Comments - Multicollinearity in Time Series Data - AnalyticBridge2021-04-12T15:10:01Zhttps://www.analyticbridge.datasciencecentral.com/profiles/comment/feed?attachedTo=2004291%3ABlogPost%3A65786&xn_auth=noNidhi, I see that I've got a…tag:www.analyticbridge.datasciencecentral.com,2010-04-13:2004291:Comment:660952010-04-13T17:54:22.879ZArunhttps://www.analyticbridge.datasciencecentral.com/profile/Arun
Nidhi, I see that I've got a problem with the basics here. Let me restate what you've just said.<br />
<br />
PCA is used for multicollinearity?! I think not! PCA is used to identify variables that seem to have similar information that can be loaded onto a factor!<br />
Where's multicollinearity here?<br />
<br />
Why would you use MLR for TimeSeries? MLR cannot handle Autocorrelation! You need to take care of autocorrelation before running a regression on it, and that an ARIMA can help with. Other wise, you need to…
Nidhi, I see that I've got a problem with the basics here. Let me restate what you've just said.<br />
<br />
PCA is used for multicollinearity?! I think not! PCA is used to identify variables that seem to have similar information that can be loaded onto a factor!<br />
Where's multicollinearity here?<br />
<br />
Why would you use MLR for TimeSeries? MLR cannot handle Autocorrelation! You need to take care of autocorrelation before running a regression on it, and that an ARIMA can help with. Other wise, you need to pre-whiten the series and then feed it into the MLR. When I say pre-whiten, you may need to use differencing based on which time lag has effect on the x(t). This can be obtained from ACF, IACF & PACF plots from ARIMA.<br />
<br />
Your forecasted model would look like<br />
Y = a + b1X1+ b11X1(t-1)+...+b2X2+b21X2(t-1)+...+e<br />
if Y is not autocorrelated.<br />
If Y is also autocorrelated, then<br />
add another set of variables a1Y(t-1)+a2Y(t-2) etc..