<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
	<title type="html"><![CDATA[Forex Software — Difference between Montecarlo analysis and OOS]]></title>
	<link rel="self" href="https://forexsb.com/forum/feed/atom/topic/5617/" />
	<updated>2015-10-24T10:16:14Z</updated>
	<generator>PunBB</generator>
	<id>https://forexsb.com/forum/topic/5617/difference-between-montecarlo-analysis-and-oos/</id>
		<entry>
			<title type="html"><![CDATA[Re: Difference between Montecarlo analysis and OOS]]></title>
			<link rel="alternate" href="https://forexsb.com/forum/post/32030/#p32030" />
			<content type="html"><![CDATA[<p>Ok, so there is no way to establish if exist some advantage to run a montecarlo test on &quot;in sample data&quot; rather than on &quot;out of sample&quot;?</p>]]></content>
			<author>
				<name><![CDATA[coldfire2]]></name>
				<uri>https://forexsb.com/forum/user/6885/</uri>
			</author>
			<updated>2015-10-24T10:16:14Z</updated>
			<id>https://forexsb.com/forum/post/32030/#p32030</id>
		</entry>
		<entry>
			<title type="html"><![CDATA[Re: Difference between Montecarlo analysis and OOS]]></title>
			<link rel="alternate" href="https://forexsb.com/forum/post/32029/#p32029" />
			<content type="html"><![CDATA[<p>There is no connection between Monte Carlo simulations and OOS.<br />OOS works only in the Generator and Optimizer. <br />Monte Carlo tests utilize the full data series available.</p><p>If you want OOS with Monte Carlo, you can use Data Horizon for limiting the data series.</p>]]></content>
			<author>
				<name><![CDATA[Popov]]></name>
				<uri>https://forexsb.com/forum/user/2/</uri>
			</author>
			<updated>2015-10-24T10:02:07Z</updated>
			<id>https://forexsb.com/forum/post/32029/#p32029</id>
		</entry>
		<entry>
			<title type="html"><![CDATA[Difference between Montecarlo analysis and OOS]]></title>
			<link rel="alternate" href="https://forexsb.com/forum/post/32028/#p32028" />
			<content type="html"><![CDATA[<p>As i got it, the Montercarlo test goes to make modifcations about historical data, execution problems and others parameters.<br />Now i&#039;m wondering if this test must be done on the &quot;in sample data&quot; or in &quot;out of the sample data&quot; in order to avoid over-fitting situations.<br />In addition, does the Montecarlo simulation be a substitute of the &quot;out of sample&quot; test?<br />Pratically, i would like to know which kind of connection exist between these two tools.</p><p>Thanks</p>]]></content>
			<author>
				<name><![CDATA[coldfire2]]></name>
				<uri>https://forexsb.com/forum/user/6885/</uri>
			</author>
			<updated>2015-10-24T09:58:25Z</updated>
			<id>https://forexsb.com/forum/post/32028/#p32028</id>
		</entry>
</feed>
