regression analysis of lagged days

12 次查看（过去 30 天）
Keran
Keran 2020-7-26
评论： Keran 2020-7-26
Hi,
I'm quite new with matlab and I need help with one thing. I want to make regression analysis where dependent variable is premium of day and independent is premium at day t-1 and so on. I can only regress one day lag but not further. I couldn'tdo this with fitlm. Below is my regression but when running there's an error: Error in LinearModel.fit (line 1224)
model.Formula =
LinearModel.createFormula(supplied,modelDef,X, ...
Error in fitlm (line 121)
model = LinearModel.fit(X,varargin{:});
pdpersistency1=fitlm(pd(1:1268,1), pd(2:1269,1), pd(3:1270,1))

请先登录，再回答此问题。

采纳的回答

Thiago Henrique Gomes Lobato
Your first argument should be a matrix with all the variables you need for prediction. So, in your case, you need to form a matrix with both time lags. Ex:
pd = randn(100,1); % Your data
pdpersistency1=fitlm([pd(1:end-2),pd(2:end-1)],pd(3:end))

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Regression 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by