H O M E / I N F O / P R O D U C T S / O R D E R / S U P P O R T

TSP / What is TSP? / Features / Requirements

Examples of TSP Graphics:

Linear model fit Log Likelihood plot Panel data VAR Impulse Response

The first three graphs below are based on TSP commands similar to those below:

 
SMPL 1,100;
RANDOM(SEEDIN=12345) X E; 
Y = X + E;
OLSQ Y C X;
GRAPH(PREVIEW) X Y @FIT;
 

This is an example of a TSP-generated graph from the PowerMac version of TSP.

Here is a similar graph in TSP/GiveWin (it looks the same in OxMetrics):

And this is what the graphics look like in the DOS/Windows version of TSP:

Most unix versions of TSP have gnuplot graphics. Here is an example showing a plot of the Log Likelihood for the two equation sample selection model (Heckman) as a function of the correlation coefficient between the two equations; showing the possibility of multiple local maxima.

Here is an example of panel graphics (implemented March 2001). It was made with the PLOT command on stacked panel data (the Grunfeld investment data). The lines are broken between each individual, so it is easy to see how some individuals fit better than others, and how the "pooled" and "fixed effects" fits compare.

Here is an example of plots of the Generalized Impulse Response from VAR estimation of a model with GNP, Consumption, and Investment:

If you have any questions or comments about TSP please send an email to info@tspintl.com.

Comments or questions about this website should also be sent to the info@tspintl.com. Lost? Please consult the site map.