probability is expressed in percentage... and 1-100% is a dang broad range buddy!"...​

:laugh:

Exactly (or not)

 

[JTH]

There are many technical indicators in use today, but all are merely a mathematical measurement of price. The terms you are referring to are not commonly used in technical analysis, instead terms like moving averages, rate of change, and linear regression are more commonly used. Everything you seek still exist, but the terminology is different. With your skill-set you may want to backwards engineer the technical indicators, and apply them to your situation. I would start by understanding the three principle types of indicators in use today. Multicollinearity Best of luck, there is no easy answer or shortcut, everyone hs to find there own path...

 

[nasa1974]

The I fund is not something I would stay in for very long. It is way to volatile. Even way back when many of us made some very good money. But that was when we had daily IFT's and could move in and out of the I fund quickly. With only 2 IFT's I would not spend much time in the I fund because it will cost you time on the lilly pad.

 

[moeniogt]

There are many technical indicators in use today, but all are merely a mathematical measurement of price. The terms you are referring to are not commonly used in technical analysis, instead terms like moving averages, rate of change, and linear regression are more commonly used. Everything you seek still exist, but the terminology is different. With your skill-set you may want to backwards engineer the technical indicators, and apply them to your situation. I would start by understanding the three principle types of indicators in use today. Multicollinearity Best of luck, there is no easy answer or shortcut, everyone hs to find there own path...

Yes, I just pulled out my Investment Science and Investment Mechanics books from school......my wife seems worried, lol.

 

[Mapper]

I am trying to understand with my own statistics how the funds are going to behave by having visuals of funds going up or down plus statistical analysis as predictors on short term (maybe longterm?).

Many of the stats being discussed are explanatory stats that describe past prices. If you want to try your hand at magic predictions you have to get into stochastic modeling (takes into account cycling; price oscillations) and you need to start applying random walks. Unfortunately there are few "rules" that the market plays by, "too many degrees of freedom" in statistical terms, so ascribing any confidence to your results is very difficult

In my opinion, compared to my experiences in natural science modeling potential market movements is pure juju.

 

[moeniogt]

Many of the stats being discussed are explanatory stats that describe past prices. If you want to try your hand at magic predictions you have to get into stochastic modeling (takes into account cycling; price oscillations) and you need to start applying random walks. Unfortunately there are few "rules" that the market plays by, "too many degrees of freedom" in statistical terms, so ascribing any confidence to your results is very difficultIn my opinion, compared to my experiences in natural science modeling potential market movements is pure juju.

True....if the market was statistically solved..it wouldnt be a market anymore. It wouldnt be Bulls and Bears anymore....maybe Sharks and Anchovies. But...there is some solid math in educated guesses.