--- In [email protected], akasha_108 <[EMAIL PROTECTED]> wrote: > > Contrary to points of various commmentators, the summary of the study, > at end, indicates that a number of models were tested and contributed > to the overall results in the National Demonstration Project findings, > JuneJuly 1993. > > First, there was a short term, 1993, frame model, that appears to > have only looked at a slice of crime, HRA (homocides, rapes, > assaults) ignoring other types
The study was always to be about *violent* crime: homicides, rapes, assaults, and robbery. That was announced in advance. (Hint: Look at the title of the study and the title of the project.) , with temperature apparently as the only control > variable. While other discussions referred to a mutiple homocide in or > near the complex at the beginning of the study, the summary focusses > on the maximum decrease was 23.3% when the size of the group was > largest during the final week of the project." > > Other discussions have mentioned the construction of a weather or heat > index -- if this was used, instead of temperature as a direct > independent variable in the model, then this would have involved the > construction of a second model -- a temperature index model. > > There was a second (or third) model, a longer term model looking > 19881993 data. Several variations or sub models were analyzed with > robberies and joint variable both HRA crimes and robberies tested as > dependent variables. Again, emphasis is on the final week of the 2 > month period, a potential sign of favorably positioning positive > results (cherry picking) or simply random or unexplained variations > on the dependent variable in that short 1/8 of the study period. The idea of the Maharishi Effect is that the more people who are practicing the TM-Sidhis together, and the longer they practice, the greater will be the effect. So of course they would focus on the end of the demonstration period, when the largest number was there, and when the practice had been going on the longest. > Robberies by themselves did not decrease. And non HRA, non robbery > crime was not reported in results (though it would have been an > obvious thing to test for -- its possible that no decrease was > found, and was not reported.) No, it wasn't studied, was never intended to be studied. Again, the study *always* was to be only of violent crime, not any other kind. I wonder how many more times it will have to be pointed out that the study protocols were *announced in advance*. > Another set of model specifications were developed and tested using > various control variables. Why these were not included in the primary > model is a mystery and raises serious methodological questions. Only > police staffing and seasonality were reported as showing no > significant effect during the ME intervnetion period. Its quite odd, > that a number of other control variables were collected, and trumpeted > at the beginning of the summary: weather variables precipitation, > humidity, daylight hours, changes in police and community anti-crime > activities, prior crime trends in the District of Columbia, and > concurrent crime trends in neighboring cities. However the > significance of these control variables, and the effects of their > inclusion in the model are ignored. They analyzed all these factors (as the summary says) and found that temperature was the only one where a significant correlation existed. Why all the control variables were > not tested in the primary shrot term and longer term models is a > mystery, and why their results in subordiante analysis was not > reported is a double mystery. You appear to be mystified as to why a one-page summary of the study doesn't include all the analysis contained in the full 48-page study. You may be knowledgeable about statistics, but you don't seem to have a whole lot of common sense. It is possible there is only citing of > TM positive results and not neutral and any negative results. As might > be the case for for non HRA.robbery crimes. As might be the case for > results prior to week 8. No, there were positive results starting from shortly after the project began. That's shown even in the summary, in the little chart. > > Aparently a fourth (set of) model(s) were specified and analysed a > "steady state gain (long-term effect)" model to estimate the gain from > a permanent group of 4,000 participants. Without discussion of > methodology, this long-term effect was calculated as a 48% reduction > in HRA crimes in the District of Columbia, about twice the figure of > the peak end week of the 8-week study. The extrapolation of these > "permanent effects" are interesting conjecture, but don't appear to > have much methodological basis. See above about the more people, the longer they practice together, etc. ------------------------ 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/
