Thanks for your response Gustav,
The dots in the models mean that there are other effects in the models. In relation to the model, it would be like this: Q(i) = Q(i-1) + b*max(s(i) - s(0), 0) + c*min(s(i) - s(0), 0) If( s(i) > s(0)) then max(s(i) - s(0), 0) = s(i)-s(0) min(s(i) - s(0), 0) = 0 There is an accumulative positive effect and Q(1) is greater than Q(0) If( s(1) < s(0)) then max(s(i) - s(0), 0) = 0 min(s(i) - s(0), 0) = s(i)-s(0) There is an accumulative negative effect and Q(1) is lower than Q(0) For i=1: Q(1) = Q(0) + b*max(s(1) - s(0), 0) + c*min(s(1) - s(0), 0) If( s(1) > s(0)) then max(s(1) - s(0), 0) = s(1)-s(0) min(s(1) - s(0), 0) = 0 If( s(1) < s(0)) then max(s(1) - s(0), 0) = 0 min(s(1) - s(0), 0) = s(1)-s(0) In the model the value of Q depends on the value of s. If that value is above a threshold, Q increases and if the value of s is below the threshold Q decreases. Then, when Q is above a threshold (different that the threshold of s) it has an effect. In my particular case, s is temperature and Q would be the amount of temperature (or something similar) that is accumulated. -----Original Message----- From: Gustaf Rydevik [mailto:[EMAIL PROTECTED] Sent: Friday, September 28, 2007 11:13 AM To: Manuel Ramon Cc: r-help@r-project.org Subject: Re: [R] Is there a model like that in R? On 9/28/07, Manuel Ramon <[EMAIL PROTECTED]> wrote: > Hi to everyone, > > > > I am starting to work with a model that is not familiar to me. > > The model would be like that: > > > > y = . - a*max(Q(i) - Q(0), 0) + . > > > > where Q(i) is the accumulated effect of a variable at time i and Q(0) > a threshold above it there is effect on y. The value of Q(i) could be > estimated as: > > > > Q(i+1) = Q(i) + b*max(s(i) - s(0), 0) + c*min(s(i) - s(0), 0) + . > > > > Where s would be the effect that produces the accumulate effect of Q, > s(i) would be this effect at time i and s(0) another threshold above > it the accumulative effect is produced. The coefficient b would be the > rate of accumulation and c the rate of decay. > > > > What kind of model is it? Is it somewhat similar to time series? > > > > I appreciate your help. > > > > Manuel Ramon > I'm not sure what you're describing, but something is wrong for your definition of Q(i). For i=1: Q(1) = Q(0) + b*max(s(0) - s(0), 0) + c*min(s(0) - s(0), 0) + .=Q(0)+b*0+c*0=Q(0). Thus, Q(n)=Q(n-1)=...=Q(0) In addition, what is intended by the dots and the final plus in "y = . - a*max(Q(i) - Q(0), 0) + ."? I think you have to describe things a bit more careful, if we are to understand what's happening. Best, Gustaf -- Gustaf Rydevik, M.Sci. tel: +46(0)703 051 451 address:Essingetorget 40,112 66 Stockholm, SE skype:gustaf_rydevik Manuel [[alternative HTML version deleted]] ______________________________________________ R-help@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.