Hi, I'm trying to plot the histogram, sd and mean of some range data I have collected and I have several questions. First off, my statistics is ancient at best, so if I get things wrong forgive me. What I'm trying to do is determine the range of the YM for 30 minute periods throughout the day. I've got the code the determining range working, but my standard deviation plots appear to be off. In the graph below the orange dotted line is the mean and the dotted red lines are +/- 1sd. What I want to determine what ranges are within 1 sd of the mean and this graph looks off to me. Can anyone confirm that I have (not) done this correctly? Is there a way I can get a finer scale on the x axis? So far I haven't found a way to set tick marks on the charts... Here's my R code: > hist(range_tmp, breaks=250, xlim=c(0,250)) > abline(v=mean(range_tmp), col='orange', lty=2, lwd=2.5) > abline(v=mean(range_tmp) + sd(range_tmp), col='red', lty=2, lwd=2.5) > abline(v=mean(range_tmp) - sd(range_tmp), col='red', lty=2, lwd=2.5) Thanks! -------------- next part -------------- A non-text attachment was scrubbed... Name: pastedGraphic.png Type: image/png Size: 30726 bytes Desc: not available URL: <https://stat.ethz.ch/pipermail/r-sig-finance/attachments/20091229/f0687b31/attachment.png>
histogram, sd and mean questions
3 messages · Brian G. Peterson, donahchoo at me.com
donahchoo at me.com wrote:
Hi, I'm trying to plot the histogram, sd and mean of some range data I have collected and I have several questions. First off, my statistics is ancient at best, so if I get things wrong forgive me. What I'm trying to do is determine the range of the YM for 30 minute periods throughout the day. I've got the code the determining range working, but my standard deviation plots appear to be off. In the graph below the orange dotted line is the mean and the dotted red lines are +/- 1sd. What I want to determine what ranges are within 1 sd of the mean and this graph looks off to me. Can anyone confirm that I have (not) done this correctly? Is there a way I can get a finer scale on the x axis? So far I haven't found a way to set tick marks on the charts... Here's my R code:
> hist(range_tmp, breaks=250, xlim=c(0,250)) > abline(v=mean(range_tmp), col='orange', lty=2, lwd=2.5) > abline(v=mean(range_tmp) + sd(range_tmp), col='red', lty=2, lwd=2.5) > abline(v=mean(range_tmp) - sd(range_tmp), col='red', lty=2, lwd=2.5)
I know better than to guess at whether a statistical calculation is correct by
looking at the graph, and you didn't include your data.
Your code looks fine, without having access to the data to check it.
In the future, please send Stats 101 and R 101 questions to the general r-help
list, as this has nothing at all to do with finance.
Regards,
- Brian
Brian G. Peterson http://braverock.com/brian/ Ph: 773-459-4973 IM: bgpbraverock
Thanks, Brian. I didn't include the data as I have over 500 data points and didn't think it would be much use. I'll redirect my other questions to r-help.
On Dec 29, 2009, at 8:22 PM, Brian G. Peterson wrote:
donahchoo at me.com wrote:
Hi, I'm trying to plot the histogram, sd and mean of some range data I have collected and I have several questions. First off, my statistics is ancient at best, so if I get things wrong forgive me. What I'm trying to do is determine the range of the YM for 30 minute periods throughout the day. I've got the code the determining range working, but my standard deviation plots appear to be off. In the graph below the orange dotted line is the mean and the dotted red lines are +/- 1sd. What I want to determine what ranges are within 1 sd of the mean and this graph looks off to me. Can anyone confirm that I have (not) done this correctly? Is there a way I can get a finer scale on the x axis? So far I haven't found a way to set tick marks on the charts... Here's my R code:
hist(range_tmp, breaks=250, xlim=c(0,250)) abline(v=mean(range_tmp), col='orange', lty=2, lwd=2.5) abline(v=mean(range_tmp) + sd(range_tmp), col='red', lty=2,
lwd=2.5)
abline(v=mean(range_tmp) - sd(range_tmp), col='red', lty=2,
lwd=2.5)
I know better than to guess at whether a statistical calculation is correct by looking at the graph, and you didn't include your data. Your code looks fine, without having access to the data to check it. In the future, please send Stats 101 and R 101 questions to the general r-help list, as this has nothing at all to do with finance. Regards, - Brian -- Brian G. Peterson http://braverock.com/brian/ Ph: 773-459-4973 IM: bgpbraverock