2008-04-09

Beautiful Correlation Tables in R

I have achieved another victory in getting R to produce SPSS-like results. In experimental psychology, an analysis of measurement variable correlations is a common method in the course of a statistical analysis. Thus, I wanted R to produce a publication-quality output similar to SPSS: a correlation matrix of measurement variables that contains only the lower triangle of observations, where observations have two decimal digits and are flagged with stars (*, **, and ***) according to levels of statistical significance. However, as statmethods notices:
Unfortunately, neither cor( ) or cov( ) produce tests of significance, although you can use the cor.test( ) function to test a single correlation coefficient.
I did a little research and found this post on the R-help list. I modified Chuck Cleland's code a little so that the following command on the swiss data frame (provided in the Hmisc package) produces a beautiful output:

> corstarsl(swiss[,1:4])

Fertility Agriculture Examination
Fertility
Agriculture 0.35*
Examination -0.65*** -0.69***
Education -0.66*** -0.64*** 0.70***

If one employs the xtable package that produces LaTeX tables from within R, xtable(corstarsl(swiss[,1:4])) produces this:
Isn't that beautiful? I like it a lot. Here's the code (as I said, much of it taken from here):

corstarsl <- function(x){
require(Hmisc)
x <- as.matrix(x)
R <- rcorr(x)$r
p <- rcorr(x)$P

## define notions for significance levels; spacing is important.
mystars <- ifelse(p < .001, "***", ifelse(p < .01, "** ", ifelse(p < .05, "* ", " ")))

## trunctuate the matrix that holds the correlations to two decimal
R <- format(round(cbind(rep(-1.11, ncol(x)), R), 2))[,-1]

## build a new matrix that includes the correlations with their apropriate stars
Rnew <- matrix(paste(R, mystars, sep=""), ncol=ncol(x))
diag(Rnew) <- paste(diag(R), " ", sep="")
rownames(Rnew) <- colnames(x)
colnames(Rnew) <- paste(colnames(x), "", sep="")

## remove upper triangle
Rnew <- as.matrix(Rnew)
Rnew[upper.tri(Rnew, diag = TRUE)] <- ""
Rnew <- as.data.frame(Rnew)

## remove last column and return the matrix (which is now a data frame)
Rnew <- cbind(Rnew[1:length(Rnew)-1])
return(Rnew)
}

Labels: , , ,

37 Comments:

Blogger longge said...

Kinds of individual ugg rainier boots are cut from the ugg rainier skins which are sewn together by professional machines. The soles are glued to ugg boots upper. Now, you can purchase ugg ! uggs have stirred up a fashion tide and become a huge fashion craze. Enjoy UGG Australia comfort please!

3:44 AM  
Blogger Sean said...

Very nice! Just copied and pasted the code into R and it worked flawlessly. A fast way to get a readable table to share results with colleagues.

8:00 PM  
Blogger Disgruntled PhD said...

Thank you so much for this. Almost finished my first latex and R paper, formatted in APA style when i realised that i had no significance stars. You're a lifesaver, thank you.

5:04 PM  
Blogger Travel Bugs said...

Seriously helpful thanks a ton for this.

11:29 AM  
Blogger aL3xa said...

Take a look at this:

https://gist.github.com/887249

It's very similar, but uses `psych` package instead `Hmisc`

6:43 PM  
Blogger Arghya Chakraborty said...

Personally, the post is in fact the most excellent on this impressive topic. I harmonize with your conclusions and will keenly look further to your future updates.
Fort Worth Brake Repair Service

1:02 PM  
Blogger onwebmedia said...

The topic is remarkable. I actually never think I could have an excellent read by this time until I find out this website. I am thankful for the information. Thank you for being so kind enough to have shared your information with us. nap mat with pillow

10:12 AM  
Blogger onwebmedia said...

This blog is excellent. I got many unknown information from this site. Buy Herbalife

12:25 PM  
Blogger arghya said...

This was very informative. I have been reading your blog a lot over the past few days and it has earned a place in my bookmarks. It is wonderful.I learn a lot from it.thanks for sharing the article. Its like you read my mind! You appear to know so much about this, like you wrote the book in it or something. I think that you could do with some pics to drive the message home a little bit, but other than that, this is great blog. domestic violence lawyer Fort Worth

11:43 AM  
Anonymous Anonymous said...

thanks, this was a super useful post.

7:40 PM  
Anonymous Anonymous said...

Hi there,

i don't get the same output like although I installed all necessary packages.

My output looks like this:

% latex table generated in R 2.15.1 by xtable 1.7-0 package
% Fri Oct 12 12:45:52 2012
\begin{table}[ht]
\begin{center}
\begin{tabular}{rlll}
\hline
& Fertility & Agriculture & Examination \\
\hline
Fertility & & & \\
Agriculture & 0.35* & & \\
Examination & -0.65*** & -0.69*** & \\
Education & -0.66*** & -0.64*** & 0.70*** \\
\hline
\end{tabular}
\end{center}

What to do???

Thanks!
Felix

11:49 AM  
Blogger fxen2k said...

Hi there,

i don't get the same output like although I installed all necessary packages.

My output looks like this:

% latex table generated in R 2.15.1 by xtable 1.7-0 package
% Fri Oct 12 12:45:52 2012
\begin{table}[ht]
\begin{center}
\begin{tabular}{rlll}
\hline
& Fertility & Agriculture & Examination \\
\hline
Fertility & & & \\
Agriculture & 0.35* & & \\
Examination & -0.65*** & -0.69*** & \\
Education & -0.66*** & -0.64*** & 0.70*** \\
\hline
\end{tabular}
\end{center}

What to do???

Thanks!
Felix

11:50 AM  
Blogger Nicole said...

Just wanted to add if you want Spearman's test instead, you have to add it in two lines, otherwise the stars are based on Pearson. I made that mistake and it took me a while to figure it out, since the p-values displayed are still the right ones from Spearman.

R <- rcorr(x, type="Spearman")$r
p <- rcorr(x, type="Spearman")$P

8:02 PM  
Anonymous Anonymous said...

WOW this is unbelievably good. From the perspective of an R newbie where nothing ever works first time, this is AMAZING. Thank you so much!

11:20 AM  
Blogger Conal said...

Fantastic code!,
A lot of professional reporting standards (e.g., APA 6) elimates the "0" in front of each correlation (e.g., 0.77 = .77) because the 0 is assumed. I wonder how this package could be altered to remove the zero in the front?

- Conal

11:53 AM  
Blogger Armando Iswahyudi said...

Hi there,I enjoy reading through your article post, I wanted to write a little comment to support you and wish you a good continuationAll the best for all your blogging efforts.

| armando manabu
| manabu mikami
| tkr dua
| mando manabu

6:54 PM  
Anonymous STHDA said...

Nice topic. This help articles helps me.

Several articles on how to compute and visualize correlation matrix are also provided here :

Computing and visualizing correlation in R

8:43 AM  
Anonymous Michael said...

The current procedure to drop the upper triangular is not optimal because it turns all numbers into characters. This may cause problems when you want to round, print in latex tables or calculate.

Therefore you better use

## remove upper triangle
Rnew[upper.tri(Rnew, diag = TRUE)] <- NA

Also, the transformation into matrix/data frame is not necessary.

6:43 PM  
Anonymous Anonymous said...

electronic cigarette reviews, e cigarette, electronic cigarette, best e cigarette, ecig forum, e cig

7:03 AM  
Anonymous Alex said...

Thanks, very useful, I just used it and it works very well!

5:05 PM  
Blogger Whatsapp Descargar said...

I love all the posts, I really enjoyed, I would like more information about this, because it is very nice., Thanks for sharing.
Signature:
download free descargar whatsapp gratis and download baixar whatsapp gratis online and descargar whatsapp , baixar whatsapp

9:03 AM  
Blogger Frozen Juegos said...

I am very happy to read this. Appreciate your sharing
Signature:
Jugar juegos de frozen en línea gratis, los nuevos de princesa de Disney juegos frozen - la princesa encantadora y linda. Divertirse frozen!

3:18 AM  
Blogger Vimax Original Pembesar Mr.P Herbal said...

artikelnya sangat membantu thanks for sharing
kunjungi web kami gan => www.vimaxkapsuloriginal.com

1:53 AM  
Blogger yana-maria priestley said...

You are amazing, thank you very much! I'm a psychology student with huge love to stats, so your blog is my perfect match :)

10:02 AM  
Blogger Happy Wheels said...

I'm happy about everything you bring it very interesting and helpful, thanks happy wheels , happywheels , happywheel

4:42 AM  
Blogger Alice Taylor said...

This comment has been removed by the author.

10:04 AM  
Blogger Alice Taylor said...

Any way I'll be subscribing to your feed and I hope you post again soon.
Monkey Go Happy | Monkey Go Happy 2 | Monkey Go Happy 3 | Learn To Fly | Learn To Fly2 | Learn To Fly 3 | Pacman | Pacman games | Pacman game | Mahjong |Mahjong games | Mahjong online | Happy Wheels|HappyWheels | Happy Wheels demo | cat mario 4 | cat mario 2 | cat mario

10:08 AM  
Blogger Ranveer Patil said...

I like this a lot. Thank you for sharing. I'm always looking for upcycles like this. In the end, you don't know it was a shipping pallet to begin with!
Australia vs India Team Selection
ICC T20 World Cup 2016 Fixtures

11:05 AM  
Blogger Gopal Dalal said...

fan movie advance ticket booking
fan full movie dvdscr dvdrip dvdprint torrent download free
fan movie friday box office collection predictions
fan movie first day box office collection
fan movie poster shooting images songs
fan movie
fan movie friday box office collection
fan movie opening day box office collection
icc t20 cricket world cup live streaming 2016
icc cricket world cup book tickets online
ind vs pak match ticket booking online ww.bookmyshow.com
icc t20 crcket world cup match summary predictions who will win the match world cup

9:36 AM  
Blogger Amit Kumar said...


IPL 2016 Schedule
Cricbuzz.com T20 Live Score
ICC T20 World Cup 2016 Ticket Booking
IPL 2016 Schedule

6:57 AM  
Blogger Amit Kumar said...


Icc T20 World Cup 2016 Live Streaming
IPL 2016 Live Score
t20 World Cup 2016 Live Streaming
T20 World Cup 2016 Live Score
IPL 2016 Fixture

6:57 AM  
Blogger Saim iqbal said...

T20 World Cup 2016

Asia Cup T20 2016 Schedule

India Team Squad for ICC T20 World Cup 2016

New Zealand Team Players List for T20 World Cup 2016


India Vs Pakistan T20 Match 2016 Live Cricket Streaming

5:15 PM  
Blogger abc.abc said...

Like a fairytale weaved and spun with magic threads, the story of KHAS started with a dream over half a century back. A subsidiary of the Sadaqat Group, that has won respect and awards all over the world, the vision of Khas is to make the same quality available here in Pakistan.
stuffed toys
trays

10:21 AM  
Blogger Champion League said...

t20 world cup 2016 theme song
t20 world cup 2016 live

9:47 AM  
Anonymous Shiwam said...

icc T20 16 time table schedule
Shiwam In
Lyricsmate

2:24 PM  
Blogger ipl 9 live score said...

this blog is really helpful. i found very interesting things here.
fan movie opening day box office collection
fan movie online ticket booking on www.bookmyshow.com
fan movie 1st DAY box office collection
T20 wc live streaming 2016
happy mothers day quotes from son and daughter to mother

10:44 AM  
Blogger Karan Arora said...

srk fan collection
fan movie tickets bookmyshow
fan box office first day collection

12:06 PM  

Post a Comment

<< Home