d*******1
发帖数: 293 | 1 I use multiple linear regression model to analyze 40 years historical market
data. However, when I divided 40 years data into 10 years periods, I found
I got four different best fit model.
So is there any better way to analyze data, like time series regression
model?
Hope to get some suggestion. | s********t
发帖数: 247 | 2 over this long time period, it's highly possible to have structural breaks,
try to test for that and fit the model with structural break(s)
market
found
【在 d*******1 的大作中提到】
: I use multiple linear regression model to analyze 40 years historical market
: data. However, when I divided 40 years data into 10 years periods, I found
: I got four different best fit model.
: So is there any better way to analyze data, like time series regression
: model?
: Hope to get some suggestion.
| f***a
发帖数: 329 | 3 there are "changing point" models. im not falimilar. maybe it can help if
your data have such structure. hehe~ | s********t
发帖数: 247 | 4 靠，在这看到你了
现在还打山口山么？
【在 f***a 的大作中提到】
: there are "changing point" models. im not falimilar. maybe it can help if
: your data have such structure. hehe~
| x**g
发帖数: 807 | 5 try spline models.
market
found
【在 d*******1 的大作中提到】
: I use multiple linear regression model to analyze 40 years historical market
: data. However, when I divided 40 years data into 10 years periods, I found
: I got four different best fit model.
: So is there any better way to analyze data, like time series regression
: model?
: Hope to get some suggestion.
| s**********e
发帖数: 63 | 6 Used pooled time series data, Split the 40 years by 10 for each period,
create an period var called "period' with value 1- 4, then use panel
regression by period in STATA, e.g.
tsset period
xtreg y x1 x2, reg
|
|
