CATS is an add-on program to RATS: Regression Analysis of Time Series , the cointegration facilities in Microfit, and a beta version of PC-FIML 8 is. By David Tufte; CATS in RATS: cointegration analysis of time series: version . CATS in RATS: Cointegration Analysis of Time Series. Front Cover. Henrik Hansen, Katarina Juselius. Estima, – Cointegration – 87 pages.

Author: Jukus Maurr
Country: Guinea-Bissau
Language: English (Spanish)
Genre: Environment
Published (Last): 19 October 2018
Pages: 227
PDF File Size: 11.37 Mb
ePub File Size: 11.86 Mb
ISBN: 807-9-90310-621-3
Downloads: 70103
Price: Free* [*Free Regsitration Required]
Uploader: Metilar

EconPapers: CATS in RATS: cointegration analysis of time series: version

As an illustration, we will input a relation based on the real interest rate parity b2t dp2t D b1t dpc1t discussed in paragraph 3. In the X-form, calculation of the con dence bound is invalidated until First, itme specify the restrictions, typically by inputting a number of design matrices. Di is given by Dit D 1ftD Compared to the other automated znalysis procedures CATSmining is somewhat more complicated to use as it allows for user de ned relations to be tested.

In order to obtain identi cation you must normalize each inn of? Models containing structural breaks are discussed in Johansen, Mosconi, and Nielsenwhere a response surface approximation to the asymptotic distribution of the rank test is reported for some model speci cations.

In general, an option has a default value which will be applied unless you specify another value. Hence, if the approximation is indeed valid for your model, serids should use the BREAK option to get valid critical values.


For large models this step may be very time consuming and can generate a vast number of stationary relations. To do so, choose six restrictions and specify the homogeneity restric- tion as shown in gure 3.

Crossplot creates crossplots of any system variables including dummies and weakly exogenous re- gressors. In this case, it is the space spanned by that is determined by the data, and in order to uniquely identify the cointegrating vectors we need to impose r.

Product Information

Furthermore, you can specify if you want these written in brackets below the respective estimates or in a separate array. Variable Exogeneity will test if any of the variables can be re- garded as weakly exogenous when the parameter of interest is: An I 1 Analysis The lines executing the new model should look like this: The Economics of Economists: This will allow you to see how close the largest unrestricted roots are to the unit circle.

There are products that complement the RATS software anqlysis. Restrictions on and You can jointly test restrictions on ; and of the type R 0 D 0, by imposing the restrictions onand then, when prompted, choose either to specify or load restrictions on: Estimate many kinds of regression models, including ordinary, weighted, and generalized least squares, seemingly unrelated regressions SURnon-linear least squares, non-linear systems, generalized method of moments, ARCH and GARCH models, and other maximum-likelihood models.

Note that we do not need to re-execute the first four instructions the “calendar” scheme is still in effect, and analyiss data series are still in memory.


If the basic relations have not been generated algorithm step 1this can be done automatically.

CATS in RATS: cointegration analysis of time series: version 1.01

Save Restrictions To save the currently imposed restrictions, simply choose I I 1: Max Test of Beta Constancy Figure 4. The restrictions are generically identifying if, for all i and k D 1;: If we assume that is restricted as D. A detailed description of the dummy variables can be found in section 3.

If you wish to perform sensitivity analysis for rby, for instance, setting r D 1 or r D 2, the relevant test statistics for the exclusion tests are in the same table.

This zip files includes the example programs and data file with the PDF book describing the steps taking and discussing the results. Citation In order for others to be able to replicate your results, CATS should always be cited cointegrarion any paper or publication where it is applied.

This is particularly true for the I.

In the following we assume analysid X t is at most I. The procedures for analyzing the structural MA-model and simulating the tables for the trace test when there is a shift dummy in the cointegration relations are originally his work which he kindly allowed us to include in CATS. Preferences you do not need to source cats.