The RATS Software Forum

} has always been synonymous with END. This appears to work because the { (which is synonymous with BEGIN) at the end of the line gets eaten by the parser. On the other hand, do i=1,3 { ?i } (where the { is on a separate line) doesn't work as the } is closing the {} block and not the do loop. do i=1...

I'm not sure that that will provide any better information than you could get with just the standard @flux test. In particular, it would be unlikely to help with any specific "parameter stability" since it really wouldn't be testing for that, but just for a general process break. The progr...

I'm not sure I understand what you are trying to do. Are you studying an economy which transitioned to dollarization, or an economy which has been dollarized throughout the data range? A VAR, or at least a VAR applied to that economy, can't really help much with the first.

That is and has been a problem for decades. At one point people looked into frequency domain methods (such as cross-spectral analysis) to try to break down the correlation by frequency, where the longer (multi-year) cycles were the main focus. The problem there is that first-differencing series larg...

The Chan-McAleer AFE 2003 replication actually estimates the STAR-GARCH model first before moving on to the more complicated model. You should read the rather lengthy comments in that post, as the model really doesn't work well in the presence of outliers.

chanmcaleer_afe2003.zip is a replication file for Felix Chan & Michael McAleer, 2003. "Estimating smooth transition autoregressive models with GARCH errors in the presence of extreme observations and outliers," Applied Financial Economics , vol. 13, no 8, 581-592. This demonstrates es...

It's now tsay3p185.rpf. (We changed the naming system to include the edition in the textbook examples).

Have you looked at the harveyp090.rpf example? That does the cycle as a separate trigonometric cycle rather than an AR(2) with complex roots.

Main Topics

• RATS Version 11.1
• RATS e-courses now available at no charge
• OECD Download now available
• RATS on RePEc

You can do the whole extra calculation with the single instruction: gset hcov %regstart() %regend() = %mqform(%cvtocorr(q),%diag(%xt(vol,t))) The problem was with trying to do a COMPUTE on a single element of HCOV without the range of the SERIES[SYMM] ever having been set. GSET takes care of that. (...

ac_1 wrote: ↑Sun Jan 25, 2026 1:09 pm acKupiecBlockBoot.src is wrong, can it be fixed?

11.1 fixed a problem with parameters or options inside PARMSETS used in SUMMARIZE.

Compute the percentage of draws that are on the wrong side of the hypothesized alpha.

sstats(mean) 1 ndraws (alphahatDist>alpha)>>pctover (alphadataDist<alpha)>>pctunder

whichever of pctover and pctunder is appropriate. See the first example in the description of SSTATS.

If you put it in the Z (as a addition to the trend state), then it will accumulate in the state (it will be an innovational shift) while you seem to be describing it as a additive shift.

No. You're not bootstrapping to get an estimate of alpha; the mean across bootstrap samples should be roughly the same as the mean of the data. Instead, you're bootstrapping to get the sampling distribution and to compare that to the assumed value of alpha. So you want to count the percentage of tim...

No. That's a different type of bootstrap (which is bootstrapping data under the null). You need to compare the results with the assumed value of alpha.