s-news
[Top] [All Lists]

Parameter Estimate

To: s-news@wubios.wustl.edu
Subject: Parameter Estimate
From: "chan MALI CHAN" <chan1909@hotmail.com>
Date: Sat, 23 Dec 2000 18:11:47 -0000
Dear S-Plus users,
I need some help in solving the problem using the S-Plus software. Sorry to say that I am new to this software. Here I have a non-linear model with additive terms yi = â0*(exp(-â0*xi)-exp(-â1*xi))/ (â0-â1) + åi where åi are independent and identically distributed random variables with mean 0 and unknown variance ó2.The problem is I need to use these four techniques to estimate the betas , get the MSE(Mean Squared Error) and list the residuals for the model
Technique 1: linearize
Technique 2: non-linear least squares estimate
Technique 3: Using Lawrence and Arthur (1990) proposal of one-step iterative reweighting scheme in which a weighted non-linear least squares process is performed on the model using Huber's weight function wi defined as 1 ,if | ei | < c and c/ei ,if | ei | > c where c is the tuning constant and ei is the standardized absolute residual. ei = | ri | / s .Lawrence and Arthur (1990) defined s as the standard deviation of the residuals {ri ; i = 1, .., n} obtained from the least-squares procedure
Technique 4: reweighted linear jackknife (RLQ)
Could any expertise out there please advise me on how to use the S-Plus by clicking the Menus and Dialogs step by steps if possible or otherwise by S-Plus syntax and grammar to write a program? Thank you in advance for spending your expensive time in giving me the advice. All the help given is much appreciated .
Wishing all the users out the MERRY CHRISTMAS AND A HAPPY NEW YEAR.
Thank you.
From chan MALI CHAN.

_________________________________________________________________________
Get Your Private, Free E-mail from MSN Hotmail at http://www.hotmail.com.


<Prev in Thread] Current Thread [Next in Thread>
  • Parameter Estimate, chan MALI CHAN <=