Lagged variables in a time series

[Daniel Hamill]

Hi I am trying to run a time series with several lagged variables to see how effects change over time. When I do this it omits them to to multicolinearity. This of course makes sense but how can it stop it from happening?

[Dimitriy V. Masterov]

Without a description of the structure of your data and the exact commands you typed, no one can possibly answer this.

[William Lisowski]

Expanding on Dimitriy's advice, to increase the likelihood that Statalist readers will be able to assist you, 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. The more you help others understand your problem, the more likely others are to be able to help you solve your problem.

[Daniel Hamill]

Okay guys sorry for the lack of information.

So I am trying to regress a model of y = D_i-mY_t-m. So this is an auto-regressive model with m being the number of time periods. D_i is a dummy term which ranges for i=1 to i=4 (So their is 4 different lagged dummies being multiplied by a lagged y. Currently m=20 for 20 lags.

The data is a panel data set with 7 individuals of a seven day period. The data being recorded is their blood glucose, which is record every 5 minutes. So there is about 2000 observations per person leaving 14000 in total. The dummy variables are recorded in a 5 minute interval when a meal was eaten. So this is close to an event study I think.

I have tsset the data. The regression I ran was:

reg bloodglucose Dyr* Dyh* Dyo* Dyp*

So Dyr, Dyh, Dyo, Dyp all have the * to capture each different lag 1-20 rather than including them in the model individually. They are calculated by:

forvalues j =1/20 {
Dyh`j' = Home[_n-`j'] * bloodglucose[_n-`j']
}

So when I run this model all data is excluded due to multicolinearity.

Any ideas on how to fix this problem?

If you need any more information feel free to ask.

Cheers,
Daniel