We consider the relationship between the finite-dimensional distributions of a stationary time series model and its asymptotic behavior in the framework of interval-valued probability (IVP), a simple generalization of additive probability measures. By Caratheodory's theorem, the specification of a countably additive probability measure on the algebra of cylinders C uniquely defines its behavior on (C) (containing the tail events). If the measure is stationary, then the ergodic theorem indicates that its extension assigns zero probability to the tail event consisting of all sequences for which the time averages diverge (the divergence event). This link between the marginals and the tail behavior is no longer valid in IVP, and we can reconcile arbitrary finite-dimensional distributions and tail behavior for stationary IVP-based models. The lining mechanism between the marginals of a time series model and its asymptotic behavior turns out to be continuity, not stationarity or even additivity. We prove that any stationary finitely additive probability (charge) defined on cylinders has a stationary charge extension that can assign the divergence event any prescribed probability. Moreover, on the space of binary sequences, we consider IVP models that incorporate: (i) Stationarity. (ii) Continuity along C. (iii) Almost sure support for divergence. (iv) Estimability of the divergence event from cylinders. (v) Nearly additive finite-dimensional distributions. We enhance the previous constructions of IVP's satisfying (i)-(iv) so that they satisfy (v) by agreeing with a stationary measure either exactly on one-dimensional cylinders or arbitrarily closely on a given clans of bounded-dimensional cylinders, Our time series constructions follow from the observation that the algebra of cylinders and the tail -algebra are mutually nonsingular. We use the same idea to prove the existence of joints for general marginal IVP's. These constructions have implications for frequentist interpretations of probability
[1]
G. Choquet.
Theory of capacities
,
1954
.
[2]
Glenn Shafer,et al.
A Mathematical Theory of Evidence
,
2020,
A Mathematical Theory of Evidence.
[3]
Bernd Anger,et al.
Representation of capacities
,
1977
.
[4]
T. Fine,et al.
Towards a Frequentist Theory of Upper and Lower Probability
,
1982
.
[5]
Anurag Kumar,et al.
Stationary lower probabilities and unstable averages
,
1985
.
[6]
T. Fine,et al.
A Note on Undominated Lower Probabilities
,
1986
.
[7]
Terrence L. Fine,et al.
Continuous Lower Probability-Based Models for Stationary Processes with Bounded and Divergent Time Averages
,
1987
.
[8]
W. Sudderth,et al.
A sequence of coin toss variables for which the strong law fails
,
1988
.
[9]
Terrence L. Fine,et al.
Lower probability models for uncertainty and nondeterministic processes
,
1988
.
[10]
P. Walley.
Statistical Reasoning with Imprecise Probabilities
,
1990
.
[11]
T. Fine,et al.
Stationarity and almost sure divergence of time averages in interval-valued probability
,
1991
.