Omitted Variable Fraud As A Propaganda Method

Omitted Variable Bias (wikipedia)

The idea is simple – though the wikipedia uses a needlessly complicated explanation:

You leave out an important factor in your base data so you arrive at the – sometimes desired – false causality. Real life example: Germany has 30 million ethnic German men. You import a million or two Muslims. Rape rate goes up. Now you say, we can’t distinguish between German and imported Muslim men because that would be discriminatory so we don’t. All men have become more rapist. Claim our feminists.

But if you look at the respective group behaviour the different rates become obvious. We witnessed that during the Cologne attacks. That’s behaviour never observed under Germans. The increased rape rate is entirely imported. For whatever reason that imported population is more rapey.

So the media and leftist sociologists and agitators consciously try to wipe out the distinction and can then claim their desired false causality which will lead to false measures.

This tactic is based on politcal correctness, non-discrimination. Now what does the word “to discriminate” mean? It means “to distinguish” or “to classify”; nothing more. Back in the 1970ies there was a simple logic device you could buy called a “discriminator” which would classify a 4 bit input value into whether it falls below or above a threshold; it’s probably still called the same because electrical engineers have no concept of political correctness.

So that’s why the Left will also cry foul once you point out how the gun crime rate in the USA is different between white-on-white, black-on-black and so on. They don’t want you to analyse that by group. That’s discriminatory.

It is, though, the obviously qualitatively superior analysis. If you have the data, you must do it – or you are guilty of Omitted Variable Fraud. The milder form is Omitted Variable Bias – where the researcher can believably claim ignorance of the clustering in his data.

So remember: Every time they don’t like how you subdivide your data into groups for political correctness reasons, they KNOW the result would go against their agenda.

The Left / the MSM is anti-scientific whenever they want to be.

Race And GDP/capita

Thinking further: In 1965 the USA decided to become a non-white nation and changed their immigration rules. Since that time, non-white population rises (black population as a percentage stayed constant by the way) – and GDP growth rate dropped over decades and is now at zero.

Relating the GDP growth rate to racial makeup is racist, right? Well then stop right there, we can’t do THAT now can we?

Of course we can. And we should if we want to AVOID omitted variable fraud. As I’ve told you know, you cannot claim ignorance anymore – if you want to analyze what the reason for the collapse in US GDP growth is, you MUST now take this as a candidate.

It does not necessarily have to be the right explanation of course. Other candidates would be trade deficit, debt as percent of GDP and so on.

So how do you find out what causality might actually be there in a non-obvious case? You do a test for Granger causality (an econometrics technique). Unfortunately it looks like econometrists are a very politically correct bunch and nobody applied the technique relating racial composition to GDP growth. Well, they live in Academia and just can’t afford to obviously.

So, we should say: Western Science commits an Omitted Variable Fraud here.

Why do I even get the idea that race and GDP growth might be related? Well simple. Post Apartheid South Africa gave me the idea.

Chart: GDP/capita SA (wikipedia)





Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s