Journal of Applied Probability · 1985 · 160 citations · 8 references
Natural SciencesMathematicsProbability TheoryStochastic ProcessesTime Series AnalysisMaximum Likelihood EstimationStationarity AnalysisThreshold ModelingStrict StationarityThreshold AutoregressionThreshold Autoregressive Models
We consider the model Z t = φ (0, k ) + φ (1, k ) Z t –1 + a t ( k ) whenever r k −1 < Z t −1 ≦ r k , 1≦ k ≦ l , with r 0 = –∞ and r l =∞. Here { φ ( i, k ); i = 0, 1; 1≦ k ≦ l } is a sequence of real constants, not necessarily equal, and, for 1≦ k ≦ l , { a t ( k ), t ≧1} is a sequence of i.i.d. random variables with mean 0 and with { a t ( k ), t ≧1} independent of { a t ( j ), t ≧1} for j ≠ k. Necessary and sufficient conditions on the constants { φ ( i, k )} are given for the stationarity of the process. Least squares estimators of the model parameters are derived and, under mild regularity conditions, are shown to be strongly consistent and asymptotically normal.
8
Joseph D. Petruccelli, Samuel W. Woolford · Journal of Applied Probability · 1984 · 249 citations
Criteria for classifying general Markov chains
Richard L. Tweedie · Advances in Applied Probability · 1976 · 248 citations