statsmodels.tsa.arima_process.deconvolve statsmodels.tsa.arima_process.deconvolve(num, den, n=None) [source] Deconvolves divisor out of signal, division of polynomials for n terms calculates den^{-1} * num Parameters: num : array_like signal or lag polynomial denom : array_like coefficients of lag polynomial (linear filter) n : None or int number of terms of quotient Returns: quot : array quotient or filtered series rem : array remainder Notes If num is a time series, then this

statsmodels.tsa.arima_process.index2lpol statsmodels.tsa.arima_process.index2lpol(coeffs, index) [source] expand coefficients to lag poly Parameters: coeffs : array non-zero coefficients of lag polynomial index : array index (lags) of lagpolynomial with non-zero elements ar : array_like coefficients of lag polynomial Returns: ar : array_like coefficients of lag polynomial

statsmodels.tsa.arima_process.arma_periodogram statsmodels.tsa.arima_process.arma_periodogram(ar, ma, worN=None, whole=0) [source] periodogram for ARMA process given by lag-polynomials ar and ma Parameters: ar : array_like autoregressive lag-polynomial with leading 1 and lhs sign ma : array_like moving average lag-polynomial with leading 1 worN : {None, int}, optional option for scipy.signal.freqz (read ?w or N?) If None, then compute at 512 frequencies around the unit circle. If a sin

statsmodels.tsa.arima_process.arma_impulse_response statsmodels.tsa.arima_process.arma_impulse_response(ar, ma, nobs=100) [source] get the impulse response function (MA representation) for ARMA process Parameters: ma : array_like, 1d moving average lag polynomial ar : array_like, 1d auto regressive lag polynomial nobs : int number of observations to calculate Returns: ir : array, 1d impulse response function with nobs elements Notes This is the same as finding the MA representati

statsmodels.tsa.arima_process.arma_generate_sample statsmodels.tsa.arima_process.arma_generate_sample(ar, ma, nsample, sigma=1, distrvs=, burnin=0) [source] Generate a random sample of an ARMA process Parameters: ar : array_like, 1d coefficient for autoregressive lag polynomial, including zero lag ma : array_like, 1d coefficient for moving-average lag polynomial, including zero lag nsample : int length of simulated time series sigma : float standard deviation of noise distrvs : func

statsmodels.tsa.arima_process.arma_pacf statsmodels.tsa.arima_process.arma_pacf(ar, ma, nobs=10) [source] partial autocorrelation function of an ARMA process Parameters: ar : array_like, 1d coefficient for autoregressive lag polynomial, including zero lag ma : array_like, 1d coefficient for moving-average lag polynomial, including zero lag nobs : int number of terms (lags plus zero lag) to include in returned pacf Returns: pacf : array partial autocorrelation of ARMA process given

statsmodels.tsa.arima_process.arma_acovf statsmodels.tsa.arima_process.arma_acovf(ar, ma, nobs=10) [source] theoretical autocovariance function of ARMA process Parameters: ar : array_like, 1d coefficient for autoregressive lag polynomial, including zero lag ma : array_like, 1d coefficient for moving-average lag polynomial, including zero lag nobs : int number of terms (lags plus zero lag) to include in returned acovf Returns: acovf : array autocovariance of ARMA process given by ar

statsmodels.tsa.arima_process.arma_acf statsmodels.tsa.arima_process.arma_acf(ar, ma, nobs=10) [source] theoretical autocorrelation function of an ARMA process Parameters: ar : array_like, 1d coefficient for autoregressive lag polynomial, including zero lag ma : array_like, 1d coefficient for moving-average lag polynomial, including zero lag nobs : int number of terms (lags plus zero lag) to include in returned acf Returns: acf : array autocorrelation of ARMA process given by ar, m

statsmodels.tsa.arima_process.ArmaProcess class statsmodels.tsa.arima_process.ArmaProcess(ar, ma, nobs=100) [source] Represent an ARMA process for given lag-polynomials This is a class to bring together properties of the process. It does not do any estimation or statistical analysis. Parameters: ar : array_like, 1d Coefficient for autoregressive lag polynomial, including zero lag. See the notes for some information about the sign. ma : array_like, 1d Coefficient for moving-average lag po

statsmodels.tsa.arima_process.arma2ma statsmodels.tsa.arima_process.arma2ma(ar, ma, nobs=100) get the impulse response function (MA representation) for ARMA process Parameters: ma : array_like, 1d moving average lag polynomial ar : array_like, 1d auto regressive lag polynomial nobs : int number of observations to calculate Returns: ir : array, 1d impulse response function with nobs elements Notes This is the same as finding the MA representation of an ARMA(p,q). By reversing the