Path: csiph.com!feeder.erje.net!2.eu.feeder.erje.net!eternal-september.org!feeder.eternal-september.org!reader02.eternal-september.org!.POSTED!not-for-mail From: Daniele Futtorovic Newsgroups: comp.lang.java.programmer Subject: Re: How to identify outliers Date: Tue, 28 Nov 2017 17:35:06 +0100 Organization: A noiseless patient Spider Lines: 24 Message-ID: References: Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Injection-Date: Tue, 28 Nov 2017 16:35:11 -0000 (UTC) Injection-Info: reader02.eternal-september.org; posting-host="db9879cdf7deb0203cd054848c3f1d8a"; logging-data="28427"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX1+WU53liGI728onXhUf/3KH" User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.4.0 In-Reply-To: X-Antivirus-Status: Clean Content-Language: en-GB X-Antivirus: AVG (VPS 171128-0, 11/28/2017), Outbound message Cancel-Lock: sha1:7v1xKW5YuSw2rxqcdnQ7nH7RsBE= Xref: csiph.com comp.lang.java.programmer:37703 On 2017-11-28 16:28, Eric Douglas wrote: > On Tuesday, November 28, 2017 at 9:40:41 AM UTC-5, Daniele Futtorovic wrote: >> Hi folks, >> >> I got a statistical problem, and due to a youth math trauma, I'd like a >> bit of help to solve it. >> >> I have a data series. Integer values, but that should be beside the >> point. I want to identify and eliminate "outliers" from this series. >> "Outliers" being values that are "too big" or "too small", in short, >> that are not congruent with the rest of the series. I am well aware that >> saying "outlier" begs the question, hence the quotes, but I can >> fine-tune the degree of outlying for my purposes later on. For the time >> being, I wonder if someone could outline some basic approaches I could >> take in the matter. > > Were you looking for help figuring out what the outliers should be, or for Java code to remove values from a list which exceed a minimum and maximum? :-) No, I was looking for the math. Code is (comparatively) easy. -- DF.