harry I do not intend to formalise the whole thing too much. I would start the thing like that: control group all daily data points of the sp future since 1984 daily Gain ln(Cto/Oto) daily range ln(Hto/Lto) now I do the same thing for each day of the moonphase. I will have about 175 datapoints for each of these days. I want to use the ttest to determine at which degree the amount of the finding is random. readings below 0.05 I would regard highly valid. nevertheless, first I have to get that data. peace
man, Can you parse these results to get your data? http://www.lunaroutreach.org/phases/phases.cgi?2003 --opm8
Ask any ambulance officer or casualty ward worker if their is a correlation between full moons and increases in crazy behaviour and they will always give you a resounding yes. Runningbear
opm8 great. exactly what I needed. here are the results. datastart 04.01.1984 dataend 06.05.2003 asset SP1 Comdty dailyGain t+1 mean 0.02% dailyGain t+1 median 0.04% range t+1 mean 1.39% range t+1 median 1.18% criteria new moon observations 165 dailyGain t+1 mean 0.07% dailyGain t+1 median 0.07% range t+1 mean 1.40% range t+1 median 1.15% ttest on dailyGain 0.64 peace
datastart 04.01.1984 dataend 06.05.2003 asset SP1 Comdty dailyGain t+1 mean 0.02% dailyGain t+1 median 0.04% range t+1 mean 1.39% range t+1 median 1.18% criteria first quarter observations 165 dailyGain t+1 mean 0.03% dailyGain t+1 median 0.10% range t+1 mean 1.40% range t+1 median 1.17% ttest on dailyGain 0.64
datastart 04.01.1984 dataend 06.05.2003 asset SP1 Comdty dailyGain t+1 mean 0.02% dailyGain t+1 median 0.04% range t+1 mean 1.39% range t+1 median 1.18% criteria full moon observations 167 dailyGain t+1 mean -0.10% dailyGain t+1 median -0.07% range t+1 mean 1.41% range t+1 median 1.24% ttest on dailyGain 0.00
datastart 04.01.1984 dataend 06.05.2003 asset SP1 Comdty dailyGain t+1 mean 0.02% dailyGain t+1 median 0.04% range t+1 mean 1.39% range t+1 median 1.18% criteria last quarter observations 171 dailyGain t+1 mean 0.14% dailyGain t+1 median 0.04% range t+1 mean 1.44% range t+1 median 1.23% ttest on dailyGain 0.01
I find the full moon thing rather interesting. Mean and median show same tedency, ttest is quite low. Looks like one should not be too long the day after full moon. harry, can you confirm this? peace opm8, thanks again for the data. wouldn't have known where to find it.