# Spatio-Temporal Data Sets

### Eurasian Collared Dove Breeding Bird Survey Data

These data are North American Breeding Bird Survey data on the Eurasian Collared Dove (Streptopelia decaocto) for the years 1986 - 2008. (See http://www.pwrc.usgs.gov/bbs/ for a full description of the BBS).

ECDovelatlon 253 x 2 matrix; 253 spatial locations with first column corresponding to latitude (degrees North) and second column corresponding to longitude (degrees West; the negative sign indicates West longitude)

ECDoveBBS1986_2003 253 x 18 matrix; 253 spatial locations and 18 years (1986 in column 1, 2008 in column 18); missing data are denoted by -1.

In addition to Chapter 5 and 9 of Cressie and Wikle (2011), these data have been described and modeled in the following:

Wikle, C.K. and Hooten, M.B. (2006). Hierarchical Bayesian Spatio-Temporal Models for Population Spread. In *Applications of Computational Statistics in the Environmental Sciences: Hierarchical Bayes and MCMC Methods*. J.S. Clark and A. Gelfand (eds). Oxford University Press. 145-169

Hooten, M. B. and C.K. Wikle, 2007: A Hierarchical Bayesian non-linear spatio-temporal model for the spread of invasive species with application to the Eurasian Collared-Dove. * Environmental and Ecological Statistics*, **15**, 59-70.

Hooten, M.B., Wikle, C.K., Dorazio, R.M., and J.A. Royle, 2007: Hierarchical matrix models for characterizing invasions, * Biometrics*, ** 63**, 558-567.

### Tropical Pacific Sea Surface Temperature (SST) Anomalies

These data represent gridded monthly SST anomalies for 399 consecutive months from January 1970 through March 2003. The data were obtained from the IRI/LDEO Climate Data Library at Columbia University (http://iridl.ldeo.columbia.edu/). The data are gridded at a 2 degree by 2 degree resolution and represent anomalies from a January 1970 - December 1985 monthly (average) climatology. A more complete description can be found at http://iridl.ldeo.columbia.edu/SOURCES/.CAC/.

SSTlonlat 2520 x 2 matrix; longitude in first column and latitude in the second, corresponding to the spatial grid locations in SST011970_032003.dat; note: the longitudes are given from 124 to 290 by 2, corresponding to 124E to 290E (where 290E corresponds to 70W).

SST011970_032003 2520 x 399 matrix; 2520 spatial locations corresponding to an 84 (longitude) by 30 (latitude) grid with 2 deg x 2 deg spacing. The longitudes correspond to 124 E to 70W and the latitudes to 29S to 29N. There are 399 time periods representing sequentially the months from January 1970 through March 2003.

SSTlandmask 2520 x 1 vector; land/sea mask corresponding to the grid locations in SSTlonlat.dat, with a value of 1 corresponding to a "land" location and a 0 corresponding to a water location.

In addition to Chapter 5 and 9 of Cressie and Wikle (2011), these data have been described and modeled in the following:

Berliner, L.M., Wikle, C.K. and N. Cressie, (2000). Long-lead prediction of Pacific SSTs via Bayesian Dynamic Modeling. *Journal of Climate*, **13** , 3953-3968.

Wikle, C.K. and M.B. Hooten, 2010: A general science-based framework for spatio-temporal dynamical models. Invited discussion paper for *Test*. ** 19**, 417-451.

Wikle, C.K. and S.H. Holan, 2011: Polynomial nonlinear spatio-temporal integro-difference equation models *Journal of Time Series Analysis*. DOI: 10.1111/j.1467-9892.2011.00729.x

### Gridded Tornado Report Data

These data represent gridded annual tornado report counts over the eastern two-thirds of the U.S. The data represent aggregations of tornado reports submitted to the National Weather Service (NWS) between 1953-2001 as archived at the National Oceanic and Atmospheric Administration NWS Storm Prediction Center ( http://www.spc.noaa.gov/climo/historical.html). A complete description of the data processing can be found in Wikle and Anderson (2003).

tornado_f2_f5_1953_2001 1836 x 49 matrix; each column corresponds to the F2-F5 tornado counts at 1836 grid locations, corresponding to a vectorized 34 (lat) by 54 (long) grid, as given in the LATvec.dat and LONvec.dat files below; the 49 columns correspond to the years from 1953 (first column) to 2001 (last column).

LATvec 1836 x 1 vector corresponding to the latitudes of a vectorized grid of dimension 34 x 54.

LONvec 1836 x 1 vector corresponding to the longitudes of a vectorized grid of dimension 34 x 54.

SST_1953_2001 49 x 1 vector corresponding to the annual average Nino 3.4 SST index for 1953-2001 (e.g., see the NCEP Climate Prediction Center website http://www.cpc.ncep.noaa.gov/data/indices/)

A portion of these data (1953-1995) have been described and modeled in:

Wikle, C.K. and C.J. Anderson, (2003). Climatological analysis of tornado report counts using a hierarchical Bayesian spatio-temporal model. *Journal of Geophysical Research-Atmospheres*, **108**(D24), 9005, doi:10.1029/2002JD002806.