TY - JOUR
T1 - A non-parametric regression approach to repeated measures analysis in cancer experiments
AU - Ruiz De Villa, M. Carme
AU - Cabral, M. Salomé E.
AU - Escriche, Eduardo Escrich
AU - Solanas, Montse
PY - 1999/12/1
Y1 - 1999/12/1
N2 - The validity conditions for univariate or multivariate analyses of repeated measures are highly sensitive to the usual assumptions. In cancer experiments, the data are frequently heteroscedastic and strongly correlated with time, and standard analyses do not perform well. Alternative non-parametric approaches can contribute to an analysis of these longitudinal data. This paper describes a method for such situations, using the results from a comparative experiment in which tumour volume is evaluated over time. First, we apply the non-parametric approach proposed by Raz in constructing a randomization F-test for comparing treatments. A local polynomial fit is conducted to estimate the growth curves and confidence intervals for each treatment. Finally, this technique is used to estimate the velocity of tumour growth.
AB - The validity conditions for univariate or multivariate analyses of repeated measures are highly sensitive to the usual assumptions. In cancer experiments, the data are frequently heteroscedastic and strongly correlated with time, and standard analyses do not perform well. Alternative non-parametric approaches can contribute to an analysis of these longitudinal data. This paper describes a method for such situations, using the results from a comparative experiment in which tumour volume is evaluated over time. First, we apply the non-parametric approach proposed by Raz in constructing a randomization F-test for comparing treatments. A local polynomial fit is conducted to estimate the growth curves and confidence intervals for each treatment. Finally, this technique is used to estimate the velocity of tumour growth.
M3 - Article
SN - 0266-4763
VL - 26
SP - 601
EP - 611
JO - Journal of Applied Statistics
JF - Journal of Applied Statistics
IS - 5
ER -
