R help - Aug 2011 - Running a column loop through the Moran.I function.

Dear R users,

I have two data frames that consist of statistical information for most
countries around the world. One dataframe consists of the latitude and
longitude ("coord.csv") of each country, while the other consists of
100's
of different attributes ("countryattri.csv") for each country (like,
GDP,
Population, etc.). The data is organized with a header and then countries
down the first column. I'm trying to run a spatial autocorrelation for each
column or attribute in the "attri" dataframe. The process for running
this
on a single column is as follows:

example of "coord.csv" dataframe:

country, lat, long
Albania, 41.00, 20.00
Algeria, 28.00, 3.00
Angola, -12.30, 18.30

example of "countryattri.csv" dataframe:

country, GDP, Population
Albania, 100000, 20000
Algeria, 1200000, 300000
Angola, 1300000, 300000
>     Locate<-read.csv("coord.csv", header = TRUE, sep =
",")
>     Locate.dists<-as.matrix(dist(cbind(Locate$long, Locate$lat)))
>     Locate.dists.inv<-1/((Locate.dists)^2)
>     diag(Locate.dists.inv)<-0
>     attri<-read.csv("countryattri.csv", header = TRUE, sep =
",")
>     Moran.I(attri$GDP, Locate.dists.inv, na.rm = TRUE)
This gives you Moran's I (correlation coefficient) for the GDP column in the
"attri" dataframe. I am trying to run the Moran.I function as a loop
for all
columns in the "attri" dataframe so that I can obtain Moran
coefficients for
every attribute.

I've tried a number of different approaches but cannot get a column loop to
run through this function. I would be very grateful if someone could help me
with this problem.

Thank you,

*Scott Seely*
p.s. the Moran.I function is a part of the "ape" package.

	[[alternative HTML version deleted]]

I'm on my phone so I can't verify this but have you tried the apply
function?

apply(attri,2,Moran.I,Locate.dists.inv,NA.rm=T)

Michael Weylandt

On Aug 4, 2011, at 4:54 PM, Scott Seely <sseely at thetus.com> wrote:
> Dear R users,
> 
> I have two data frames that consist of statistical information for most
> countries around the world. One dataframe consists of the latitude and
> longitude ("coord.csv") of each country, while the other consists
of 100's
> of different attributes ("countryattri.csv") for each country
(like, GDP,
> Population, etc.). The data is organized with a header and then countries
> down the first column. I'm trying to run a spatial autocorrelation for
each
> column or attribute in the "attri" dataframe. The process for
running this
> on a single column is as follows:
> 
> example of "coord.csv" dataframe:
> 
> country, lat, long
> Albania, 41.00, 20.00
> Algeria, 28.00, 3.00
> Angola, -12.30, 18.30
> 
> example of "countryattri.csv" dataframe:
> 
> country, GDP, Population
> Albania, 100000, 20000
> Algeria, 1200000, 300000
> Angola, 1300000, 300000
> 
>>    Locate<-read.csv("coord.csv", header = TRUE, sep =
",")
>>    Locate.dists<-as.matrix(dist(cbind(Locate$long, Locate$lat)))
>>    Locate.dists.inv<-1/((Locate.dists)^2)
>>    diag(Locate.dists.inv)<-0
>>    attri<-read.csv("countryattri.csv", header = TRUE, sep
= ",")
>>    Moran.I(attri$GDP, Locate.dists.inv, na.rm = TRUE)
> 
> This gives you Moran's I (correlation coefficient) for the GDP column
in the
> "attri" dataframe. I am trying to run the Moran.I function as a
loop for all
> columns in the "attri" dataframe so that I can obtain Moran
coefficients for
> every attribute.
> 
> I've tried a number of different approaches but cannot get a column
loop to
> run through this function. I would be very grateful if someone could help
me
> with this problem.
> 
> Thank you,
> 
> *Scott Seely*
> p.s. the Moran.I function is a part of the "ape" package.
> 
>    [[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.