Thursday, March 10, 2016

The foolishness of inflation measurements

A lot of garbage statistics is used to collect inflation data and to calculate stuff like CPI (Consumer price index). Your mortgage and other interest rates and sometimes your rent are adjusted to this number; and this statistical trickery of taking data to find out the value of money and how it varies over time has a bearing on your everyday life.

Can you give a precise value for money (dollars) by measuring the value of all other things the way the Index with the inflation basket does? I don't think so.  Here are the problems with this measurement:

1. It does not consider the statistical deviation in prices. Whenever an inflation data is published, I would like to know the standard deviation of the data. No mention is made; to hide the fact that the prices vary all the time! For the basket used to measure this data, what is the standard deviation of the prices?

2. The choice of basket is arbitrary, and even if the data for the basket was statistically reliable, one can't say that the basket can be used to measure the general value of money over all things for all human beings (thousands of things and millions of human beings consuming them in different ways). It is a measure of money for that basket only, and any conclusions about the general spending habits of people in so many other ways they spend money from that basket is outright silly. The inflation data, strictly speaking, is valid just for that basket.

Any changes in the basket composition will give you altogether different values of inflation (which shows there's nothing real behind the data-it is all noise).

3. Measuring the value of a basket in money terms, or a bunch of items in money terms, does not give you the value of money. The demand of money varies just like of other things (potatoes, electricity, whatever) and you cannot just average it out over a bunch of things and come up with "one value" of money, as a CPI calcuation does. The natural variation of prices of everything, and of money (cash) in itself, is not considered at all.  It also assumes that the reason the value of money is what it is is because of increase or decrease in supply of money; and does not consider that the demand of money, just like of any other commodity, is itself variable.

To explain this further-let's say we started measuring things in potatoes, and we could control the production of potatoes so that every year we would increase the potato supply by 2%. Can this be captured by measuring everything else in potatoes and coming up with something like "the supply of potatoes increased 2% in 1 year"? I believe it is impossible. With all things valued in potatoes, and because their value is itself very variable depending on the supply and demand, you will end up with a very noisy idea of the value of things in terms of potatoes. It is very unlikely that you will hit the mark of 2%. So even in a controlled enviroment, when you simply increase the supply of potatoes by 2% in a year, you will not be able to come up with the exact value by your statistical data taking of market prices. The same holds if you measure it in dollars or pesos.

3. It also assumes that the sellers of the goods run their businesses at constant profit percentage. In practice, businesses play with prices all the time, and often times will lower profit margins to get more volume. Such a strategy is not considered by inflation measurement fanatics-who assume that all variation in price is because of the variation in supply of money.

The basic idea of measuring things to get the value of money is not bad-you can get an idea, a very rough idea about inflation, if EVERYTHING in your basket goes up in price by a significant amount (at least 10%). This happens in Argentina and Venezuela, for example. Then you are able to see inflation-but even then to give an exact number to it like 20% per year or 50% per year is foolish. For small variation in prices, less than 5%, you cannot conclude that the price of things increased because you printed more money, or because of simply that the demand of money went down in relation to other things, etc.

If there was something real in measuring the value of money using things in the inflation basket-ALL items would go up with a very similar amount e.g. 5%. Then you can say with confidence that it is the price of money which is changing and it is not the statistical variation in it which you are capturing.

In effect, there are a lot of holes in the basket measurement of inflation. Any number which is less than 5% and is quoted as inflation is but noise-and they are careful to hide the noise by not publishing the standard deviation of data.

Other holes in the measurement of inflation: a) they invented something called "core inflation" to remove the volatile parts of the inflation basket, food and energy. A real statistician never discards any data, here it is being discarded on purpose to remove the deviations and noise in the data, to make the inflation numbers "smooth" and b) a small change in the composition of the inflation basket will lead to an entirely different number for inflation. If the real value of money was being measured, a change in just the composition of the inflation basket should make no difference.

Inflation measurements which are increasing steadily at say 2 or 4% per year are in reality a clever way of defrauding the persons who borrow-who almost always see their interest payment go up with time, because they measure the index in a peculiar way to make it increase slightly almost every year. The noise of the measurements is removed carefully to always come up with a slightly positive number  between 0% and 5%, to give the banks a license to increase interest payments on the borrowers. Or rent payments, which are also adjusted to inflation in most big cities. The inflation data publishers meet the needs of the market well-the massage the data to come up with a number of between 0 and 5%, and get to keep their jobs. But the real value of all this data is zero, for the reasons mentioned above.

The futility of inflation measurements is best illustrated by countries like Panama and Ecuador, which use the US dollar as their currency. Since they have no influence or control over how US dollars, a foreign currency there, is valued, their inflation measurements are nothing but noise. Amazingly, they have an inflation measurement department...where dozens of statisticians and bureaucrats are employed to come up with this data. Link for Panama here   and Here for Ecuador.

Clearly if the inflation in Panama is high, there's nothing they can do about it. Nor they can do anything if it is low, because they can't control the amount of dollars in the country or it's banking system. You wonder why they measure it at all!

In Ecuador, the annual cumulative inflation was 3.38% in 2015, and 3.67% in 2014. Since they have no control over the emission or use of US dollars, clearly that is NOISE...and you can see easily that small measurements of inflation, below 5%, and probably even below 10%, are statistical noise, nothing else.

The most ridiculous use of inflation data is by utilities  (electricity, telecom companies, etc.) and essential services companies. Utilities use this data to justify increasing rates. They say that because of inflation, they be allowed to raise rates. Since their own products form a part of the basket of things used to measure inflation, they basically go into a feedback loop-the basic necessities companies raise rates because of inflation data, and since the raise rates, next year inflation data shows even more inflation, and they raise rates even more. Imagine if every product or service in the inflation basket started raising rates, the next year's inflation would go through the roof! Here in Chile where I live, this is why gas and electricity prices are the highest in the Americas (North and South)..and the Government lets these utility companies increase rates , who use the excuse of higher inflation.

Central banks have no influence in jobs creation, unemployment or real interest rates. Here's the post explaining this.


Saturday, January 23, 2016

Understanding evolution-zebra article today

Some biologists today published a study on why they think zebra stripes are not for camoflage, etc. They do not seem to understand evolution quite right.

The winner in evolution transmits all their characteristics to the offspring. But  you can't say that the characteristic (e.g. stripes) was the cause of the individual being a winner.

A particular human being might be a survivor in a difficult situation because of their excellent intelligence. They may have a mole on their right chin, or have a hairy back, etc. All these characteristics will be passed on to their progeny; but it is not because of their hairy back or the mole on their right chin that they are a winner.

Or instead of intelligence, it might be just luck; maybe the individual just hid in a cave while the rest of the pack was eaten by a predator. Since this individual now reproduces, all his characteristics will be transmitted to his offspring.

The characteristics you see in a species like a zebra are just that; they are not there because somehow that characteristic lead the species to win out.

Even for sexual selection this is the same. The characteristic is not a cause of victory; it is a by product of already being victorious.

The same intelligent human being might be able to get more mates; but the females are not selecting the individual for their mole on the right chin or his hairy back.

This is a common problem I see in evolution related publications; essentially they do not get the causality right. The causes of why an individual survives are not known; the characteristics you see in an individual are the effects of them being winners.


Friday, December 25, 2015

Fools in Medicine

The issue of removing life-support to brain dead individuals comes up in the news quite often. The families normally want to give more time; but the expert doctors want to turn the thing off, probably to save costs, and let the patient die.

‘Brain dead’ son enjoys Xmas after dad armed with gun refuses to let medics end his life'

This is a major problem when medicine becomes a know-it-all cult, as it is in the US. The medics will not accept their own mistakes; and this story which fortunately has a happy ending is often times not even out in the press; because the medics are able to sell their "expert opinion" to the public. Often this is with social pressure-several of them will be together when taking this decision; so the family members think that they have really some knowledge here. Unfortunately, they are being lied too with group pressure.

Keep this in mind when someone goes into coma next time, and if need be, move them to a new country rather than a country where medics have more control over a patient than their own family members.


Wednesday, December 23, 2015

Probability fudging-drug companies with too many vaccinations, airplanes safer than cars

In this post I cover some examples of probability fudging which goes on around us daily. The basic tenet of this post is:
When probabilities of two things are low (less than 1%), the comparison between these two things loses is a property of statistical distributions. If something is very rare, and something else is very very rare, it is difficult to compare them. You don't have much confidence in drawing conclusions.

HPV and rare disease Vaccinations

There is a lot of talk about Human Papillomavirus (HPV) vaccinations. Kids, especially girls, between the age of 10 to 15 years are recommended to get this vaccine. Let us look at the data, published by CDC here.

There are 79 Millions Americans (total population of about 300 Million) affected with HPV. There are 12 Million cases of new infections per year. Cancers attributed to HPV are 27000, of which 18000 are girls, the rest of 9000 being boys.

Since 1 in 4 Americans has the virus already, and 12 million get it every year, the virus itself can't be that bad. This is a classic case of measuring too much-if common bacteria presented in the mouth are measured, surefly 1 in 4 have some particular "infection"...most Americans get on with their lives just fine, and HPV infection, even if they don't know about it, doesn't seem to be a big deal in everyday life. From this data, it is more common than the common cold virus-and you begin to wonder how (and why) they collected this data at the first place. But let's trust the data for a moment anyway.

The cases where you have severe effects (cancers) are interesting to us, 27000. It is a large number, but looking at the overall population of HPV infected people (79 Million), it is a very small percentage, about 0.0034%.   Only 3 in 10000 people are getting cancers attributable to HPV.

The pharma companies say we can eliminate this tiny percentage of people getting cancers by injecting them with the HPV vaccine. The side effects of thee vaccine appear on the same page: Out of 67 million doses of vaccine, 25000 people reported some side effects, and 2000 of these were serious. The serious side effects are about 0.00025%, or about 0.25 in 10000. We must remember that many people may not report a problem even if their child has some side effects, so this number 25000 is likely to go up.

At first instance, it will look like the benefit of the vaccine, eliminating 3 in 10000 cancers, is about 10 times better than the serious side effects of the vaccine (0.25 in 10000). But these are very small percentages, do we have good reliability of such measurements? No. The confidence level at these probabilities is very low, and a vaccine needs to be at least a 100 times effective (than non vaccine) for it to be not drowned in statistical error.

If the disease is rare, like this HPV-cancer, does it make sense to vaccinate at all? Obviously what's rare and not rare is subjective, but to me, a disease which will going to happen to 3 in 10000 is quite rare, and we should not hurry to vaccinate kids against it. Couple that with the problem with this specific case where there's no clear indication that the HPV is causing the cancer (they are confusing correlation with causality, and assuming that the HPV vaccine with prevent cancers 30 years from now, which is very speculative an assumption) and you see that HPV should not be a mandatory vaccine.

When probabilities are very low, the right distribution to look at is the 1-x distribution. That is the statistical trickery these guys are doing to convince us of the wonderful effects of the vaccine. If x is small, less than 0.1% (1 in 1000), you must evaluate the risk of intervention causing more damage then the disease itself. Unless you have clear data that this does not happen, don't put vaccines (or other procedures)

Let us look at the 1-x distribution of the same data.

99.9964% will not develop a cancer related to HPV if they are not vaccinated.
99.99975% will develop a serious side effect if given a vaccine for HPV.

Everybody in their right mind can see that these are comparable numbers, and we do not need to vaccinate kids against HPV, because the risk of side effects is the in the same ball park as the benefit of taking the vaccine!

By focusing on the "x" distribution, the data is magnified; but in reality, the real distribution of interest is the 1-x, which is a stable distribution, and doesn't change much by vaccinating our children.

To make this more clear, let us look at other examples of daily life, where the 1-x distribution should be looked at, not the distribution of x.

Airplane and Car driving safety

Airplanes are safe, driving in cars is safe. Most people know this, and will take a plane or car ride from a place to another without thinking about safety-they will only worry about costs and the conveniences and inconveniences when comparing the two. However, you have all sorts of bad statisticians comparing airplane safety to car safety, and concluding that airplanes are safer (or unsafer) than driving. The error there is that the 1-x is the real distribution of interest: the probability of survival. That is maybe 99.95% over 10 years of car driving  to 99.99% for plane riding, and those two are similar, dont you think? One thing is 99.99% safe, the other is 99.95% safe...we can agree that they are both quite safe. Noone thought that planes are significantly safer or unsafer than cars. Both are safe, the 1-x is the real distribution.

When the benefits are doubtful, as is the case for HPV vaccines (that's why they are banned in Europe, a continent not exactly stupid), it gets even worse; you are putting unnecessary risk for these kids in vaccinating them.

But from statistics alone you can see that pharma companies are comparing the wrong distribution to sell their drugs.


Thursday, December 17, 2015

On allowing mergers of big companies-they should never be approved!

Recently Dow and Dupont signed an agreement to merge.
Big companies merge all the time in all countries. In almost all cases, this is bad for the country. Here's how to see this.

The most common argument used by companies to get approval from the Government (FTC, FDA, etc.) is that a larger company will be better scale, and economies of scale will lead to lower costs, which they will pass along to the customer in the form of lower prices.

They are telling half of the story right. The economies of scale will work to reduce costs, but they are not going to pass along the cost savings to the customer or the consumers! They will just keep the extra profit themselves.

The price of something is decided by the market demand. If a company is able to lower costs, it will keep the extra profit to itself. It will lower prices only when 1) there is competition, and/or 2) they believe that lower prices will lead to much larger volume, leading to  the net dollar value of the revenue (price x volume) being much larger than before. Since no one can be sure that the volume will increase on lowering prices, and it will need extra investment and hassle on the company's part to increase volumes, the safest bet is to keep prices unchanged; and that means they will just keep the extra cost savings to themselves. Only a foolish businessman passes along their extra cost savings to the customers; the intelligent one just keeps it himself!

What is more likely to happen when companies merge is that they will reduce competition, and therefore in reality increase prices for the consumers. It is like collusion; and only competition lowers prices. The larger the companies, the less the competition; and the more chances they have to collude and raise prices (easier to collude when there are 2 to 3 actors than when there are 10 to 20). Mergers almost always will result in higher prices for the consumers. They should never be approved.

The only exception where they can be approved are when the product is international-e.g. crude oil, copper, etc. Since there are many big competitors in other countries, it makes sense for commodities which are easily shippable worldwide to have large players at home as well. But this should be done only if we can buy foreign goods easily. In almost all cases, this is not true; therefore, mergers in general are bad for the country's consumers.

But here I just wanted to point out the fallacy of the argument of Economies of Scale - Lower Costs-Lower is simply Economies of Scale and Lower Costs, but not Lower Prices for the consumers. Those are two different things-lower costs are a benefit of economics of scale. But what lowers prices in the marketplace is competition. The producers always want to lower their costs and increase their profit margins; and they use bogus arguments to get the Governments and anti-monopoly organizations to pass  their mergers.

Taking out a competitor lowers competition, and therefore increases prices for the consumers.

Next time a trade body like the FDA or FTC of your country approves a merger, tell them this! Almost all countries in the Americas, both North and South, have a problem in the Telecom and Pharma Sector. The Telecom monopolies are really horrible for the country's consumer. This is why Carlos Slim is so rich-he has little competition, and Mexico has given him a license to screw over all Mexicans by having little or no competition.

Competition and presence of many actors lowers prices for consumers. Mergers do exactly the opposite.

This is also related to whose side the Government must take-the consumer or the producer? It must always be the consumer. Here's the blog post which explains this.