Jay H. Beder
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jay H. Beder has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Jeb F. Willenbring
University of Wisconsin-Milwaukee
2 shared publications - Jesse S. Beder
Department of Mathematics University of Illinois at Urbana-Champaign 1409 W. Green Street Urbana 61801 IL
1 shared publication Margaret Ann McComack
Department of Mathematical Sciences, University of Wisconsin-Milwaukee, Milwaukee, WI, USA
1 shared publication- Margaret Ann McComack
Department of Mathematical Sciences University of Wisconsin-Milwaukee P.O. Box 413 53201-0413 Milwaukee WI
1 shared publication - Milan N. Lukić
Department of Mathematics, Viterbo University, 815 South 9th Street, La Crosse, Wisconsin 54601
1 shared publication Richard Gomulkiewicz
School of Biological Sciences and Department of Mathematics, Washington State University, Pullman, USA
1 shared publication
Latest Publications
- Open Access
- 18 April 2016
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 46 (8) , 3690-3697
A note on the minimum size of an orthogonal array
It is an elementary fact that the size of an orthogonal array of strength t on k factors must be a multiple of a certain number, say Lt, that depends on the orders of the factors. Thus Lt is a lower bound on the size of arrays of strength t on those factors, and is no larger than Lk, the size of the complete factorial design. We investigate the relationship between the numbers Lt, and two questions in particular: For what t is Lt < Lk? And when Lt = Lk, is the complete factorial design the only array of that size and strength t? Arrays are assumed to be mixed-level. We refer to an array of size less than Lk as a proper fraction. Guided by our main result, we construct a variety of mixed-level proper fractions of strength k − 1 that also satisfy a certain group-theoretic condition.
- 18 April 2016
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 46 (8) , 3690-3697
Open AccessA note on the minimum size of an orthogonal array
It is an elementary fact that the size of an orthogonal array of strength t on k factors must be a multiple of a certain number, say Lt, that depends on the orders of the factors. Thus Lt is a lower bound on the size of arrays of strength t on those factors, and is no larger than Lk, the size of the complete factorial design. We investigate the relationship between the numbers Lt, and two questions in particular: For what t is Lt < Lk? And when Lt = Lk, is the complete factorial design the only array of that size and strength t? Arrays are assumed to be mixed-level. We refer to an array of size less than Lk as a proper fraction. Guided by our main result, we construct a variety of mixed-level proper fractions of strength k − 1 that also satisfy a certain group-theoretic condition.
- Open Access
A note on the minimum size of an orthogonal array
It is an elementary fact that the size of an orthogonal array of strength t on k factors must be a multiple of a certain number, say L_t, that depends on the orders of the factors. Thus L_t is a lower bound on the size of arrays of strength t on those factors, and is no larger than L_k, the size of the complete factorial design. We investigate the relationship between the numbers L_t, and two questions in particular: For what t is L_t < L_k? And when L_t = L_k, is the complete factorial design the only array of that size and strength t? Arrays are assumed to be mixed-level. We refer to an array of size less than L_k as a proper fraction. Guided by our main result, we construct a variety of mixed-level proper fractions of strength k-1 that also satisfy a certain group-theoretic condition.
Open AccessA note on the minimum size of an orthogonal array
It is an elementary fact that the size of an orthogonal array of strength t on k factors must be a multiple of a certain number, say L_t, that depends on the orders of the factors. Thus L_t is a lower bound on the size of arrays of strength t on those factors, and is no larger than L_k, the size of the complete factorial design. We investigate the relationship between the numbers L_t, and two questions in particular: For what t is L_t < L_k? And when L_t = L_k, is the complete factorial design the only array of that size and strength t? Arrays are assumed to be mixed-level. We refer to an array of size less than L_k as a proper fraction. Guided by our main result, we construct a variety of mixed-level proper fractions of strength k-1 that also satisfy a certain group-theoretic condition.
- Open Access
Box-Hunter resolution in nonregular fractional factorial designs
In a 1961 paper, Box and Hunter defined the resolution of a regular fractional factorial design as a measure of the amount of aliasing in the fraction. They also indicated that the maximum resolution is equal to the minimum length of a defining word. The idea of a wordlength pattern has now been extended to nonregular designs by various authors, who show that the minimum generalized wordlength equals the maximum strength plus 1. Minimum generalized wordlength is often taken as the definition of resolution. However, Box and Hunter's original definition, which does not depend on wordlength, can be extended to nonregular designs if they are simple. The purpose of this paper is to prove that the maximum Box-Hunter resolution does equal the maximum strength plus 1, and therefore equals the minimum generalized wordlength. Other approaches to resolution are briefly discussed.
Open AccessBox-Hunter resolution in nonregular fractional factorial designs
In a 1961 paper, Box and Hunter defined the resolution of a regular fractional factorial design as a measure of the amount of aliasing in the fraction. They also indicated that the maximum resolution is equal to the minimum length of a defining word. The idea of a wordlength pattern has now been extended to nonregular designs by various authors, who show that the minimum generalized wordlength equals the maximum strength plus 1. Minimum generalized wordlength is often taken as the definition of resolution. However, Box and Hunter's original definition, which does not depend on wordlength, can be extended to nonregular designs if they are simple. The purpose of this paper is to prove that the maximum Box-Hunter resolution does equal the maximum strength plus 1, and therefore equals the minimum generalized wordlength. Other approaches to resolution are briefly discussed.
- Open Access
Generalized wordlength patterns and strength
Xu and Wu (2001) defined the \emph{generalized wordlength pattern} $(A_1, ..., A_k)$ of an arbitrary fractional factorial design (or orthogonal array) on $k$ factors. They gave a coding-theoretic proof of the property that the design has strength $t$ if and only if $A_1 = ... = A_t = 0$. The quantities $A_i$ are defined in terms of characters of cyclic groups, and so one might seek a direct character-theoretic proof of this result. We give such a proof, in which the specific group structure (such as cyclicity) plays essentially no role. Nonabelian groups can be used if the counting function of the design satisfies one assumption, as illustrated by a couple of examples.Open AccessGeneralized wordlength patterns and strength
Xu and Wu (2001) defined the \emph{generalized wordlength pattern} $(A_1, ..., A_k)$ of an arbitrary fractional factorial design (or orthogonal array) on $k$ factors. They gave a coding-theoretic proof of the property that the design has strength $t$ if and only if $A_1 = ... = A_t = 0$. The quantities $A_i$ are defined in terms of characters of cyclic groups, and so one might seek a direct character-theoretic proof of this result. We give such a proof, in which the specific group structure (such as cyclicity) plays essentially no role. Nonabelian groups can be used if the counting function of the design satisfies one assumption, as illustrated by a couple of examples. - 1 August 2009
- Published by Elsevier in Journal of Statistical Planning and Inference
- Vol. 139 (8) , 2706-2714
Invariance of generalized wordlength patterns
- 1 August 2009
- Published by Elsevier in Journal of Statistical Planning and Inference
- Vol. 139 (8) , 2706-2714
Invariance of generalized wordlength patterns
- Open Access
Invariance of generalized wordlength patterns
The generalized wordlength pattern (GWLP) introduced by Xu and Wu (2001) for an arbitrary fractional factorial design allows one to extend the use of the minimum aberration criterion to such designs. Ai and Zhang (2004) defined the $J$-characteristics of a design and showed that they uniquely determine the design. While both the GWLP and the $J$-characteristics require indexing the levels of each factor by a cyclic group, we see that the definitions carry over with appropriate changes if instead one uses an arbitrary abelian group. This means that the original definitions rest on an arbitrary choice of group structure. We show that the GWLP of a design is independent of this choice, but that the $J$-characteristics are not. We briefly discuss some implications of these results.
Open AccessInvariance of generalized wordlength patterns
The generalized wordlength pattern (GWLP) introduced by Xu and Wu (2001) for an arbitrary fractional factorial design allows one to extend the use of the minimum aberration criterion to such designs. Ai and Zhang (2004) defined the $J$-characteristics of a design and showed that they uniquely determine the design. While both the GWLP and the $J$-characteristics require indexing the levels of each factor by a cyclic group, we see that the definitions carry over with appropriate changes if instead one uses an arbitrary abelian group. This means that the original definitions rest on an arbitrary choice of group structure. We show that the GWLP of a design is independent of this choice, but that the $J$-characteristics are not. We briefly discuss some implications of these results.
- 1 August 2007
- Published by Springer Nature in Journal of Mathematical Biology
- Vol. 55 (5-6) , 861-882
Optimizing selection for function-valued traits
- 1 August 2007
- Published by Springer Nature in Journal of Mathematical Biology
- Vol. 55 (5-6) , 861-882
Optimizing selection for function-valued traits
- Open Access
- 14 May 2001
- Published by American Mathematical Society (AMS) in Transactions of the American Mathematical Society
- Vol. 353 (10) , 3945-3969
Stochastic processes with sample paths in reproducing kernel Hilbert spaces
A theorem of M. F. Driscoll says that, under certain restrictions, the probability that a given Gaussian process has its sample paths almost surely in a given reproducing kernel Hilbert space (RKHS) is either 0 or 1. Driscoll also found a necessary and sufficient condition for that probability to be 1. Doing away with Driscoll's restrictions, R. Fortet generalized his condition and named it nuclear dominance. He stated a theorem claiming nuclear dominance to be necessary and sufficient for the existence of a process (not necessarily Gaussian) having its sample paths in a given RKHS. This theorem-specifically the necessity of the condition-turns out to be incorrect, as we will show via counterexamples. On the other hand, a weaker sufficient condition is available. Using Fortet's tools along with some new ones, we correct Fortet's theorem and then find the generalization of Driscoll's result. The key idea is that of a random element in a RKHS whose values are sample paths of a stochastic process. As in Fortet's work, we make almost no assumptions about the reproducing kernels we use, and we demonstrate the extent to which one may dispense with the Gaussian assumption.
- 14 May 2001
- Published by American Mathematical Society (AMS) in Transactions of the American Mathematical Society
- Vol. 353 (10) , 3945-3969
Open AccessStochastic processes with sample paths in reproducing kernel Hilbert spaces
A theorem of M. F. Driscoll says that, under certain restrictions, the probability that a given Gaussian process has its sample paths almost surely in a given reproducing kernel Hilbert space (RKHS) is either 0 or 1. Driscoll also found a necessary and sufficient condition for that probability to be 1. Doing away with Driscoll's restrictions, R. Fortet generalized his condition and named it nuclear dominance. He stated a theorem claiming nuclear dominance to be necessary and sufficient for the existence of a process (not necessarily Gaussian) having its sample paths in a given RKHS. This theorem-specifically the necessity of the condition-turns out to be incorrect, as we will show via counterexamples. On the other hand, a weaker sufficient condition is available. Using Fortet's tools along with some new ones, we correct Fortet's theorem and then find the generalization of Driscoll's result. The key idea is that of a random element in a RKHS whose values are sample paths of a stochastic process. As in Fortet's work, we make almost no assumptions about the reproducing kernels we use, and we demonstrate the extent to which one may dispense with the Gaussian assumption.
- 31 March 2000
- Published by Elsevier in Journal of Statistical Planning and Inference
- Vol. 84 (1-2) , 343
Erratum to “Conjectures About Hadamard Matrices” [J Statist. Plann. Inference 72 (1998) 7–14]
- 31 March 2000
- Published by Elsevier in Journal of Statistical Planning and Inference
- Vol. 84 (1-2) , 343
Erratum to “Conjectures About Hadamard Matrices” [J Statist. Plann. Inference 72 (1998) 7–14]