Impaired boxplot functionality - mean instead of median

"Evgeniy" == Evgeniy Kachalin <ka4alin at yandex.ru>
    on Thu, 01 Dec 2005 19:04:47 +0300 writes:

Hello to all users and wizards.

I am regulary using 'boxplot' function or its analogue - 'bwplot' from
the 'lattice' library. But they are, as far as I understand, totally
flawed in functionality: they miss ability to select what they would
draw 'in the middle' - median, mean. What the box means - standard
error, 90% or something else. What the whiskers mean - 100%, 99% or
something else.
Is there any way to realize it? Or is there any other good data
visualization function for comparing means of various data groups?
Ideally I would like to have a bit more customised function for doing
that. For example, 'boxplot(a~b,data=d,mid='mean').


--
Evgeniy, ICQ 38317310.

Boxplots were invented by John W. Tukey and I think should be
counted among the top "small but smart" achievements from the
20th century.  Very wisely he did *not* use mean and standard deviations.

Even though it's possible to draw boxplots that are not boxplots
(and people only recently explained how to do this with R on this
 mailing list), I'm arguing very strongly against this.

If I see a boxplot - I'd want it to be a boxplot and not have
the silly (please excuse)  10%--------90% whiskers  which
declare 20% of the points as outliers {in the boxplot sense}.

If you want the mean +/- sd plot, do *not* misuse boxplots
for them, please! 

Boxplots were invented by John W. Tukey and I think should be
counted among the top "small but smart" achievements from the
20th century.  Very wisely he did *not* use mean and standard deviations.

Even though it's possible to draw boxplots that are not boxplots
(and people only recently explained how to do this with R on this
 mailing list), I'm arguing very strongly against this.

If I see a boxplot - I'd want it to be a boxplot and not have
the silly (please excuse)  10%--------90% whiskers  which
declare 20% of the points as outliers {in the boxplot sense}.

If you want the mean +/- sd plot, do *not* misuse boxplots
for them, please! 

Martin Maechler, ETH Zurich

"Evgeniy" == Evgeniy Kachalin <ka4alin at yandex.ru>
   on Thu, 01 Dec 2005 19:04:47 +0300 writes:

    Evgeniy> Hello to all users and wizards.
    Evgeniy> I am regulary using 'boxplot' function or its analogue - 'bwplot' from 
    Evgeniy> the 'lattice' library. 

 [there's the lattice *package*  !]

    Evgeniy> But they are, as far as I understand, totally 
    Evgeniy> flawed in functionality: they miss ability to select what they would 
    Evgeniy> draw 'in the middle' - median, mean. What the box means - standard 
    Evgeniy> error, 90% or something else. What the whiskers mean - 100%, 99% or 
    Evgeniy> something else.
    Evgeniy> Is there any way to realize it? Or is there any other good data 
    Evgeniy> visualization function for comparing means of various data groups? 
    Evgeniy> Ideally I would like to have a bit more customised function for doing 
    Evgeniy> that. For example, 'boxplot(a~b,data=d,mid='mean').


    Evgeniy> -- 
    Evgeniy> Evgeniy, ICQ 38317310.

Martin Maechler ??????????:

Boxplots were invented by John W. Tukey and I think should be
counted among the top "small but smart" achievements from the
20th century.  Very wisely he did *not* use mean and standard deviations.

Even though it's possible to draw boxplots that are not boxplots
(and people only recently explained how to do this with R on this
 mailing list), I'm arguing very strongly against this.

If I see a boxplot - I'd want it to be a boxplot and not have
the silly (please excuse)  10%--------90% whiskers  which
declare 20% of the points as outliers {in the boxplot sense}.

If you want the mean +/- sd plot, do *not* misuse boxplots
for them, please!

So I analize genetics data. I have some factor (gene variant, c(1,2,3))
and the quantitative variable corresponding to that factor. How do I
visualize this situation? Compare mean of samples corresponding to
factor values?

Should boxplot support 'mean-in-the-middle', it would fit my needs
ideally. How do I plot mean +/- SD plot?

Also there is a way to rewrite boxplot.stats and replace "fivenum" there
for self-made function. Then I would need to write self-made
boxplot.formula (or boxplot.default?) function. And all this stuff would
not be configurable. I'm still novice in R, so I need simple way to
pre-visualize my data and estimate approximate result.

Martin Maechler Ð¿Ð¸ÑˆÐµÑ‚:

Boxplots were invented by John W. Tukey and I think should be
counted among the top "small but smart" achievements from the
20th century.  Very wisely he did *not* use mean and standard deviations.

Even though it's possible to draw boxplots that are not boxplots
(and people only recently explained how to do this with R on this
 mailing list), I'm arguing very strongly against this.

If I see a boxplot - I'd want it to be a boxplot and not have
the silly (please excuse)  10%--------90% whiskers  which
declare 20% of the points as outliers {in the boxplot sense}.

If you want the mean +/- sd plot, do *not* misuse boxplots
for them, please! 

So I analize genetics data. I have some factor (gene variant, c(1,2,3))
and the quantitative variable corresponding to that factor. How do I
visualize this situation? Compare mean of samples corresponding to
factor values?

Should boxplot support 'mean-in-the-middle', it would fit my needs
ideally. How do I plot mean +/- SD plot?

Also there is a way to rewrite boxplot.stats and replace "fivenum" there
for self-made function. Then I would need to write self-made
boxplot.formula (or boxplot.default?) function. And all this stuff would
not be configurable. I'm still novice in R, so I need simple way to
pre-visualize my data and estimate approximate result.

I'd like to add two comments to Martin's sensible response.

1. I've seen several intro-stats textbooks that define a
boxplot to have whiskers to the extreme data values
and then define Tukey's boxplot as a "modified" boxplot.
I wish authors wouldn't do that.

2. I've also seen boxplots used for sample sizes as small
as -- are you ready for it? -- n = 2!! (Admittedly, only in
plots comparing several groups.) The help page for
stripchart() points out that stripcharts "are a good
alternative to boxplots when sample sizes are small".
My own rule-of-thumb: n > 20 for single boxplots, n > 12
for multiple boxplots.

Peter Ehlers

Martin Maechler wrote:

 

Boxplots were invented by John W. Tukey and I think should be
counted among the top "small but smart" achievements from the
20th century.  Very wisely he did *not* use mean and standard deviations.

Even though it's possible to draw boxplots that are not boxplots
(and people only recently explained how to do this with R on this
mailing list), I'm arguing very strongly against this.

If I see a boxplot - I'd want it to be a boxplot and not have
the silly (please excuse)  10%--------90% whiskers  which
declare 20% of the points as outliers {in the boxplot sense}.

If you want the mean +/- sd plot, do *not* misuse boxplots
for them, please! 

Martin Maechler, ETH Zurich


   

"Evgeniy" == Evgeniy Kachalin <ka4alin at yandex.ru>
  on Thu, 01 Dec 2005 19:04:47 +0300 writes:
             

   Evgeniy> Hello to all users and wizards.
   Evgeniy> I am regulary using 'boxplot' function or its analogue - 'bwplot' from 
   Evgeniy> the 'lattice' library. 

[there's the lattice *package*  !]

   Evgeniy> But they are, as far as I understand, totally 
   Evgeniy> flawed in functionality: they miss ability to select what they would 
   Evgeniy> draw 'in the middle' - median, mean. What the box means - standard 
   Evgeniy> error, 90% or something else. What the whiskers mean - 100%, 99% or 
   Evgeniy> something else.
   Evgeniy> Is there any way to realize it? Or is there any other good data 
   Evgeniy> visualization function for comparing means of various data groups? 
   Evgeniy> Ideally I would like to have a bit more customised function for doing 
   Evgeniy> that. For example, 'boxplot(a~b,data=d,mid='mean').


   Evgeniy> -- 
   Evgeniy> Evgeniy, ICQ 38317310.

-----Original Message-----
From: r-help-bounces at stat.math.ethz.ch 
[mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of 
Michael H. Prager
Sent: Thursday, December 01, 2005 10:11 AM
To: r-help at stat.math.ethz.ch
Subject: Re: [R] Impaired boxplot functionality - mean 
instead of median

All--

Would someone kindly post the reference to Tukey's formula 
for a boxplot 
without whiskers?

I am looking at his book "Exploratory Data Analysis" from 1977.  The 
index includes "box-and-whisker" plot but not "boxplot."  On 
page 39-40 
construction of the plot is described, including the statements: "We 
draw a long, thinnish box that stretches from hinge to hinge, 
crossing 
it with a bar at the median.  Then we draw a 'whisker' from 
each end of 
the box to the corresponding extreme."

MHP


on 12/1/2005 11:57 AM P Ehlers said the following:

I'd like to add two comments to Martin's sensible response.

1. I've seen several intro-stats textbooks that define a
boxplot to have whiskers to the extreme data values
and then define Tukey's boxplot as a "modified" boxplot.
I wish authors wouldn't do that.

2. I've also seen boxplots used for sample sizes as small
as -- are you ready for it? -- n = 2!! (Admittedly, only in
plots comparing several groups.) The help page for
stripchart() points out that stripcharts "are a good
alternative to boxplots when sample sizes are small".
My own rule-of-thumb: n > 20 for single boxplots, n > 12
for multiple boxplots.

Peter Ehlers

Martin Maechler wrote:

 

Boxplots were invented by John W. Tukey and I think should be
counted among the top "small but smart" achievements from the
20th century.  Very wisely he did *not* use mean and 

standard deviations.

Even though it's possible to draw boxplots that are not boxplots
(and people only recently explained how to do this with R on this
mailing list), I'm arguing very strongly against this.

If I see a boxplot - I'd want it to be a boxplot and not have
the silly (please excuse)  10%--------90% whiskers  which
declare 20% of the points as outliers {in the boxplot sense}.

If you want the mean +/- sd plot, do *not* misuse boxplots
for them, please! 

Martin Maechler, ETH Zurich


   

"Evgeniy" == Evgeniy Kachalin <ka4alin at yandex.ru>
  on Thu, 01 Dec 2005 19:04:47 +0300 writes:
             

   Evgeniy> Hello to all users and wizards.
   Evgeniy> I am regulary using 'boxplot' function or its 

analogue - 'bwplot' from 

   Evgeniy> the 'lattice' library. 

[there's the lattice *package*  !]

   Evgeniy> But they are, as far as I understand, totally 
   Evgeniy> flawed in functionality: they miss ability to 

select what they would 

   Evgeniy> draw 'in the middle' - median, mean. What the 

box means - standard 

   Evgeniy> error, 90% or something else. What the 

whiskers mean - 100%, 99% or 

   Evgeniy> something else.
   Evgeniy> Is there any way to realize it? Or is there 

any other good data 

   Evgeniy> visualization function for comparing means of 

various data groups? 

   Evgeniy> Ideally I would like to have a bit more 

customised function for doing 

   Evgeniy> that. For example, 'boxplot(a~b,data=d,mid='mean').


   Evgeniy> -- 
   Evgeniy> Evgeniy, ICQ 38317310.

On Thu, 2005-12-01 at 19:40 +0300, Evgeniy Kachalin wrote:

Martin Maechler ??????????:

So I analize genetics data. I have some factor (gene variant, c(1,2,3))
and the quantitative variable corresponding to that factor. How do I
visualize this situation? Compare mean of samples corresponding to
factor values?

Should boxplot support 'mean-in-the-middle', it would fit my needs
ideally. How do I plot mean +/- SD plot?

Also there is a way to rewrite boxplot.stats and replace "fivenum" there
for self-made function. Then I would need to write self-made
boxplot.formula (or boxplot.default?) function. And all this stuff would
not be configurable. I'm still novice in R, so I need simple way to
pre-visualize my data and estimate approximate result.

If you want means and SDs, you might want to look at:

1. plotCI() and plotmeans() in the gplots package

I'd like to add two comments to Martin's sensible response.

1. I've seen several intro-stats textbooks that define a
boxplot to have whiskers to the extreme data values
and then define Tukey's boxplot as a "modified" boxplot.
I wish authors wouldn't do that.

2. I've also seen boxplots used for sample sizes as small
as -- are you ready for it? -- n = 2!! (Admittedly, only in
plots comparing several groups.) The help page for
stripchart() points out that stripcharts "are a good
alternative to boxplots when sample sizes are small".
My own rule-of-thumb: n > 20 for single boxplots, n > 12
for multiple boxplots.

Peter Ehlers

Martin Maechler wrote:

Boxplots were invented by John W. Tukey and I think should be
counted among the top "small but smart" achievements from the
20th century.  Very wisely he did *not* use mean and standard deviations.

Even though it's possible to draw boxplots that are not boxplots
(and people only recently explained how to do this with R on this
 mailing list), I'm arguing very strongly against this.

If I see a boxplot - I'd want it to be a boxplot and not have
the silly (please excuse)  10%--------90% whiskers  which
declare 20% of the points as outliers {in the boxplot sense}.

If you want the mean +/- sd plot, do *not* misuse boxplots
for them, please! 

Martin Maechler, ETH Zurich

"Evgeniy" == Evgeniy Kachalin <ka4alin at yandex.ru>
   on Thu, 01 Dec 2005 19:04:47 +0300 writes:

    Evgeniy> Hello to all users and wizards.
    Evgeniy> I am regulary using 'boxplot' function or its analogue - 'bwplot' from 
    Evgeniy> the 'lattice' library. 

 [there's the lattice *package*  !]

    Evgeniy> But they are, as far as I understand, totally 
    Evgeniy> flawed in functionality: they miss ability to select what they would 
    Evgeniy> draw 'in the middle' - median, mean. What the box means - standard 
    Evgeniy> error, 90% or something else. What the whiskers mean - 100%, 99% or 
    Evgeniy> something else.
    Evgeniy> Is there any way to realize it? Or is there any other good data 
    Evgeniy> visualization function for comparing means of various data groups? 
    Evgeniy> Ideally I would like to have a bit more customised function for doing 
    Evgeniy> that. For example, 'boxplot(a~b,data=d,mid='mean').


    Evgeniy> -- 
    Evgeniy> Evgeniy, ICQ 38317310.

P Ehlers wrote:

I'd like to add two comments to Martin's sensible response.

1. I've seen several intro-stats textbooks that define a
boxplot to have whiskers to the extreme data values
and then define Tukey's boxplot as a "modified" boxplot.
I wish authors wouldn't do that.

2. I've also seen boxplots used for sample sizes as small
as -- are you ready for it? -- n = 2!! (Admittedly, only in
plots comparing several groups.) The help page for
stripchart() points out that stripcharts "are a good
alternative to boxplots when sample sizes are small".
My own rule-of-thumb: n > 20 for single boxplots, n > 12
for multiple boxplots.

Woul've it make sense to have an option to replace boxes with dotplots
for only those groups with number of observations lesser tahn nmin=20 (say)

Kjetil