* * DISTRIBLAG.RPF * Example of estimation of a distributed lag * * RATS User's Guide, Example from Section 2.8. * open data haversample.rat calendar(m) 1947 data(format=rats) 1947:1 2007:4 fltg ftb3 set shortrate = ftb3 set longrate = fltg * * Long unrestricted lags * linreg longrate # constant shortrate{0 to 24} summarize # shortrate{0 to 24} set lagdist 1 25 = %beta(t+1) graph(header="Lag Distribution-Long Unconstrained",number=0) # lagdist 1 25 * * ARDL estimates * linreg longrate # constant longrate{1 2 3} shortrate{0 to 4} * * From the regression, extract the autoregressive polynomial, (which will * be 1-a(1)L-a(2)L^2-a(3)L^3) since LONGRATE is the dependent variable), * and the distributed lag polynomial. Divide DLPOLY by ARPOLY and expand * out to the 24th degree. * compute arpoly=%eqnlagpoly(0,longrate) compute dlpoly=%eqnlagpoly(0,shortrate) compute ardlpoly=%polydiv(dlpoly,arpoly,24) * * Copy the expanded polynomial to the series lagdist and graph it. * set lagdist 1 25 = ardlpoly(t) graph(header="Lag Distribution-ARDL(3,4)",number=0) # lagdist * * Compute the long-run response from the ARDL model * disp "LR Response" %polyvalue(dlpoly,1.0)/%polyvalue(arpoly,1.0)