0

Possible Duplicate:
When are Log scales appropriate?

Say you have a bar graph displaying data, for example, "Cost of Computer Orders by Population", and you are trying to analyze the data and find a distribution. The information does not indicate anything so you take the logarithm of the variable and the graph then resembles a normal distribution. What does taking the logarithm of the information indicate?

Community
  • 1
Masterminder
  • 101
  • 2
  • have you tried to read [this](http://en.wikipedia.org/wiki/Logarithmic_scale#Motivation)? – user603 Jan 26 '13 at 03:06
  • This question isn't perfectly clear. Can you say more about what you're asking? What kind of answer are you looking for? Eg, do you want to know why a variable might be log-normally distributed, or the effect of the transformation, etc? – gung - Reinstate Monica Jan 26 '13 at 16:20
  • For lots of information about this topic, please use our [search](http://stats.stackexchange.com/search?q=%2Blogarithm+%2Binterpretation). – whuber Jan 26 '13 at 20:01

0 Answers0