When Only 80% Of Computers Having Viruses Is Considered A Good Thing

from the ouch dept

The headline of this story sounded like good news at first, claiming: Fewer computers infected with virus. Then you read the details, and realize they’re saying that the number of virus infected computers in China has dropped from 88% to just 80% — and you have to wonder just what folks are doing there to have so many viruses. Given China’s ability to control so much of the internet in that country, you would think that part of those efforts would go towards trying to block viruses. Apparently not.

Rate this comment as insightful
Rate this comment as funny
You have rated this comment as insightful
You have rated this comment as funny
Flag this comment as abusive/trolling/spam
You have flagged this comment
The first word has already been claimed
The last word has already been claimed
Insightful Lightbulb icon Funny Laughing icon Abusive/trolling/spam Flag icon Insightful badge Lightbulb icon Funny badge Laughing icon Comments icon

Comments on “When Only 80% Of Computers Having Viruses Is Considered A Good Thing”

Subscribe: RSS Leave a comment
dorpus says:

Confidence Interval?

I would want to know the 95% CI on that. There is the concept of Risk Function — mathematically, it is very difficult to prove whether a coin flip has a 50% chance of heads, or a 55% chance of heads.

To determine probability, our intuition may tell us to flip 100 times and count the number of heads, i.e. use the sample proportion. However, it can be shown mathematically that it is better to artificially add 3 heads and 3 tails to our counts, if we are confident that the true probability is close to 50%. Our estimate will be about 11% more accurate this way.

antigone says:

Re: Re: Re: Confidence Interval?

By using a higher confidence interval, you’re less likely to make a Type II error, which is a really stupid thing to make – to claim something is statistically significant when it isn’t. It’s like the commercial for the prescription for Detrol LA. When you actually look at the reports for it, the medication really didn’t do anything that was significant.

And the 95% CI is a typical cutoff for estimating unusual values.

dorpus says:

Re: Re: Re:2 Confidence Interval?

Actually, that’s a Type I error, when you conclude that something is significant (when it isn’t). A Type II error will conclude the effect is insignificant, when in fact it is significant.

The probability of not making a Type II error, i.e. correctly finding significance, is known as “power”.

95% CI has been the gold standard for much of scientific research for many years. It’s saying that if we were to repeat the experiment at the same scale, we have a 95% chance of reaching the same conclusion. Here, the 95% is known as the “size” of the test. One can perform 90% CI in situations where the results are inexact, or 99% CI’s in situations that demand more precision.

Add Your Comment

Your email address will not be published. Required fields are marked *

Have a Techdirt Account? Sign in now. Want one? Register here

Comment Options:

Make this the or (get credits or sign in to see balance) what's this?

What's this?

Techdirt community members with Techdirt Credits can spotlight a comment as either the "First Word" or "Last Word" on a particular comment thread. Credits can be purchased at the Techdirt Insider Shop »

Follow Techdirt

Techdirt Daily Newsletter

Techdirt Deals
Techdirt Insider Discord
The latest chatter on the Techdirt Insider Discord channel...