In this paper we formulate a particular statistical model validation problem in which we wish to determine the probability that a certain hypothesized parametric uncertainty model is consistent with a given input-output data record. Using a Bayesian approach and ideas from the field of hypothesis testing, we show that in many cases of interest this problem reduces to computing relative weighted volumes of convex sets in RN (where N is the number of uncertain parameters). We also present and discuss a randomized algorithm based on gas kinetics, as well as the existing Hit-and-Run family of algorithms, for probable approximate computation of these volumes.

1.
Applegate, D., and Kannan, R., “Sample and Integration of Near Log-Concave Functions,” Comp. Science Report CMU, 1990.
2.
Barany, I., and Furedi, Z., “Computing the Volume is Difficult,” Proc. of the 18th Annual Symp. on Theory of Computing, pp. 442–447, 1986.
3.
Be´lisle
C. J. P.
,
Romejin
H. E.
, and
Smith
R. L.
, “
Hit-and-Run Algorithms for Generating Multivariate Distributions
,”
Mathematics of Operations Research
, Vol.
18
, No.
2
, pp.
255
266
,
1993
.
4.
Dyer
M. E.
, and
Frieze
A. M.
, “
On the Complexity of Computing the Volume of a Polyhedron
,”
SIAM J. Computing
, Vol.
17
, pp.
967
974
,
1988
.
5.
Goodwin
G. C.
,
Gevers
M.
, and
Ninness
B.
, “
Quantifying the Error in Estimated Transfer Functions with Application to Model Selection
,”
IEEE TAC
, Vol.
37
, pp.
913
928
, July
1992
.
6.
Gu
G.
, and
Khargonekar
P. P.
, “
Linear and Nonlinear Algorithms for Identification in H with Error Bounds
,”
IEEE TAC
, Vol.
37
, pp.
953
963
, July
1992
.
7.
Helmicki
A. J.
,
Jacobson
C. A.
, and
Nett
C. N.
, “
Control Oriented System Identification: A Worst-Case/Deterministic Approach in H
,”
IEEE TAC
, Vol.
36
, pp.
1163
1176
, Oct.
1991
.
8.
Karwan, M. H., ed., Redundancy in Mathematical Programming, Springer-Verlag, New York, 1993.
9.
Kearns, M. J., and Vazirani, U. V., Topics in Computational Learning Theory, preprint, 1993.
10.
Khachiyan
L. G.
, “
On the Complexity of Computing the Volume of a Polytope
,”
Izvestia Acad. Nauk. SSSR Engr. Cybernetics
, Vol.
3
, pp.
216
217
,
1988
. (in Russian)
11.
Kosut
R. L.
,
Lau
M.
, and
Boyd
S.
, “
Set-Membership Identification of Systems with Parametric and Nonparametric Uncertainties
,”
IEEE TAC
, Vol.
37
, pp.
929
941
, July
1992
.
12.
Krause
J. M.
, and
Khargonekar
P. P.
, “
Parameter Identification in the Presence of Nonparametric Dynamic Uncertainty
,”
Automatica
, Vol.
26
, pp.
113
124
, Jan.
1990
.
13.
Lee, L., and Poolla, K., “Statistical Validation for Uncertainty Models,” Control, Complexity, and Identification: A festschrift for Professor George Zames, Springer-Verlag, 1994.
14.
Lee, L. H., and Poolla, K., “Statistical Validation and Testability of Uncertainty Models,” submitted for publication to Automatica.
15.
Ljung, L., System Identification: Theory for the User, Prentice-Hall, Englewood Cliffs, NJ, 1987.
16.
Ljung
L.
, and
Yuan
Z.-D.
, “
Asymptotic Properties of Black-Box Identification of Transfer Functions
,”
IEEE TAC
, Vol.
30
, pp.
514
530
, June
1985
.
17.
Ma¨kila¨, P. M., and Partington, J. R., “Robust Approximation and Identification in H,” Proc. of the 1991 ACC, pp. 70–76, 1991.
18.
Meyn, S. P., and Tweedie, R. L., Markov Chains and Stochastic Stability, Springer-Verlag, New York, 1993.
19.
Partington
J. R.
, “
Robust Identification and Interpolation in H
,”
Int. J. Contr.
, Vol.
54
, pp.
1281
1290
,
1991
.
20.
Poolla
K.
,
Khargonekar
P. P.
,
Tikku
A.
,
Krause
J.
, and
Nagpal
K. M.
, “
A Time-Domain Approach to Model Validation
,”
IEEE TAC
, Vol.
39
, No.
5
, pp.
951
959
,
1994
.
21.
Popper, K., Conjectures and Refutations, Harper and Row, 1963.
22.
Smith
R. L.
, “
Efficient Monte Carlo Procedures for Generating Points Uniformly Distributed Over Bounded Regions
,”
Operations Research
, Vol.
32
, No.
6
, pp.
1296
1308
,
1984
.
23.
Smith
R.
, and
Doyle
J. C.
, “
Towards a Methodology for Robust Parameter Identification
,”
IEEE TAC
, Vol.
37
, pp.
942
952
, July
1992
.
24.
Tempo
R.
, and
Wasilkowski
G.
, “
Maximum Likelihood Estimators and Worst Case Optimal Algorithms for System Identification
,”
Systems and Control Letters
, Vol.
10
, pp.
265
270
,
1988
.
25.
Tse
D. N. C.
,
Dahleh
M. A.
, and
Tsitsiklis
J. N.
, “
Optimal Asymptotic Identification Under Bounded Disturbances
,”
IEEE TAC
, Vol.
38
, pp.
1176
1190
,
1993
.
26.
Valiant
L. G.
, “
A Theory of the Learnable
,”
Communications of the ACM
, Vol.
27
, pp.
1134
1142
,
1984
.
27.
Younce
R. C.
, and
Rohrs
C. E.
, “
Identification with Non-Parametric Uncertainties
,”
IEEE TAC
, Vol.
37
, pp.
715
728
, June
1992
.
28.
Zames
G.
,
Lin
L.
, and
Wang
L. Y.
, “
Fast Identification n-Width and Uncertainty Principles for LTI and Slowly Varying Systems
,”
IEEE TAC
, Vol.
39
, pp.
1827
1838
, Sept
1994
.
This content is only available via PDF.