Ordinal dominance curve based inference for stochastically ordered distributions

Summary.  In a variety of applications researchers collect data that are sampled under ordered experimental conditions. In such situations it is reasonable to assume that outcomes are ordered stochastically by the level of the treatment. For example a toxicologist may want to assess the effect of a toxin on the reproductive system by studying the number of offspring produced by an animal as a function of the dose that it received. A variety of scientific questions arise in such a context. The most basic is whether a dose–response relationship is present. If so, determining the minimal toxic dose is of great interest. The strength of the ordering between groups i<j may be assessed by the probabilities or monotone functions thereof. Large probabilities indicate a strong ordering. We find that such (and other) questions are naturally addressed by studying the ordinal dominance curve and the area under the curve (AUC). We develop new, non-parametric, order-restricted estimators for the AUCs in K2 samples and investigate them in detail. We show that the restricted estimators are strongly consistent and have lower mean-squared error compared with the unrestricted estimators. In the two-sample case estimators are considerably improved in those situations where the data are highly variable and/or sample sizes are small, and where the AUC is close to its boundary value. Note that these are precisely the conditions under which estimating the AUC is difficult. Simulations indicate that in the multisample case estimators are improved under a much broader set of conditions with substantial reductions in mean-squared error. These estimators provide a basis for a family of distribution-free tests for the usual stochastic order in K2 samples. Limiting distributions are derived. An accurate and simple approximation to the tail area is given for K=2. Simulation studies show that the new tests perform well compared with existing alternatives. The methodology proposed is illustrated by applying it to an aquatic toxicology study where it is used to determine the minimal toxic dose more accurately.

[1]  F. T. Wright,et al.  Order restricted statistical inference , 1988 .

[2]  J. Rojo.  On the estimation of survival functions under a stochastic order constraint , 2004 .

[3]  J. Wellner,et al.  On the distribution of Brownian areas , 1996 .

[4]  Rhonda C. Magel,et al.  A new nonparametric test for the ordered alternative problem , 2003 .

[5]  D. A. Williams,et al.  A test for differences between treatment means when several dose levels are compared with a zero dose control. , 1971, Biometrics.

[6]  J. Tebbs,et al.  Nonparametric tests for and against likelihood ratio ordering in the two-sample problem , 2005 .

[7]  S. Peddada,et al.  Tests for Order Restrictions in Binary Data , 2001, Biometrics.

[8]  Satishs Iyengar,et al.  Multivariate Models and Dependence Concepts , 1998 .

[9]  D. Bamber.  The area above the ordinal dominance graph and the area below the receiver operating characteristic graph , 1975 .

[10]  Samuel Kotz,et al.  The stress-strength model and its generalizations , 2013 .

[11]  T. J. Terpstra,et al.  The asymptotic normality and consistency of kendall's test against trend, when ties are present in one ranking , 1952 .

[12]  A. R. Jonckheere,et al.  A DISTRIBUTION-FREE k-SAMPLE TEST AGAINST ORDERED ALTERNATIVES , 1954 .

[13]  David J. Hand,et al.  A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems , 2001, Machine Learning.

[14]  B. Turnbull,et al.  NONPARAMETRIC AND SEMIPARAMETRIC ESTIMATION OF THE RECEIVER OPERATING CHARACTERISTIC CURVE , 1996 .

[15]  Thomas Brox,et al.  Maximum Likelihood Estimation , 2019, Time Series Analysis.

[16]  E. Lehmann.  Some Concepts of Dependence , 1966 .

[17]  E Shirley,et al.  A non-parametric equivalent of Williams' test for contrasting increasing dose levels of a treatment. , 1977, Biometrics.

[18]  Stephen E. Fienberg,et al.  Testing Statistical Hypotheses , 2005 .

[19]  P. Qiu.  The Statistical Evaluation of Medical Tests for Classification and Prediction , 2005 .

[20]  Thomas P. Hettmansperger,et al.  A Class of Non-Parametric Tests for Homogeneity Against Ordered Alternatives , 1973 .

[21]  Stochastic Orders , 2008 .

[22]  Yazhen Wang.  A Likelihood Ratio Test against Stochastic Ordering in Several Populations , 1996 .

[23]  Christian P. Robert,et al.  Is Pitman Closeness a Reasonable Criterion , 1993 .

[24]  K. Strassburger,et al.  The partitioning principle: a powerful tool in multiple decision theory , 2002 .

[25]  T Hyslop,et al.  Generalized treatment effects for clinical trials. , 2000, Statistics in medicine.

[26]  H. Mukerjee,et al.  Inferences Under a Stochastic Ordering Constraint , 2005 .

[27]  C. Yiannoutsos,et al.  Ordered multiple‐class ROC analysis with continuous measurements , 2004, Statistics in medicine.

[28]  On the estimation of stochastically ordered survival functions , 1996 .

[29]  M. A. Arcones,et al.  Nonparametric Estimation of a Distribution Subject to a Stochastic Precedence Constraint , 2002 .

[30]  Ordered inference, rank statistics and combining p-values: A new perspective , 2012 .

[31]  Douglas A. Wolfe,et al.  A Distribution-Free Test for Stochastic Ordering , 1976 .

[32]  D. L. Hanson,et al.  Maximum Likelihood Estimation of the Distributions of Two Stochastically Ordered Random Variables , 1966 .

[33]  Shyamal D. Peddada,et al.  Confidence Interval Estimation Subject to Order Restrictions , 1994 .

[34]  Leonid Tolmatz.  Asymptotics of the distribution of the integral of the absolute value of the Brownian bridge for large arguments , 2000 .

[35]  O. Davidov,et al.  Testing for order among K populations: theory and examples , 2009 .

[36]  W. Franck,et al.  A Likelihood Ratio Test for Stochastic Ordering , 1984 .

[37]  Shyamal D Peddada,et al.  Incorporating Historical Control Data When Comparing Tumor Incidence Rates , 2007, Journal of the American Statistical Association.

[38]  E. Lehmann,et al.  Invariant Directional Orderings , 1992 .