Invalid Numlist - r(125)

[tinfah chung]

Hi

I ran a ardl regression as follows:
. ardl grw_id grwlro LG LRER LI LNX, ec lags (1,1)

invalid numlist has elements outside of allowed range
r(125);

What is the problem that I have in the above variables?

TQ

grwlro LG LI LNX LRER grw_id
10.197 4.63448 3.96386 9.15588
.1219547 10.2686 4.62359 4.04217 9.18605 .0220451
.1315193 10.4528 4.62278 4.14789 9.23893 .0282059
-.0149975 10.6998 4.70362 4.18449 9.19421 -.020525
.0945489 10.3059 4.62671 4.09284 9.1146 .0202742
.0842154 10.5214 4.61168 4.14425 9.13378 .0202007
.0128791 10.4699 4.61737 4.22156 9.12967 .037035
-.2483866 10.7214 4.62368 4.25504 9.10426 -.0187092
-.0455747 10.3424 4.62964 4.19404 9.11877 .0202627
.1953452 10.559 4.6065 4.26662 9.10886 .0265131
.1138146 10.5331 4.61499 4.32599 9.12096 .0372009
.1421068 10.7413 4.62258 4.38639 9.14767 -.0271978
.0227504 10.378 4.63358 4.47152 9.1275 .0238104
.1770306 10.6102 4.63218 4.55713 9.12913 .0273066
.0752704 10.6647 4.64536 4.57523 9.15165 .0367517
-.6890855 10.8928 4.61853 4.52721 9.29652 -.0363913
-.3048935 10.5504 4.60668 4.35401 9.35487 .0165453
.1235712 10.7614 4.60482 4.40158 9.23088 .0236197
.3234839 10.7581 4.61776 4.45771 9.17627 .0380325
.0724761 11.0583 4.61681 4.56664 9.14793 -.0237064
-.0495844 10.4733 4.61713 4.51798 9.11597 .0202217
.184207 10.687 4.61188 4.54913 9.11218 .0264988
-.1127017 10.8057 4.63469 4.57636 9.09661 .0334311
.0581203 11.1277 4.61828 4.75909 9.10609 -.0143023
.1580932 10.4995 4.62189 4.71492 9.07194 .0167751
.2431316 10.7312 4.60296 4.82799 9.05666 .0277758
-.0769634 10.8342 4.623 4.8507 9.08137 .0326424
-.0491056 11.1564 4.61309 4.86206 9.11245 -.0148115
-.0202682 10.5627 4.6176 4.82012 9.12085 .0157213
.0719044 10.8142 4.60972 4.84095 9.14767 .0279093
-.1112013 10.8058 4.61998 4.82222 9.16639 .0314093
.0160687 11.1227 4.61111 4.8663 9.17342 -.0150089
.0468781 10.5671 4.62375 4.84198 9.18168 .013835
-.1257441 10.8357 4.6152 4.86097 9.20281 .0253077
.0537808 10.8912 4.64771 4.89343 9.35703 .0302601
.0136147 11.1855 4.61122 5.04401 9.40673 -.014411
-.0115688 10.6028 4.62131 4.9694 9.33785 .009119
-.0173726 10.8281 4.60894 4.98114 9.3805 .024456
-.0204418 10.9352 4.62187 4.97873 9.40796 .0296087
-.2091253 11.1995 4.63134 5.03246 9.42424 -.0141468

[Clyde Schechter]

I don't use -ardl- and know nothing about it. But, if the option -lags()- is supposed to take a Stata numlist, your problem is the comma. Stata numlists do not have commas: the numbers are just separated by spaces. Try -lags(1 1)- instead of what you have.

[William Lisowski]

I'm embarrassed to contradict Clyde, but help numlist tells us that in this case commas are allowed, although discouraged.

Advice: Do not use commas to separate the entries -- use spaces instead -- because commas are not always allowed. You may use commas when a numlist appears inside the parentheses of an option, but you may not use commas in other cases.

The sample data does not seem to include the time variable required by the tsset which in turn is required before running ardl. So it's difficult to know whether ardl is complaining because of problems with the time variable.

Please review the Statalist FAQ linked to from the top of the page, as well as from the Advice on Posting link on the page you used to create your post. Note especially sections 9-12 on how to best pose your question. This advice should sound familiar because I gave it in my initial response to your previous topic in early December.

In particular, the sample of your data is peculiar, in that not only is the time variable missing, but the first observation posted does not contain all of the variables. Please post a better sample of your data, and in doing so, follow the advice to use dataex and code delimiters to present data and results in your post. It would also be useful to present the tsset command and its output.

The more you help others understand your problem, the more likely others are to be able to help you solve your problem.

[Clyde Schechter]

I'm embarrassed to contradict Clyde, but help numlist tells us that in this case commas are allowed, although discouraged.

Heavens! Don't shrink from contradicting me. I make mistakes, and I learn by having them pointed out. I happily stand corrected.

[tinfah chung]

Thanks for the suggestions.
I still have the problem after typing
tsset
ardl grw_id grwlro LG LRER LI LNX, ec lags (1,1)
On the data, I have 2 missing values for the first row.. under grw_id and grwlro. Is that the problem?

[tinfah chung]

I have uploaded an image file

[Monir Ahmed]

Many articles like Pata and Isik (2021) “Determinants of the load capacity factor in China: A novel dynamic ARDL approach for ecological footprint accounting” reports the bound-test results like the following:

F-stats (overall)	9.731*
t-test (for dependent)	-6.858*
F-stats (independent)	5.048**

F and t stats are readily available at ARDL package after ectest. I know that the additional F-stats for independent test are proposed by Sam et al and McNown et al. I want to know that are the ARDL STATA’s F and t tests sufficient to conclude our result? Or, we need to do additional F-Stats for independent variables after regress option?

[Nick Cox]

Please repost #7 as the start of a new thread. It doesn't bear any relation to the title of this thread.

[Bahar Stone]

Hi Tinfah Chung, your error is in "lags(1 1)". You must use as many numbers as your variables. Please try this option "lags(1 1 1 0 0 )". Please let me know if it works.

[Tatenda Zibizapanzi]

In this case, the lag length for your dependent variable must not be zero try 1 as your lag for the dependent variable it works out

[Tatenda Zibizapanzi]

In this case, the lag length for your dependent variable must not be zero try 1 as your lag for the dependent variable it works out.