XTLSDVC interpretation of the coefficients

[Robert Jansen]

Dear fellow STATA users,

For my MSc thesis I performed a XTLSDVC regression. I have some trouble with the interpretation of its coefficients. Could anyone help me with this?

For instance what is the meaning of a strongly significant outcome of the variable log-longtermbonds 1.18? According to the literature there should be a positive influence of longtermbondrates on yields of approxiamately 0.34 meaning that 1% increase in longtermbondrates would increase yields with 0.34 %. With standard OLS i got a simular outcome, however the outcome of the LSDVC dynamic regression of 1.18 doesn't seem to be abke to get interpreted in de same direct manner.

Please find enclosed the output of the LSDCV dynamic regression.

Help is very much appreciated. Looking forward to your respons.

Kind regards,

R. Jansen

[Carlo Lazzaro]

Robert:
welcome to the list.
Please provide attachments in Stata formats only (as per FAQ);
Please provide what you typed and what Stata gave you back via code delimiters (as per FAQ again). Thanks.

[Carlo Lazzaro]

Robert:
Q1: I meant .dta format, so that other listers have all they need to repeat your analysis (if they want);
Q2 (code delimiters): please take a look at FAQ #12. Be informative about commands and data and give examples. Thanks.

[Marcos Almeida]

Hello, Robert,

Taken from the FAQ, below you have the excepts Carlo mentioned when giving your a reply.

Stata code (i.e. the exact commands issued) is very much easier to read if presented as such. Click on the “Toggle Advanced Editor” button (an underlined A) in the area above where you enter text for posts and, in the menu that appears, click on the # button to insert [...]. Write your code between, paying particular attention to linebreaks and indentation. Or just insert those mark-ups manually before, or indeed after, you insert your code.

You can attach datasets or other documents, but that is usually much less convenient than the methods above. Note, in particular, that MS Word and MS Excel file formats are not universally readable by forum members.

Best,

Marcos

[Marcos Almeida]

Hello, Robert,

Unfortunately, I cannot see your output, neither a comparison between models. Besides, bias-corrected least-square dummy variable estimators are far from my field. That said, I gather you may find what you want here (http://www.stata-journal.com/sjpdf.h...iclenum=st0091) and here(http://gatton.uky.edu/faculty/hankin...s/JCF_2013.pdf). In page 17 from the second source you may find interesting discussion on this, plus a nice display of the coefficients from differents models.

Best,

Marcos