corARMA                 package:nlme                 R Documentation

_A_R_M_A(_p,_q) _C_o_r_r_e_l_a_t_i_o_n _S_t_r_u_c_t_u_r_e

_D_e_s_c_r_i_p_t_i_o_n:

     This function is a constructor for the 'corARMA' class,
     representing an autocorrelation-moving average correlation
     structure of order (p, q). Objects created using this constructor
     must later be initialized using the appropriate 'Initialize'
     method.

_U_s_a_g_e:

     corARMA(value, form, p, q, fixed)

_A_r_g_u_m_e_n_t_s:

   value: a vector with the values of the autoregressive and moving
          average parameters, which must have length 'p + q' and all
          elements between -1 and 1. Defaults to a vector of zeros,
          corresponding to uncorrelated observations.

    form: a one sided formula of the form '~ t', or '~ t | g',
          specifying a time covariate 't' and,  optionally, a grouping
          factor 'g'. A covariate for this correlation structure must
          be integer valued. When a grouping factor is present in
          'form', the correlation structure is assumed to apply only to
          observations within the same grouping level; observations
          with different grouping levels are assumed to be
          uncorrelated. Defaults to '~ 1', which corresponds to using
          the order of the observations in the data as a covariate, and
          no groups.

    p, q: non-negative integers specifying respectively the
          autoregressive order and the moving average order of the
          'ARMA' structure. Both default to 0.

   fixed: an optional logical value indicating whether the coefficients
          should be allowed to vary in the optimization, or kept fixed
          at their initial value. Defaults to 'FALSE', in which case
          the coefficients are allowed to vary.

_V_a_l_u_e:

     an object of class 'corARMA', representing an
     autocorrelation-moving average correlation structure.

_A_u_t_h_o_r(_s):

     Jose Pinheiro Jose.Pinheiro@pharma.novartis.com and Douglas Bates
     bates@stat.wisc.edu

_R_e_f_e_r_e_n_c_e_s:

     Box, G.E.P., Jenkins, G.M., and Reinsel G.C. (1994) "Time Series
     Analysis: Forecasting and Control", 3rd Edition, Holden-Day.

     Pinheiro, J.C., and Bates, D.M. (2000) "Mixed-Effects Models in S
     and S-PLUS", Springer, esp. pp. 236, 397.

_S_e_e _A_l_s_o:

     'corAR1', 'corClasses' 'Initialize.corStruct', 'summary.corStruct'

_E_x_a_m_p_l_e_s:

     ## ARMA(1,2) structure, with observation order as a covariate and
     ## Mare as grouping factor
     cs1 <- corARMA(c(0.2, 0.3, -0.1), form = ~ 1 | Mare, p = 1, q = 2)

     # Pinheiro and Bates, p. 237 
     cs1ARMA <- corARMA(0.4, form = ~ 1 | Subject, q = 1)
     cs1ARMA <- Initialize(cs1ARMA, data = Orthodont)
     corMatrix(cs1ARMA)

     cs2ARMA <- corARMA(c(0.8, 0.4), form = ~ 1 | Subject, p=1, q=1)
     cs2ARMA <- Initialize(cs2ARMA, data = Orthodont)
     corMatrix(cs2ARMA)

     # Pinheiro and Bates use in nlme:  
     # from p. 240 needed on p. 396
     fm1Ovar.lme <- lme(follicles ~ sin(2*pi*Time) + cos(2*pi*Time),
                        data = Ovary, random = pdDiag(~sin(2*pi*Time)))
     fm5Ovar.lme <- update(fm1Ovar.lme,
                     corr = corARMA(p = 1, q = 1))
     # p. 396
     fm1Ovar.nlme <- nlme(follicles~
          A+B*sin(2*pi*w*Time)+C*cos(2*pi*w*Time),
        data=Ovary, fixed=A+B+C+w~1,
        random=pdDiag(A+B+w~1),
        start=c(fixef(fm5Ovar.lme), 1) )
     # p. 397
     fm3Ovar.nlme <- update(fm1Ovar.nlme,
              corr=corARMA(p=0, q=2) )