Symbolic time-series analysis is used for estimating the parameters of chaotic systems. It is assumed that a “target model” (i.e., a discrete- or continuous-time description of the data-generating mechanism) is available, but with unknown parameters. A time series, i.e., a noisy, finite sequence of a measured (output) variable, is given. The proposed method first prescribes to symbolize the time series, i.e., to transform it into a sequence of symbols, from which the statistics of symbols are readily derived. Then, a symbolic model (in the form of a Markov chain) is derived from the data. It allows one to predict, in a probabilistic fashion, the time evolution of the symbol sequence. The unknown parameters are derived by matching either the statistics of symbols, or the symbolic prediction derived from data, with those generated by the (parametrized) target model. Three examples of application (the Henon map, a population model, and the Duffing system) prove that satisfactory results can be obtained even with short time series.