Sampling Errors

"In statistics, sampling error or estimation error is the error caused by observing a sample instead of the whole population."

--Copy-pasted from Wikipedia

Or we could say, "counting the hits but not the misses".

In the real world, sampling errors are common. One that we observe daily, albeit unconsciously, normally in the media, is one that I would call a forced sampling error. For example, a biased news report may cite "many people disliking [insert topic here]", followed by quotes from respondents. Unfortunately, it is not an obligation that ALL respondents are quoted; it might even be the case that only those who are known to be in favour of the bias are interviewed, i.e. it is possible that the opinion of an entire population is wrongly portrayed by a (possibly) erroneous sample, due to the fact that a sample is only a part of the entire population.

You might want to note that this is a very powerful tool of propaganda; in WWII, Nazi advertisements of inmates in concentration camps were portrayed as well-fed, enticing the Aryan population to expose Jews without guilt. Or when a Jew commits a crime, the media does not fail to ensure that it is known nationwide so that "Jew" was synonymous to "criminal".

In North Korea today, visiting journalists and tourists are brought to model cities, farms, etc., portraying the economy as being well-off and developed, despite defector testimony strongly suggesting otherwise.

So, how is this related to Malaysian chess? Frankly speaking, not much. But lately, there is one example.

If you manage to reach the third paragraph without your head exploding, you will see that the sample in this case was one parent. Statistically, this is an impossible sample to work with.

Ilham, have you been tricked?