Jump to content
Urch Forums

Is Time Series really important for economists?


Linethan

Recommended Posts

Hi all, I am doing economics phd now, and my interests mainly focus on financial economics. I plan to do theoretic research, maybe corporate finance or asset market. Not very clear what issue I want to do, but now I need to choose my second year courses. Since I prefer to doing theory, I do not plan to take many courses in econometrics. But today the program advisor strongly suggested me to take Time Series. Even though I said I prefer to doing theory, he told me that I still need to learn Time Series for reviewing literature. Since we already have two compulsory courses in econometrics (but not focus on time series), originally I did not plan to take time series. But now I hesitate. Is time series really important?
Link to comment
Share on other sites

I took a Time Series (TS) course during my MA program and though it is was not as rigorous as a PhD course I found it helpful for financial studies. The course was actually pretty fun to take. There are certain aspects of TS that aren't necessarily covered under cross sectional studies. Of course random walks are covered but TS also goes over issues of how to clean up data to remove trends, etc. I think if your focus is financial econ then it would greatly assist you to take it. I was told by professors that TS isn't necessarily helpful to most economists but makes sense for applied econ and financial econ.

 

I can be over generalizing financial econ theory so if there are any others that are well versed in financial econ and/or have taken PhD level TS please correct me.

Link to comment
Share on other sites

OP: cross-sectional and time series regressions are two of the major tools financial economists use, and you'd be hard pressed to find a fin.theorist who doesn't have a solid grasp of them

 

agramon: your avatar piqued my curiosity...what is the caption?

Link to comment
Share on other sites

Hmm...I agree with you. General speaking, time series is useful for financial economics.

However, as I know (maybe I am wrong), for asset pricing, time series is more useful; but for corporate finance, cross-sectional regression is more useful.

Of course, asset pricing and corporate finance are all foundations of financial economics. But since I am inclined to doing corporate finance now, I consider postpone the studies of time series.

And, everyone agrees that, even for just doing theory, time series (or econometrics, general speaking) is still very important? I thought answer is no...but...maybe I am wrong.

 

 

OP: cross-sectional and time series regressions are two of the major tools financial economists use, and you'd be hard pressed to find a fin.theorist who doesn't have a solid grasp of them

 

agramon: your avatar piqued my curiosity...what is the caption?

Link to comment
Share on other sites

You want to do financial economics? Then Time Series is absolutely crucial..

 

Wrong. That statement is too general. If you want to be a pure corporate finance theorist, time series is far from crucial. It's useful to have some knowledge of it for reviewing literature, but not crucial. Even if you want to do empirical corporate finance, taking a pure time series class may be overkill. You'll learn about stuff like spectral analysis, ()ARCH-modeling, etc, which I wouldn't think someone researching, say capital structure and CEO compensation would ever use.

 

If you want to be an asset pricing theorist knowing some time series is important, because you will often want to (1) test your own theories, and (2) be able to scrutinize others' empirical work. For (1) you might get away with just studying the last chapters of Cochrane's book. However, let me give an example of (2). You come up with a good theory and publish it. Someone else tests it and rejects it and calls it a piece of junk. If you have solid training in financial/time series metrics you might be able to detect flaws in their testing and "reject" their rejection of your theory.

 

Now you might think that (1) and (2) apply to corporate finance theory as well, but it doesn't really seem to do so. From what I hear, within asset pricing the empirics are more closely related to the theory than in corporate finance. So if your time is limited and you want to be a corporate finance theorist, something like stochastic calculus would probably be more useful than a time series class.

 

Now unless you are perfectly sure that you want to do corp fin theory, i'd strongly consider taking the time series class, it will make you more versatile.

 

Edit:

 

Again, if you wanna do corp fin theory, go and ask some corp fin theorists what they think you should do. If you're in an econ department, you'll likely want to reach out to some profs at your finance department (possibly at your business school, if you have one). Ask the people who know.

Link to comment
Share on other sites

Corporate finance is definitely a part of financial economics.

MIT Sloan says, there are two informal tracks in financial economics: corporate finance and asset pricing.

 

I wouldn't necessarily call corporate finance, "financial economics".

But heck, what do I know about financial economics (no sarcasm whatsoever).

Although I feel an urge to down vote your post, I'll restrain from doing so.

Link to comment
Share on other sites

Thanks for your advice!! Your opinion is convincing and quite useful. Although I haven't decided to focus on corporate finance or asset pricing in my phd studying, I am a kind of inclined to corporate finance now. I know what I should do now. Many thanks.

 

Wrong. That statement is too general. If you want to be a pure corporate finance theorist, time series is far from crucial. It's useful to have some knowledge of it for reviewing literature, but not crucial. Even if you want to do empirical corporate finance, taking a pure time series class may be overkill. You'll learn about stuff like spectral analysis, ()ARCH-modeling, etc, which I wouldn't think someone researching, say capital structure and CEO compensation would ever use.

 

If you want to be an asset pricing theorist knowing some time series is important, because you will often want to (1) test your own theories, and (2) be able to scrutinize others' empirical work. For (1) you might get away with just studying the last chapters of Cochrane's book. However, let me give an example of (2). You come up with a good theory and publish it. Someone else tests it and rejects it and calls it a piece of junk. If you have solid training in financial/time series metrics you might be able to detect flaws in their testing and "reject" their rejection of your theory.

 

Now you might think that (1) and (2) apply to corporate finance theory as well, but it doesn't really seem to do so. From what I hear, within asset pricing the empirics are more closely related to the theory than in corporate finance. So if your time is limited and you want to be a corporate finance theorist, something like stochastic calculus would probably be more useful than a time series class.

 

Now unless you are perfectly sure that you want to do corp fin theory, i'd strongly consider taking the time series class, it will make you more versatile.

 

Edit:

 

Again, if you wanna do corp fin theory, go and ask some corp fin theorists what they think you should do. If you're in an econ department, you'll likely want to reach out to some profs at your finance department (possibly at your business school, if you have one). Ask the people who know.

Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Restore formatting

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...