

   BBooddyy TTeemmppeerraattuurree SSeerriieess ooff BBeeaavveerr 22

   AArrgguummeennttss::

        day: Day of observation (in days since the beginning of
             1990), November 3-4.

       time: Time of observation, in the form `0330' for 3.30am

       temp: Measured body temperature in degrees Celcius

      activ: Indicator of activity outside the retreat

   SSUUMMMMAARRYY::

        The `beaver2' data frame has 100 rows and 4 columns on
        body temperature measurements at 10 minute intervals.

   DDAATTAA DDEESSCCRRIIPPTTIIOONN::

        Reynolds (1994) describes a small part of a study of
        the long-term temperature dynamics of beaver Castor
        canadensis in north-central Wisconsin.  Body tempera-
        ture was measured by telemetry every 10 minutes for
        four females, but data from a one period of less than a
        day for each of two animals is used there.

        This data frame contains the following columns:

   SSOOUURRCCEE::

        P. S. Reynolds (1994) Time-series analyses of beaver
        body temperatures.  Chapter 11 of Lange, N., Ryan, L.,
        Billard, L., Brillinger, D., Conquest, L.  and Green-
        house, J. eds (1994) Case Studies in Biometry.  New
        York: John Wiley and Sons.

   SSeeee AAllssoo::

        `beaver1'

   EExxaammpplleess::

        ### Not usable in R
        attach(beav2)
        beav2$hours <- 24*(day-307) + trunc(time/100) + (time%%100)/60
        plot(beav2$hours, beav2$temp, type="l", xlab="time",
           ylab="temperature", main="Beaver 2")
        usr <- par("usr"); usr[3:4] <- c(-0.2, 8); par(usr=usr)
        lines(beav2$hours, beav2$activ, type="s", lty=2)

        attach(beav2)
        temp <- rts(temp, start=8+2/3, frequency=6, units="hours")
        activ <- rts(activ, start=8+2/3, frequency=6, units="hours")
        acf(temp[activ==0]); acf(temp[activ==1]) # also look at PACFs
        ar(temp[activ==0]); ar(temp[activ==1])

        arima.mle(temp, xreg=rep(1, length(temp)), model=list(ar=0.75))
        arima.mle(temp, xreg=cbind(1, activ), model=list(ar=0.75))

        beav2.lme <- lme(temp ~ activ, cluster = ~rep(1,100),
             data=beav2,  serial.structure="ar1", est.method="ML")
        summary(beav2.lme)

