1. ## lg10 versus ln

Hi there,

I have a log transformation question. At school, we always used the ln() function in SPSS, but I recently found out that there is a LG10() function as well.

When would you use one over the other?

2. ## Re: lg10 versus ln

It doesn't matter.

ln is natural log so it uses base 'e' (approximately 2.718282). LG10 I'm assuming is log with a base of 10. Those functions are a constant multiple of each other.

ln(x) = LG10(x)*ln(10)

and ln(10) is approximately 2.302585 so you could say ln(x) = 2.302585 * LG10(x)

So the transformation has the exact same impact on the shape of the result but one will be a constant multiple larger. So it's like asking when you would use "feet" over "meters". The answer being when it's more convenient or when you feel like it.

3. ## The Following User Says Thank You to Dason For This Useful Post:

Jazz3 (03-21-2017)

4. ## Re: lg10 versus ln

ln() is the Natural logarithm (base e) while LG10() is the logarithm (base 10). In statistics, you are typically just using the logarithm to transform your data, either to make it more normal, or to linearize a relationship between two variables. In these cases it really does not matter which you use. However, in some fields such as engineering or economics, the natural log can be more easily interpreted as approximate proportional differences.

5. ## The Following User Says Thank You to Miner For This Useful Post:

Jazz3 (03-21-2017)

6. ## Re: lg10 versus ln

Thanks people, very clear haha

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts