[BlindMath] When making a graph, when is it appropriate to log adjust the values on the y-axis?

[Godfrey, Jonathan]

In R, you have several choices.

For example:
Make new variables explicitly LogX = log(x) for natural logarithm.
Make the graph do the log on the axes as part of the graphing command plot(y~x, log="y")  to log the y axis. This keeps the original units but uses the log scale.


A common thing to do when points tend to be further and further apart, but still linear, is to log both axes

Jonathan

-----Original Message-----
From: BlindMath <blindmath-bounces at nfbnet.org> On Behalf Of Emily Schlenker via BlindMath
Sent: Friday, 14 February 2020 4:26 PM
To: Blind Math list for those interested in mathematics <blindmath at nfbnet.org>
Cc: Emily Schlenker <eschlenker at cox.net>
Subject: Re: [BlindMath] When making a graph, when is it appropriate to log adjust the values on the y-axis?

Hi. I am sorry it is not directly related to blindness, but when I asked my instructor why   students  would be asked to make a curve but the method she wants us to use makes a graph that is linear,  I  was second-guessing myself and thought maybe I was doing something wrong. The concentration and absorbance are directly related, so most likely the line is OK, and  the assignment is written in a confusing way. I remember seeing a lot of ecological and biological graphs before and after the log adjustment, and the difference was very interesting and it usually made for a very nice and neat curve. 
It is also hard to get good answers from those outside of the math department who expect math as part of the homework they assign, so thank you for clarifying some things and helping me to think through and solve this problem for myself.
I did this in Excel, but I plan to work with The same data using r this weekend, because that is the software I really want to learn more about.
Thank you.
Emily

Sent from my iPhone

> On Feb 13, 2020, at 9:07 PM, Godfrey, Jonathan via BlindMath <blindmath at nfbnet.org> wrote:
> 
> Hi,
> 
> You use the phrasing "linear graph" which ought to mean the points lie on (roughly) straight line. I'm guessing that isn't the case though.
> 
> If that was so, then you wouldn't normally make any transformations because the relationship is already the easiest one to work with.
> 
> A log transformation only helps if the relationship is (roughly) a curve, and usually it has to be monotonic.
> 
> The way you do the actual transformation is then dependent on the software you are using. Watch out for the distinction between natural log and log base ten, which is preferred in some disciplines or contexts.
> 
> So, you'll probably need to provide a little more information to get the most help from this community. I'd probably note that your question isn't (yet) one of blindness, but I'm currently stuck in a tedious meeting so thought to get some quick feedback to you.
> 
> HTH
> Jonathan
> 
> -----Original Message-----
> From: BlindMath <blindmath-bounces at nfbnet.org> On Behalf Of Emily 
> Schlenker via BlindMath
> Sent: Friday, 14 February 2020 3:44 PM
> To: blindmath at nfbnet.org
> Cc: Emily Schlenker <eschlenker at cox.net>
> Subject: [BlindMath] When making a graph, when is it appropriate to log adjust the values on the y-axis?
> 
> Hi, everyone. After passing calculus last semester with an A, I just cannot look at math the same way I used to. I am working on a graph for one of my biology labs, and it just looks weird. The handout states that we are to make a standard curve where we plot absorption values from spectrophotometry on the Y axis and different concentrations on the X axis in micrograms per milliliter. The problem is, this makes a linear graph that definitely is not a curve, and I’m wondering if it would be better to do some type of adjustment on the y-axis so that it is more user-friendly. I have seen this done on graphs before. When is it appropriate to log adjust the Y values, and how exactly is this done?
> Thank you for any help.
> Emily
> 
> Sent from my iPhone
> 
> _______________________________________________
> BlindMath mailing list
> BlindMath at nfbnet.org
> http://nfbnet.org/mailman/listinfo/blindmath_nfbnet.org
> To unsubscribe, change your list options or get your account info for BlindMath:
> http://nfbnet.org/mailman/options/blindmath_nfbnet.org/a.j.godfrey%40m
> assey.ac.nz BlindMath Gems can be found at 
> <http://www.blindscience.org/blindmath-gems-home>
> _______________________________________________
> BlindMath mailing list
> BlindMath at nfbnet.org
> http://nfbnet.org/mailman/listinfo/blindmath_nfbnet.org
> To unsubscribe, change your list options or get your account info for BlindMath:
> http://nfbnet.org/mailman/options/blindmath_nfbnet.org/eschlenker%40co
> x.net BlindMath Gems can be found at 
> <http://www.blindscience.org/blindmath-gems-home>


_______________________________________________
BlindMath mailing list
BlindMath at nfbnet.org
http://nfbnet.org/mailman/listinfo/blindmath_nfbnet.org
To unsubscribe, change your list options or get your account info for BlindMath:
http://nfbnet.org/mailman/options/blindmath_nfbnet.org/a.j.godfrey%40massey.ac.nz
BlindMath Gems can be found at <http://www.blindscience.org/blindmath-gems-home>