Re: [ferret_users] [FERRET]calculate spatial correlation of 2 variables

[muyin wang <muyin.wang@xxxxxxxx>]

Hi, Andy:
Thank you for your regressxy script. One thing I don't understand is why does 
the order of averaging matter? See the example blow. The results are so 
different! What was wrong here?
Thanks,
Muyin



let p=eofs[d=1,l=1]
let q=eofs[d=2,l=1]

let pq=p*q
let pqmsk=pq-pq

let pmsk=p+pqmsk
let qmsk=q+pqmsk

let pxavg=pmsk[x=@ave]
let pyavg=pmsk[y=@ave]

let pxya=pxavg[y=@ave]
let pyxa=pyavg[x=@ave]

list pxya,pyxa

 Column  1: PXYA is PXAVG[Y=@AVE]
 Column  2: PYXA is PYAVG[X=@AVE]
             PXYA     PYXA
I / *:    -0.01525  0.01854


Andy Chiodi wrote:
> Hi Zhen,
>
>     The spatial correlation of two varaibles can be found with the 
> following ferret script.  This is simply the regresst script re-written 
> to consider space rather than time.
>
> To use this, copy the regressxy script below to a .jnl file and then type
>
> yes?  go regressxy
> yes?  let P = myvar1
> yes?  let Q = myvar2
>
> in ferret.  The variable "corr" is then the spatial correlation between 
> myvar1 and myvar2.
>
> I hope this helps,
>
> Andy
>
>
> regressxy.jnl script:
>
> \CANCEL MODE VERIFY
> ! Description:  define FERRET variables for regression along the X and Y 
> axis
>
> say ... Linear Regression In the XY Plane
> say ... Instructions:
> say Use the LET command to define new variables
> say Define the variable P as your independent (X) variable
> say Define the variable Q as your   dependent (Y) variable
> say Results will be variables "SLOPE", "INTERCEP" and "RSQUARE"
> say QHAT will be the regression estimate
> say Note: If "Y" is your independent variable then
> say ...   "SET GRID Q" after defining Q.
> say ...
>
> let pq = p*q
> let pqmask = pq-pq  ! 0 or "missing" so all variables share the same 
> missing
> let pmasked = p + pqmask
> let qmasked = q + pqmask
> let pp = pmasked*pmasked
> let qq = qmasked*qmasked
>
> let pxave = pmasked[x=@ave]
> let qxave = qmasked[x=@ave]
> let pave = pxave[y=@ave]
> let qave = qxave[y=@ave]
> let pqxave = pq[x=@ave]
> let ppxave = pp[x=@ave]
> let qqxave = qq[x=@ave]
> let pqave = pqxave[y=@ave]
> let ppave = ppxave[y=@ave]
> let qqave = qqxave[y=@ave]
> let pvar  = ppave - pave*pave
> let qvar  = qqave - qave*qave
> let pqvar = pqave - pave*qave
>
> let slope = pqvar / pvar
> let intercep = qave - slope*pave
> let qhat = slope*p + intercep
> let rsquare = (pqvar*pqvar) / (pvar*qvar)
> let corr = pqvar/(pvar*qvar)^0.5
>
> SET MODE/LAST VERIFY
> >