Statistics Help @ Talk Stats Forum - Regression Analysis
http://www.talkstats.com/
Linear regression, linear models, nonlinear regressionenFri, 22 Sep 2017 05:59:34 GMTvBulletin60http://www.talkstats.com/images/misc/rss.pngStatistics Help @ Talk Stats Forum - Regression Analysis
http://www.talkstats.com/
combining error terms for two dissimilar regressions
http://www.talkstats.com/showthread.php/70181-combining-error-terms-for-two-dissimilar-regressions?goto=newpost
Thu, 21 Sep 2017 16:32:55 GMTI have a linear regression for Y on X, and a power regression for Z on Y, each having associated error. (the Y values are different (independent) in...I have a linear regression for Y on X, and a power regression for Z on Y, each having associated error. (the Y values are different (independent) in each case). I have combined the equations to model Z as a function of X.

What I want is a confidence envelope around the model estimates of Z.

Thanks,
]]>Regression AnalysisGeorge Kraemerhttp://www.talkstats.com/showthread.php/70181-combining-error-terms-for-two-dissimilar-regressionsSpend against views/day. Include days of no spend?
http://www.talkstats.com/showthread.php/70177-Spend-against-views-day.-Include-days-of-no-spend?goto=newpost
Thu, 21 Sep 2017 04:41:28 GMTHi everyone,

just looking at doing some simple linear regression and I've got views on an article. Occasionally we choose to spend a bit of money to promote the article and boost views. I want to see how spending affects our views.

It's pretty simple, but since spending is so on and off i'm not sure. I get a good R-squared value when I include those days but a terrible one when I don't. How I see it is including days of no spend gives a good R-squared because spending definitely boosts our views. Not including those days has a terrible R-squared because the amount we're spending isn't hugely affecting the views we're getting.

If I'm looking to do simple linear regression, should I include those days where we haven't spend any money? If I do include those days, how do I choose which days to include? Do I pick days in between spending? Would I pick days before/after spending has started/ended?

Cheers guys!
]]>Regression AnalysisEdorianhttp://www.talkstats.com/showthread.php/70177-Spend-against-views-day.-Include-days-of-no-spendResidual Modelling and Generating Scenarios for variables
http://www.talkstats.com/showthread.php/70176-Residual-Modelling-and-Generating-Scenarios-for-variables?goto=newpost
Thu, 21 Sep 2017 02:33:12 GMTnewbie here with a trivial question. i am trying to create scenarios on a set of macro variables. i started with creating a bayesian VAR model on...newbie here with a trivial question. i am trying to create scenarios on a set of macro variables. i started with creating a bayesian VAR model on insample data and created some forecasts. then took the residuals from the model and used copula to find the joint distribution from the marginal distribution of the residuals of the variables. I found out the ranks of error of variables and Fit a t copula. Then I simulated the errors from the built copula.

now that i have simulated errors, if i wanted to create scenarios based on these simulation, how should I go about it? Should I just add the simulated errors to the mean of the forecasts? How do I get simulated paths for each variable?
]]>Regression Analysiseemrunhttp://www.talkstats.com/showthread.php/70176-Residual-Modelling-and-Generating-Scenarios-for-variables