The RATS Software Forum

Hello, Is the procedure shaped for testing no break versus one break? i find a supF(1|0) very high (1640) for a sample of 444 obs. (pure structural change model). Given the number of observations and the shape of my serie (REER between 1975 to 2010), a high probability of rejected the null (zero bre...

The paper is : "International Business Cycles: Regime Shifts in the Stochastic Process of Economic Growth" and the standard code for ms-var seems to be: nonlin(parmset=varparms) mu phi sigmav nonlin(parmset=msparms) theta gset pt_t gstart gend = %zeros(nexpand,1) gset pt_t1 gstart gend = %...

it seems to be also the case in the Replication file for Krolzig's "International Business Cycles: Regime
Shifts in the Stochastic Process of Economic Growth.

Hi Tom, I would like to identify common business cycle of a set of countries (as in krozlig 2001), and test the predictive power of leading indicators in the identification of this common cycle. The best approach may be a MS-VAR-TVTP model. Do the programm of filardo 1994 enjoy this feature? Because...

Hello,

I don't find the code needed for differentiate series with symbol and in the same time with color on a same graph. The style symbols give the same output.

Thank You.

Hello, I would like a line in my scatter plot wich rely all point of the scatter. However the scatter is composed of pairs (points) that are aligned forming a curve more or less flat (regime switching probabilities given transitional variable). The curve is modelling given a logistic function... I u...

As for precedent solution, it doesn't work. Thank you, what is strange is that i have no error message or something else... the prog stop after the last command before the code in question.

My condition should be: if the first value of my serie p1tr is different from NA, lb is executed. I tried this if.not.p1tr(1976:2)=NA @lb(lags=1) reso but it doesn't work. Surely because NA is a real. An d i tried @lb(lags1) reso=%if(%valid(p1trr)) but it doesn't work too. Thanks for your help.

Thank you. Precedently i had: The Error Occurred At Location 267, Line 21 of LB Called From Location 3742, Line 265 of loop/block ## REG7. Variance is Zero ## REG7. Variance is Zero The Error Occurred At Location 267, Line 21 of LB Called From Location 3742, Line 265 of loop/block But It seems that ...

Hi, Is there a possibility to forced a loop even if we have a error message? In fact i created a loop to test different lag specifications for MS-TVTP model. And for each lag i compute a Ljung-box test for my residuals (the test is inside the loop). The problem is that for some specification, the LB...

Thank you, Yes it work with gsave=none or gformat=none .... Thank you very much. Please let me ask a last question, there is a possibility to save graph with "env save" but without display or print the graph ? In fact i need to save some graph but it is no necessary to open a graph window....

Hi, I estimate different specifications of a MS-TVTP model. I mean by different speficification, different set of lag (for the exogenous and transition variables). But i would like to make a loop to do it automatically. I arrived to creat a basic loop for estimation of a set of lag associated to the...

Thank you, However it seems that there is a bug with env gsave command: 1\ firstly i run my prog with the command env gsave="sing_mal_usa*.eps" gformat=portrait 2\ I wante to comment-out env gsave line, so i use simply this command: *env gsave="sing_mal_usa*.eps" gformat=portrait...

Hi,

I would like to display in a report the signifiance of my betas coefficient, indeed the signifiance associated to the T-stat.

I tried %signif and with other %**signif functions but it doesn't work.

Thank you.

Hi, I must save a lot of graphs and i would like to generate automatically the name of these ones, indeed without rename each files. I tried this code but without approrpiate results. compute nlags = 1 compute ivlags = 1 compute con1lags = 1 ***** Reading the data Cal(q) 1975:1 open data RATES_GDP_q...