User talk:Asaduzaman

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Welcome[edit]

Hello, Asaduzaman, and welcome to Wikipedia. Thank you for your contributions. I hope you like the place and decide to stay. If you are stuck, and looking for help, please come to the New contributors' help page, where experienced Wikipedians can answer any queries you have! Or, you can just type {{helpme}} and your question on your user talk page, and someone will show up shortly to answer. Here are a few good links for newcomers:

We hope you enjoy editing here and being a Wikipedian! By the way, you can sign your name on talk and vote pages using four tildes, like this: ~~~~. If you have any questions, see the help pages, add a question to the village pump or ask me on my talk page. Again, welcome! DickClarkMises 13:11, 26 March 2007 (UTC)

Cointegration[edit]

Saying "there is no relationship between the two series" seems a bit strong. One would expect at least a weak relationship between one country's GNP and another's consumption metric, no? Brycehughes (talk) 07:41, 13 September 2014 (UTC)

What do you think about GNP of Afghanistan having high correlation with consumption in El Salvador? Or GNP in Fiji Islands and consumption in Guatemala?(Asaduzaman (talk) 16:20, 13 September 2014 (UTC))
You have removed the WHOLE explanation of co-integration, just because of a minor (& invalid) objection to one sentence which is merely an illustration of the concept by a specific example? Using correct measure of relationship between trendy series, one can compute that their is no significant relationship between GNP of Afghanistan and consumption in El Salvador, Or GNP in Fiji Islands and consumption in Guatemala? I refrained from undoing your change, so that you can respond. Alternatively, if you agree, you can undo it yourself. Asaduzaman (talk) 12:30, 14 September 2014 (UTC) (Asaduzaman (talk) 16:20, 13 September 2014 (UTC))
What? I did not remove anything. I just moved it to a section. It doesn't belong in the article lead. Brycehughes (talk) 15:35, 14 September 2014 (UTC)
Re the actual question, ok, then perhaps we should edit "pick any consumption series for any country and regress it against GNP for any other country", because as it stands this would allow for the United States and Canada, for example. What do you think? Brycehughes (talk) 15:40, 14 September 2014 (UTC)
Oh, I did not realize that you had moved the section. Now, somebody wants references for the material. Actually, this material is by now so well known that it is available all over the place, and no specific references come to mind except a few which have already been covered in the article.
Another way to fix the (potential) problem would be to say no (or a weak) relationship -- but it seems pedantic and un-necessary. The theoretical point is that given any two Statistically Independent series with nearly zero correlation, if we add trends to both them they will appear correlated.
Using the expample of consumption and GNP is just a colorful way to make the dry theoretical point.Asaduzaman (talk) 16:39, 14 September 2014 (UTC)
AFTER REFLECTION, I think the section DOES BELONG in the opening paragraph or at least in the introduction. It is not a technical addition, but a conceptual explanation of the importance of the concept. Current section title is misleading -- BTW stochastic drift and stochastic trend are the same things. Your typical Wikepedia reader is UNINFORMED about the concept so those who have studied it in a course would not need to refer to this entry. Actually the material overlaps with what it written in the INTRODUCTION -- the introduction does make the same point, but in an indirect and implicit way -- that is someone who knows the subject would understand that what I have written is implied in it, but a newbie to the field would not understand. Also, why the blank entry for Phillips-OUlaris? there are also MANY other tests for cointegration. I can ask one of my students to prepare a more complete list and descriptions of these testsAsaduzaman (talk) 23:52, 14 September 2014 (UTC)
It does not belong in the article lead. A one or two sentence summary could go in the lead. Overlap is entirely the point. Please see WP:LEAD.
I don't know about Phillips-Oularis. You may have better luck asking that on the article's talk page.
Re the question, what if we said: "To verify this, pick any consumption series for any country and regress it against GNP for some other, dissimilar country (for example, Fiji and Afghanistan)." Brycehughes (talk) 15:24, 15 September 2014 (UTC)
I went ahead and did this. Ping me and/or revert me if you object. Hope you keep editing here. Your contributions and expertise are much appreciated. Brycehughes (talk) 09:33, 19 September 2014 (UTC)
No objections to the change. However, I think the section title is misleading, and I am amending it. Asaduzaman (talk) 17:05, 19 September 2014 (UTC)