irfPlotData#

Purpose#

Reshape IRF, FEVD, or SV-BVAR IRF results into a plot-ready long-format dataframe.

Format#

df = irfPlotData(result, shock, response)#

df = irfPlotData(result)

Parameters:

result (struct) – an instance of an irfResult, svIrfResult, or fevdResult structure.
shock (scalar) – Optional, shock index (1 to m). If omitted, all shocks are included.
response (scalar) – Optional, response variable index (1 to m). If omitted, all responses are included.

Returns:

df (dataframe) – Dataframe. For irfResult: columns horizon, shock, response, value. For svIrfResult: columns horizon, shock, response, median, lower_68, upper_68, lower_90, upper_90. For fevdResult: columns horizon, shock, response, share.

Examples#

Plot a Single Shock-Response Pair#

new;
library timeseries;

data = loadd(getGAUSSHome("pkgs/timeseries/examples/macro.dat"));
result = varFit(data, 4);
irf = irfCompute(result, 20, quiet=1);

// GDP response to FFR shock
df = irfPlotData(irf, 3, 1);
plotXY(df[., "horizon"], df[., "value"]);

Plot SV-BVAR IRF with Credible Bands#

new;
library timeseries;

data = loadd(getGAUSSHome("pkgs/timeseries/examples/macro.dat"));
result = bvarSvFit(data, quiet=1);
irf = irfSvCompute(result, 20, quiet=1);

// GDP response to FFR shock with bands
df = irfPlotData(irf, 3, 1);

// Plot median with 68% band
plotXY(df[., "horizon"],
    df[., "median"]~df[., "lower_68"]~df[., "upper_68"]);

Extract All Pairs#

new;
library timeseries;

data = loadd(getGAUSSHome("pkgs/timeseries/examples/macro.dat"));
result = varFit(data, 4, quiet=1);
irf = irfCompute(result, 20, quiet=1);

// All m*m pairs in long format
df = irfPlotData(irf);
print df[1:10, .];

Remarks#

This is a convenience function for plotting. It reshapes the array-of-matrices representation into a long-format dataframe that can be passed directly to plotXY() or exported to CSV.

No Rust FFI call — this is a pure GAUSS reshape operation.

Library#

timeseries

Source#

irf.src