TY - JOUR
T1 - Spectral analysis for discrete longitudinal data
AU - Beckett, Laurel A
AU - Diaconis, Persi
PY - 1994/1/1
Y1 - 1994/1/1
N2 - We develop a Fourier type of analysis for data consisting of many short strings X1, X2, …, Xn, with Xi = (Xi1, …, Xip). The paper offers an approach testing and residual analysis based on a group theoretic decomposition of the sample space. This is illustrated on a physical chance type data set where it is natural to allow each string to have its own parameter (i.i.d. coin-tossing with parameter varying from string to string). The usual model is rejected.
AB - We develop a Fourier type of analysis for data consisting of many short strings X1, X2, …, Xn, with Xi = (Xi1, …, Xip). The paper offers an approach testing and residual analysis based on a group theoretic decomposition of the sample space. This is illustrated on a physical chance type data set where it is natural to allow each string to have its own parameter (i.i.d. coin-tossing with parameter varying from string to string). The usual model is rejected.
UR - http://www.scopus.com/inward/record.url?scp=0040314267&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0040314267&partnerID=8YFLogxK
U2 - 10.1006/aima.1994.1002
DO - 10.1006/aima.1994.1002
M3 - Article
AN - SCOPUS:0040314267
VL - 103
SP - 107
EP - 128
JO - Advances in Mathematics
JF - Advances in Mathematics
SN - 0001-8708
IS - 1
ER -