Recent content by Lubomir

  1. L

    error correction model

    Hi, Could anyone give me the code for error correction model, please? I learned, how to apply both steps in "two-stage approach", but who should these results from both steps be used? What is the final model that should be implemented? Can anyone give me the SAS code that I could use? Any...
  2. L

    interpretation for %DFTEST results

    Hello, I need to interpret the results of this macro %DFTEST: proc print data=sashelp.air;run; %dftest(sashelp.air, air, ar=1, dif=(1), trend=1, outstat=delete); proc print data=delete; run; I created this example to demonstrate this problem I am trying to resolve. I need to find out...
  3. L

    Dunn index and Davies-Bouldin index in Clustering

    Does SAS calculate Dunn Index or Davies-Bouldin Index? It relates to validation of different cluster algorithms... Thanks for any suggestions.
  4. L

    decision trees

    Hi there, Is there a better package than RPART for modelling decision trees in R? I can generate a decision tree using rpart, but it is only a binary tree. Is there any package that would make for example 3 or 5 splits from one node? Thanks in advance.
  5. L

    How much of bootstraping is too much?

    Analysts typically mention that the observations should not be correlated. In bootstraping, you are violating this. However, is there any statistical test on autocorrelation of the observed data? Simply, does any statistical test provide an answer on the question in the title? Also, imagine...
  6. L

    How to generate two random vectors correlated to three existing vectors

    Let's have three vectors that are given and cannot change (M, N and O). I have to generate two random vectors X and Y. The correlation that has to be kept is given by the correlation matrix C. The correlation matrix show the correlation between all the vectors (M, N, O , X and Y). Does anyone...