Amendments/corrections from authors to "Is equine colic seasonal? Novel application of a model based approach"
Helen Clough, University of Liverpool
28 September 2006
Please note that the authors intended to include the following additional citations in the main manuscript, and, with apologies for any confusion, request that the reader makes the appropriate annotations to the text:
Page 2, column 2, lines 2-5 (page 5, lines 8-10 in provisional pdf) should read
One possibility lies in the use of a Poisson distribution to model count data within a framework broadly analogous to that of generalised linear modelling (e.g. [17, 41-42]).
On page 7 (page 14 in provisional pdf) there is a discussion of different types of dependence. An important reference in this area (observation versus parameter driven models), cited in [42], is:
[51] Cox, D. R. (1981) Statistical analysis of time series, some recent developments. Scandinavian Journal of Statistics 8:93-115.
Page 7, column 2, line 20-21 (page 14, line 10 in provisional pdf) should then be modified to
This type of dependence is described as "observation driven" (for example, [41, 42, 51]).
and page 7, column 2, line 29-30 (page 14, line 16 in provisional pdf) should be modified to
Here, dependence (and subsequent models) is described as "parameter driven" (for example, [42, 51]).
Finally, for description of the package R2WinBUGS (page 9 (page 20 in provisional pdf)) in addition to package documentation provided in R [49] please see
Sturtz, S., Ligges, U., Gelman, A. (2005): R2WinBUGS: A Package for Running WinBUGS from R. Journal of Statistical Software 12(3), 1-16.
Amendments/corrections from authors to "Is equine colic seasonal? Novel application of a model based approach"
28 September 2006
Please note that the authors intended to include the following additional citations in the main manuscript, and, with apologies for any confusion, request that the reader makes the appropriate annotations to the text:
Page 2, column 2, lines 2-5 (page 5, lines 8-10 in provisional pdf) should read
One possibility lies in the use of a Poisson distribution to model count data within a framework broadly analogous to that of generalised linear modelling (e.g. [17, 41-42]).
On page 7 (page 14 in provisional pdf) there is a discussion of different types of dependence. An important reference in this area (observation versus parameter driven models), cited in [42], is:
[51] Cox, D. R. (1981) Statistical analysis of time series, some recent developments. Scandinavian Journal of Statistics 8:93-115.
Page 7, column 2, line 20-21 (page 14, line 10 in provisional pdf) should then be modified to
This type of dependence is described as "observation driven" (for example, [41, 42, 51]).
and page 7, column 2, line 29-30 (page 14, line 16 in provisional pdf) should be modified to
Here, dependence (and subsequent models) is described as "parameter driven" (for example, [42, 51]).
Finally, for description of the package R2WinBUGS (page 9 (page 20 in provisional pdf)) in addition to package documentation provided in R [49] please see
Sturtz, S., Ligges, U., Gelman, A. (2005): R2WinBUGS: A Package for Running WinBUGS from R. Journal of Statistical Software 12(3), 1-16.
Competing interests
None.