The base level constant that shifts the series.
The autoregressive coefficient determining the influence of the previous value on the current value.
The noise term magnitude, which is added or subtracted randomly based on a dice function.
The number of samples to generate in the autoregressive process.
result: A double array containing n samples of the generated autoregressive process.
Notes: - The process is defined as: yi = alpha + rho * y[i-1] ± e_t where the sign of e_t is randomly determined by the dice(0.5, 0.5) function. - If rho = 0, the process degenerates into a purely stochastic sequence. - If e_t = 0, the process becomes a simple autoregressive model without noise. - The function dynamically appends values to time_series, which may cause memory reallocation. If performance is critical, preallocating the array may be more efficient. - The dice function is assumed to return 1 or 0 with equal probability. - This type of stochastic autoregressive model can be useful in simulating random shocks in economic and financial time series.
Summary: Generates an AutoRegressive (AR) process with stochastic perturbations determined by a dice-based mechanism. The function models a time series where each value is influenced by its previous value, a deterministic term (alpha), and a stochastic noise term (e_t) that randomly switches sign.