Economics Job Market Rumors Topic: stats question
https://www.econjobrumors.com/topic/stats-question
Economics Job Market Rumors Topic: stats questionen-USTue, 04 Aug 2020 00:33:05 +0000http://bbpress.org/?v=1.0.2<![CDATA[Search]]>q
https://www.econjobrumors.com/search.php
Economist on "stats question"
https://www.econjobrumors.com/topic/stats-question#post-199655
Thu, 29 Sep 2011 11:39:27 +0000Economist199655@https://www.econjobrumors.com/<p>OK, so you have a Skorohod embedding of a diffusion. I think the results should still hold (maybe with some adjustment). But you can just do the ML with order stats and the mean. That should be fairly straightforward. - Q36spacemodulator
</p>Economist on "stats question"
https://www.econjobrumors.com/topic/stats-question#post-199629
Thu, 29 Sep 2011 09:37:46 +0000Economist199629@https://www.econjobrumors.com/<p>Q36spacemodulator and other EJMR friends,</p>
<p>I read Parkinson's paper carefully and it does not apply to my case. Parkinson assumes that the diffusion process is monitored continuously over time so that the sample max and the sample min are actually the max and the min along the realized path.</p>
<p>This is not my case. In my case the process is discretely observed (say, at full hours like 9:00, 10:00, 11:00 etc), someone recorded the max, min, and mean of those say N=24 hours, and then lost the individual hourly observations and just kept the max, min, and mean. </p>
<p>How do I estimate the standard deviation in this case?</p>
<p>Domo arigato
</p>Economist on "stats question"
https://www.econjobrumors.com/topic/stats-question#post-199528
Thu, 29 Sep 2011 04:17:01 +0000Economist199528@https://www.econjobrumors.com/<p>Go jack off a few times and come back to the problem. It will come to you eventually.
</p>Economist on "stats question"
https://www.econjobrumors.com/topic/stats-question#post-199518
Thu, 29 Sep 2011 04:07:06 +0000Economist199518@https://www.econjobrumors.com/<p>Use order statistics and assume a parametric family. Go figure
</p>Economist on "stats question"
https://www.econjobrumors.com/topic/stats-question#post-199475
Thu, 29 Sep 2011 03:13:19 +0000Economist199475@https://www.econjobrumors.com/<p>Found Parkinson, Parkinson will be<br />
Domo arigato Q36spacemodulator!
</p>Economist on "stats question"
https://www.econjobrumors.com/topic/stats-question#post-199464
Thu, 29 Sep 2011 03:02:53 +0000Economist199464@https://www.econjobrumors.com/<p>Forgot to mention: if you have some notion of the distribution (other than normal), you could do some maximum likelihood using the mean and order statistics to estimate the standard deviation. But, if you are OK with a normality assumption, Parkinson is a nice, simple estimator.</p>
<p>Also forgot to note that I remain the - Q36spacemodulator
</p>Economist on "stats question"
https://www.econjobrumors.com/topic/stats-question#post-199452
Thu, 29 Sep 2011 02:36:43 +0000Economist199452@https://www.econjobrumors.com/<p>You could use a Parkinson estimator with the high and low
</p>Economist on "stats question"
https://www.econjobrumors.com/topic/stats-question#post-199440
Thu, 29 Sep 2011 02:21:35 +0000Economist199440@https://www.econjobrumors.com/<p>make it up
</p>Economist on "stats question"
https://www.econjobrumors.com/topic/stats-question#post-199436
Thu, 29 Sep 2011 02:13:25 +0000Economist199436@https://www.econjobrumors.com/<p>Dear EJMR friends<br />
How do I get a point estimate for standard deviation when I know sample size, sample mean, sample max, and sample min?<br />
Arigato
</p>