The state where I lived has a good reputation for its freezing weather. Even the first snow of this year looked formidable. The sliding snow flakes, the grayish sky, and piercing winds were depressing. In a winter day like this, something miserable might happen easily.

I was surfing the internet, reading news and killing my time. My head was full of thoughts, or more precisely, it was like hundreds of horses tramping my brain. I should do something to rein those horses.

Meditation! This should work.

(more…)

Longevity is a fluid concept. One hundred years ago, 80 years of age were thought as eternity, while now we are targeting 100 years of age. How amazing it is!

It is science that raises our hope. The Time magazine two weeks ago featured Dr. Andrew Weil’s integrative medicine, a new medicine to extend the life. However, in the 125th anniversary of Science magazine, the topic whether we can find a way to live longer was listed as one of the major unknown questions.

Biological observations suggest that three mechanisms may be involved in longevity: restricting calorie intake, preventing oxidative damage , and reducing insulin-like growth factor-I in your body. These factors are surely interconnected although how they do it is largely uncertain.

(more…)

An Iceland company recently announced a cardiovascular drug which targets a gene variant common in European descendents but uncommon in African Americans. The gene variant, or polymorphism, has been associated with a higher risk of heart attack among African Americans but not among European descendents.

This gene variant is very interesting in that it is associated with a more active response to the inflammation. In one way, it is protective because it fights against inflammation. On the other hand, the inflammation hypothesis in the etiology of cardiovascular diseases suggests that the chronic inflammation may cause the plaque build-up in the arterial walls. Furthermore, the acute inflammation in the plaque spot may trigger the rupture of the plaque, thus leading to a heart attack. The active form of the gene variant may not be good to your heart.

(more…)

禽流感，今天是个令人恐慌的词，因为他与“人流感”联系了起来。如果我们用过去常说的“鸡瘟”一词（鸡瘟还包括其他疾病）就使人自然而然地生出一种安全感。毕竟是鸡的瘟疫，与人何干？

过去鸡瘟时，因为穷没肉吃，很多人都吃瘟鸡肉，但更多的是说不能吃瘟鸡肉。当然还更多的是鸡一生病人就生病。不过从来没有人调查过这些事。

这次鸡瘟（也包括鸭瘟，鸟瘟），传的病毒与往年不同。这次是毒性比较大的Ｈ５系列。鸡鸭的病死率非常高。同时这病毒一到人身上，病死率现在是５０％。万一这病毒获取了人传人的绝秘法术，岂不是个１９１８大流行的重现？全球恐慌情有可原。

最近在中国湖南，毛主席的故乡，出了三个肺炎。不是ＳＡＲＳ，不是肺琏球菌感染，也不是支原体。大家只推测是病毒性肺炎。那是什么病毒？

难道是流感病毒？Ｈ１阳性，Ｈ２阳性，一男孩Ｈ５可疑阳性！一女孩死亡后当天火化，病因未知。一教师痊愈，病因未明。

当地同时也出现了禽内Ｈ５流感流行。病人和瘟鸡鸭也过接触史。

卫生部首次通报：湖南三起肺炎与禽流感无关。
几天后，卫生部再次通报：湖南三起肺炎，有一例可疑Ｈ５阳性。欢迎ＷＨＯ指导。

(原报道见http://weblogflu.blogspot.com)

这是怎么回事？

首先应该恭喜媒体的报道能力。媒体能够发掘出湖南农村的三起肺炎并及时报道。和SARS时期的报道水平，这次有了很大的提高。

但是反观当地政府和卫生部门，我不竟有点担心。

我认为当地的医院是负责任的，他们对这三起病例还是比较及时通报了有关卫生部门。当然他们有经验不足的地方。比如没有留样本，血清检查没有过关。病人处理不是最妥。但是由于是全国第一批病人，又是普通乡村医院，我们不能苛求过多。

但是当地行政部门和卫生防疫部门的管理水平却是有很大的问题。传染病的一般流程是基层医院发现病例后必须及时上报，当地的卫生防疫部门必须对传染隔离，取样留样和分析负全责。这次地方卫生部门在这方面做的确实不如人意。

到目前为止，我不知道当地行政部门到底如何应对此事。但是从当天就火化病死的小女孩做法来看，行政部门恐怕施加了一定的压力。这就反映出地方政府有可能怀疑是人感的禽流感，企图毁灭证据来推卸责任的可能。

国家卫生部的做法更是不妥。对禽流感首次通报反映出中央对这次流感不够重视，没有接受ＳＡＲＳ教训，过分相信地方报告。

每一次疾病的流行，地方政府和卫生部门是最重要的一环。为什么地方部门会隐瞒疫情，压而不报？我认为关键是把疾病流行程度和地方官员的仕途联系过紧，中央搞一刀切。行政部门不懂得疾病流行的自然规律，比如在ＳＡＲＳ流行期间，凡是有新发ＳＡＲＳ的地方，基层干部就被认为是防治不力，一律会受到降职甚至撤职。这种做法的直接后果就是地方隐瞒疫情，从而错过在第一时间内控制疾病的传播。

控制疾病流行不能靠蛮干和行政乱干预。不能因为ＳＡＲＳ大流行的特殊期间的特殊做法来推断对新的流行必须采取“严防死守” 和“一刀切”。这种高压政策下只会不利于疾病流行的控制。

在新的挑战来临之前，我们需要理解和配合。行政和卫生部门，上级和下级，干部和群众，我们都需要一个和谐的环境来接受这个挑战。

We sleep everyday for 6~8 hours, mostly during the night. Why do people sleep and sleep so much? It is always an intriguing question. Isn’t that nice if we can skip the sleep and play 24/7? Our lives would be a whole lot different, that’s for sure.

Well, every breathing human being knows that we need sleep to rest and to recover our energy and intelligence. Sleep deprivation is second to food deprivation to damage your health.

The critical question is how much we need sleep? 8 hours’ sleep makes you stupid, as Napoleon I once commented. But 5 hours seem too little. At least I can’t stand it.

(more…)

Paul Krugman in today’s NYT is selling his national health insurance idea again. He reiterated the rationales those liberals had promoted ten years ago. Former president Clinton, and in particular Hillary Clinton, also strongly support this view. In fact, it was Hillary who drove the national health insurance movement in 1993.  For this, I will support Hillary to go for president in 2008. -:)

I am a firm believer of national health insurance. I was and am still deeply disturbed by the mistake of crushing the health system for peasants (accuse Deng Xiao Ping for this).  Yes, I once believed that everything during old days was wrong, but now I am more critical. I believe that only national health insurance can provide health care to its people. It is the responsibility of the government to ensure its people’s health.  Private health plan can serve as a supplement to the national insurance, but nothing more.

(more…)

I found that spotting English mistakes is a great way to learn English. Here is another example (from People’s Daily, 110605):

Death rate of myocardial infarction higher among Beijing’s middle-aged

This is very confusing. I am not sure whether the reporter was quoting death from myocardial infarction (MI), or death rate among those who suffered from MI. About 30% MI patient will not die after a heart attack. Besides, heart attack is used more often in popular newspaper than myocardial infarction does. The word “higher” is also not accurate and too descriptive.

The mortality rate of myocardial infarction rose by 154 percent among people between 35 and 44 years of age in Beijing in the past 15 years, a Chinese expert has disclosed, calling on people to adopt a more healthy lifestyle.

There is an obvious grammatical error (they didn’t use spell check?). “More healthy” should be “healthier.” The “a Chinese expert” is a typical Chinglish. Better to say “a Chinese researcher.” I am not sure whether “has disclosed” should be “disclosed.”

(more…)

Here is a very enlightening email post about working on large dataset, written by William Gould, the CEO of Statacorp, the maker of Stata.

Basically, working on dataset at the scale of 10 millions may cause numerical and substantive problems:

1) Precision problem: when the number of observation is large, even the basic calculation such as summation may be wrong. Each time you lost some very tinny thing due to computer limit, you may end up with a big deviance in the final summation.
2) Matrix operation thus may be inaccurate due to the inaccuracy.
3) For a large sample, standard error for estimates may not have the usual meaning. The standard error (=standard deviation/sqtr(nobs)) is very small. On the other hand, the estimates may be the population you are working on. So where is the uncertainty for the hypothesis testing?

Therefore, the solutions are:
1) Be cautious.
2) Use a manageable random subsample to test the model
3) Make sure you have roughly equal means and standard deviation in all x and ys. (But how about discrete variables?)

Anyway, I have been working on large datasets for a while. My data usually accumulates millions of observations. I am fully aware of precision problem as I am a nonbeliever of computer. I also fully agree with Bill about the issue of population representativeness in large datasets.

However, even inference from the national dataset, which one can say this is the population for the year, still has merit of hypothesis testing. We usually use the sample years to extrapolate, or predict, the future. The total population in this case is the 10 years or even 20 years of national records. The prediction makes sense, and the confidence interval for the prediction is appropriate.

On the other hand, the small standard error creates a trap for exploratory analysis. With large datasets, everything will be significant. A nonsignificant coefficient or comparison may be truly nonessential, but a significant one doesn’t mean important. Unfortunately, this has been intentionally or unintentionally ignored in many surprising findings in the top notch journals. Examples include numerous false reports about the effect of vitamins and nutrients on health.

Another thing may occur in the large dataset is that you always have anomalies. You can exclude them by capping and flooring the variable values. However, there may have hidden patterns in these anomalies and missing values.

One nice feature of large dataset, of course, is that all the large sample theory, the asymptotic stuff, is satisfied. There is not much difference whether you do a frequentist analysis of Bayesian analysis.

Today’s Wall Street Journal had an opinion piece written by the John Hopkins epidemiologist Donald S. Burke. He had a similar proposal as I had. He emphasized that the US should reach out to help the Southeast Asian combat the avian flu. He suggested that during the initial stage of the pandemic, the US should send antivirus drugs and vaccine to the infected countries. Stockpiling drugs and vaccines are important, but quenching the disease in the first place is more important.

He also explained that the virus can either exchange genetic materials with existing human virus, or directly evolved into a lethal human one. His view again is the same as mine (as professionals always do ^_^) . We don’t know where and when the virus may leap to human and spread among humans, but we can stop it if we are prepared.

Today I received an email from one of my old neighbors in which she prayed and asked me to pray for the almighty God. In the attachment, I was informed that the center of the Bible is the God’s secret message:

It is better to take refuge in the Lord than to trust in man.” –Psalm 118:8

I like this verse. It says that even in old old days, people couldn’t trust each other. They had to resort to the mysterious God to appease their mind.

It also intrigues me whether the center verse of the Bible is indeed Psalm 118:8. I did a Google search on this. It turns out that it is approximately true. I assure you here that God do play probability because He invent the probability too.

The first comment is very interesting. When we talk about the center piece of the Bible, which Bible are we referring to? Certainly not the Hebrew one, or Catholic ones, or the modern one we nowadays use. It is probably the King James Version.

The shortest chapter is Psalm 117, and the longest is Psalm 118. There are 594 chapters before Psalm 118, and 594 chapters after. In the KJV, there are 31,174 verses in the bible and the center piece is in the Psalm 118. BUT, the number of verses is an even number, so there is no center verse after all.

In fact, the center verses (median) would be within these two:

It is better to take refuge in the Lord than to trust in man.

It is better to take refuge in the Lord than to trust in princes.

Anyway, these two verses express the same thing: trust the Lord instead of mortal things.

Digging things in the Bible is fun, as one of my colleagues joked: “We don’t need to do research. Everything is in the Bible. You just need to find it.”