--- In FairfieldLife@yahoogroups.com, "authfriend" <[EMAIL PROTECTED]> wrote: > > --- In FairfieldLife@yahoogroups.com, akasha_108 <[EMAIL PROTECTED]> > wrote: > > > > --- In FairfieldLife@yahoogroups.com, "authfriend" <[EMAIL PROTECTED]> > wrote: > > > > > > --- In FairfieldLife@yahoogroups.com, akasha_108 <[EMAIL PROTECTED]> > > > wrote: > > > <snip> > > > > So when separate models are used to predict crime, distinct > from the > > > > intervention model, its unconventional. Its not needed, unless > there > > > > were severe data problems. Doing so weakens the predictive > power of > > > > the model(s). > > > > > > > > There is nothing in the data issues, at first glance, that > suggest > > > > why multiple, models were used. > > > > > > I have no idea what you're talking about when you > > > refer to "multiple models." I never said anything > > > about multiple models. > > > > see adjacent post in my response to LBS. > > Doesn't help.
So you still hold ony one model was used? You said it was an ARIMA model, so it was a multivariate AR IMA model that controlled for weather and croime factor variables? > > > > You seem to say the prediction based on past trends > > > was unnecessary; but then to what do you compare the > > > actual crime rate during the period to determine > > > whether and how much it's been affected? > > > > If it was a short term model, then crime rates would be compared to the pre course "one month"* and the post course "one month". These would be control periods (not necessarily good ones, but thats another story.) > > They didn't do that because they wanted to control > for seasonal variations. So why did they have a pre and post period? > > If they had the pre and post periods, why did they need the "5 year" > > (or what ever longer term model) to estimate the crime rate without > > intervention? They had the "control" periods, pre and post. They > > didn't need to estimate a non-intervention period. > > Pre and post aren't "control" periods because they > take place at *different times of the year*. So they did not use pre and post periods? > > See my adjacent post. I think the longer term model was a second > > stage of analysis used to control for weather. > No. For at least the fifth time now, the weather > protocol was decided on and announced before the > intervention even began. And again, it is important to you that this was announced at the beginning of the study, why? > > See my adjacent post. Its the only explanation that makes sense to > > me at this point. Actually reading the study would be halpful > > though, instead of specualation. > Well, yes. Your speculation is pretty much useless, > I'm afraid. OK, if my speculation is so off base, once and for all, please explain analytical method of the study. Thats all I want. A single, coherent explanation. Was it a single multivariate ARIMA model that controlled for weather,sesonal factors and crime factor variables, along with the ME impact over a 3-5 year period? What was added in the 25% second round of analysis, relative to the first round, the 17% results? ------------------------ Yahoo! Groups Sponsor --------------------~--> Get fast access to your favorite Yahoo! Groups. Make Yahoo! your home page http://us.click.yahoo.com/dpRU5A/wUILAA/yQLSAA/JjtolB/TM --------------------------------------------------------------------~-> To subscribe, send a message to: [EMAIL PROTECTED] Or go to: http://groups.yahoo.com/group/FairfieldLife/ and click 'Join This Group!' Yahoo! Groups Links <*> To visit your group on the web, go to: http://groups.yahoo.com/group/FairfieldLife/ <*> To unsubscribe from this group, send an email to: [EMAIL PROTECTED] <*> Your use of Yahoo! Groups is subject to: http://docs.yahoo.com/info/terms/
