statsmodels.tsa.vector_ar.vecm.select_coint_rank

statsmodels.tsa.vector_ar.vecm.select_coint_rank(endog, det_order, k_ar_diff, method='trace', signif=0.05)[source]

Calculate the cointegration rank of a VECM.

Parameters
endogarray_like (nobs_tot x neqs)

The data with presample.

det_orderint

  • -1 - no deterministic terms

  • 0 - constant term

  • 1 - linear trend

k_ar_diffint, nonnegative

Number of lagged differences in the model.

methodstr, {"trace", "maxeig"}, default: "trace"

If "trace", the trace test statistic is used. If "maxeig", the maximum eigenvalue test statistic is used.

signiffloat, {0.1, 0.05, 0.01}, default: 0.05

The test’s significance level.

Returns
rankCointRankResults

A CointRankResults object containing the cointegration rank suggested by the test and allowing a summary to be printed.