Abstract: Using the weighed conditional least squares method, we estimated the parameters of the firstorder integer-valued autoregressive model (ADCINAR(1)) based on dependent counting series. We gave the expression of parameter estimation 
 and its asymptotic distribution, and derived the higherorder moments, higherorder cumulants, spectral density and bispectral density of the model. The numerical simulation results show that the validity of weighed conditional least squares method is verified by comparing weighed conditional least squares estimation with conditional least squares estimation and YuleWalker estimation.

Key words: bispectral density, dependent counting series, higherorder moment, integervalued time series, weighed conditional least squares