How to Lie with statistics

There are three types of lies: lies, damned lies and statistics-Disreli

We are presented with graphs and statistics every day. "Most SEOs that keywords in the title tag is a factor important rank. "spending on search to increase by $ 10B. have you ever this sense of what you will be presented with sounds reasonable, but the conclusion is simply not logical?

Here are some common ways people attempt to pull the wool over your eyes with some statistics will be familiar if you have more, add 'em comments:)

1. built in BiAS

Eksempeldatæne supports an obvious dagsorden. f. eks formula that is practically a to display a chart that displays your product have produced negative results.Try to determine the difference between local time for the person or organization that presents data presented-"what would you want to listen to" ask yourself, "what data does not appear to me?"

2. the average

The media loves to indicate "instrument" and then fails to tell them what average, we are talking about.

For example, the average price for a residential area is 500 K and 200 K, depending on the type of average use could refer either the mean, median or mode. mix well, depending on what conclusion you wish to achieve.

3. Inadequate sample size

20% Web Designer makes over $ 1 m may be the case if the sample size was made up of ten highest bonustype people in the industry, and two people just happens to have a great year, but what if the sample size for all those who practice Web design for life; the result may be different.

4. No meaningful

A difference is only a difference if you make a difference. Potential employee Jill might have an IQ of over 120 and potential employee Jack can have a 118 IQ, but really means something? what if Jill has a problem and Jack is a great conversationalist; what would be better to rent?

5. Oh my God!