Timeline for What can I do with these two time series?
Current License: CC BY-SA 3.0
26 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 30, 2013 at 6:20 | history | edited | Siddharth Gopi | CC BY-SA 3.0 |
deleted 55 characters in body
|
| Nov 30, 2013 at 5:50 | vote | accept | Siddharth Gopi | ||
| Nov 29, 2013 at 14:31 | history | edited | Siddharth Gopi | CC BY-SA 3.0 |
edited title
|
| S Nov 29, 2013 at 14:30 | history | bounty ended | Siddharth Gopi | ||
| S Nov 29, 2013 at 14:30 | history | notice removed | Siddharth Gopi | ||
| Nov 28, 2013 at 8:06 | history | edited | Siddharth Gopi | CC BY-SA 3.0 |
added 310 characters in body
|
| Nov 27, 2013 at 17:35 | history | edited | Siddharth Gopi | CC BY-SA 3.0 |
added 16 characters in body; edited title
|
| Nov 27, 2013 at 9:58 | comment | added | mpiktas | Yes, this a natural start. You might also want to use rolling forecasts and the forecasting model $Y_{t+h}=\sum_{j=0}^kX_{tm-h}+\varepsilon_{t+h}$, i.e. forecast the t+h observation using the data until $t$, this is how usually MIDAS regression is used. For example you can forecast the current monthly value using half-month data of high frequency regressor. | |
| Nov 27, 2013 at 9:58 | history | tweeted | twitter.com/#!/StackStats/status/405636683263385600 | ||
| Nov 27, 2013 at 9:52 | answer | added | mpiktas | timeline score: 4 | |
| Nov 27, 2013 at 9:40 | comment | added | Siddharth Gopi | @mpiktas hey, i've updated the question. thanks for the r package link, it looks excellent for this question and im going to start studying it. I was thinking of seperating my data into 70% training and 30% cv, and testing to see how accurate the predictive nature of the red line is. do you think thats a good idea? | |
| Nov 27, 2013 at 9:25 | history | edited | Siddharth Gopi | CC BY-SA 3.0 |
deleted 40 characters in body
|
| Nov 27, 2013 at 9:08 | comment | added | mpiktas | Also please update the question with the info that you want show that blue line can be predicted by red line. This will make question more answerable in my opinion. | |
| Nov 27, 2013 at 9:06 | comment | added | mpiktas | Then use MIDAS regression, which is specifically designed to regress low frequency time series on high frequency time series. There is an R package for doing that, cran.r-project.org/web/packages/midasr. That package will enable to quickly test out whether it is possible to predict blue line with red line. The package comes with the user guide, with the examples, try following them. Note, I am the developer of this package, so I am a little biased in giving suggestions. | |
| Nov 27, 2013 at 8:46 | comment | added | Siddharth Gopi | @mpiktas I was thinking about showing that it is possible to use the red line as a predictor for the blue line. This is important because a lot of policy decisions depend on the blue line and if I can show that the red line forecasts the blue line, then there would be some real world relevance to this analysis. I also have a feeling that it would be overkill to do tests or analysis to show that the red line is a predictor, its already really obvious from the plot. What are your thoughts? Im struggling to find a decent project idea for my course. | |
| Nov 27, 2013 at 8:21 | comment | added | mpiktas | Running tests without some goal is usually meaningless. What are you trying to achieve? To what end will you use this data? | |
| Nov 27, 2013 at 8:19 | answer | added | power | timeline score: 0 | |
| Nov 27, 2013 at 8:02 | history | edited | Siddharth Gopi | CC BY-SA 3.0 |
edited title
|
| Nov 27, 2013 at 5:45 | history | edited | Siddharth Gopi | CC BY-SA 3.0 |
added 134 characters in body
|
| Nov 26, 2013 at 4:42 | answer | added | RegressForward | timeline score: 0 | |
| S Nov 26, 2013 at 3:42 | history | bounty started | Siddharth Gopi | ||
| S Nov 26, 2013 at 3:42 | history | notice added | Siddharth Gopi | Draw attention | |
| Nov 26, 2013 at 3:39 | history | edited | Siddharth Gopi | CC BY-SA 3.0 |
deleted 44 characters in body
|
| Nov 24, 2013 at 4:00 | comment | added | Alecos Papadopoulos | Before asking the data anything, make sure that you study and fully understand what does it mean, and what does it take, to try to compare/examine/contrast data of different frequency. | |
| Nov 24, 2013 at 3:58 | comment | added | John | Economists have traditionally used low frequency data (like monthly or quarterly). There has been a lot of work on developing higher frequency data to improve forecasts. So you might look into mixed frequency techniques (Midas or Kalman Filters might be a start). | |
| Nov 24, 2013 at 3:37 | history | asked | Siddharth Gopi | CC BY-SA 3.0 |