@book{
 title = {Statistical hypothesis testing in positive unlabelled data},
 type = {book},
 year = {2014},
 pages = {66-81},
 volume = {8726 LNAI},
 issue = {PART 3},
 id = {6f06d9c1-29b5-39f0-a0fe-53ded68ac897},
 created = {2021-11-12T08:30:19.550Z},
 file_attached = {false},
 profile_id = {789246de-927b-32cc-ae4f-1b7e2b31674c},
 group_id = {e3c82d43-35db-3bbb-b28a-0fd521d70498},
 last_modified = {2021-11-12T08:30:19.550Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 source_type = {book},
 private_publication = {false},
 abstract = {We propose a set of novel methodologies which enable valid statistical hypothesis testing when we have only positive and unlabelled (PU) examples. This type of problem, a special case of semi-supervised data, is common in text mining, bioinformatics, and computer vision. Focusing on a generalised likelihood ratio test, we have 3 key contributions: (1) a proof that assuming all unlabelled examples are negative cases is sufficient for independence testing, but not for power analysis activities; (2) a new methodology that compensates this and enables power analysis, allowing sample size determination for observing an effect with a desired power; and finally, (3) a new capability, supervision determination, which can determine a-priori the number of labelled examples the user must collect before being able to observe a desired statistical effect. Beyond general hypothesis testing, we suggest the tools will additionally be useful for information theoretic feature selection, and Bayesian Network structure learning. © 2014 Springer-Verlag.},
 bibtype = {book},
 author = {Sechidis, K and Calvo, B and Brown, G}
}

{"_id":"4eWrYtkXPkCR4jZKY","bibbaseid":"sechidis-calvo-brown-statisticalhypothesistestinginpositiveunlabelleddata-2014","downloads":0,"creationDate":"2018-01-30T12:38:06.518Z","title":"Statistical hypothesis testing in positive unlabelled data","author_short":["Sechidis, K.","Calvo, B.","Brown, G."],"year":2014,"bibtype":"book","biburl":"https://bibbase.org/service/mendeley/789246de-927b-32cc-ae4f-1b7e2b31674c","bibdata":{"title":"Statistical hypothesis testing in positive unlabelled data","type":"book","year":"2014","pages":"66-81","volume":"8726 LNAI","issue":"PART 3","id":"6f06d9c1-29b5-39f0-a0fe-53ded68ac897","created":"2021-11-12T08:30:19.550Z","file_attached":false,"profile_id":"789246de-927b-32cc-ae4f-1b7e2b31674c","group_id":"e3c82d43-35db-3bbb-b28a-0fd521d70498","last_modified":"2021-11-12T08:30:19.550Z","read":false,"starred":false,"authored":false,"confirmed":false,"hidden":false,"source_type":"book","private_publication":false,"abstract":"We propose a set of novel methodologies which enable valid statistical hypothesis testing when we have only positive and unlabelled (PU) examples. This type of problem, a special case of semi-supervised data, is common in text mining, bioinformatics, and computer vision. Focusing on a generalised likelihood ratio test, we have 3 key contributions: (1) a proof that assuming all unlabelled examples are negative cases is sufficient for independence testing, but not for power analysis activities; (2) a new methodology that compensates this and enables power analysis, allowing sample size determination for observing an effect with a desired power; and finally, (3) a new capability, supervision determination, which can determine a-priori the number of labelled examples the user must collect before being able to observe a desired statistical effect. Beyond general hypothesis testing, we suggest the tools will additionally be useful for information theoretic feature selection, and Bayesian Network structure learning. © 2014 Springer-Verlag.","bibtype":"book","author":"Sechidis, K and Calvo, B and Brown, G","bibtex":"@book{\n title = {Statistical hypothesis testing in positive unlabelled data},\n type = {book},\n year = {2014},\n pages = {66-81},\n volume = {8726 LNAI},\n issue = {PART 3},\n id = {6f06d9c1-29b5-39f0-a0fe-53ded68ac897},\n created = {2021-11-12T08:30:19.550Z},\n file_attached = {false},\n profile_id = {789246de-927b-32cc-ae4f-1b7e2b31674c},\n group_id = {e3c82d43-35db-3bbb-b28a-0fd521d70498},\n last_modified = {2021-11-12T08:30:19.550Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n source_type = {book},\n private_publication = {false},\n abstract = {We propose a set of novel methodologies which enable valid statistical hypothesis testing when we have only positive and unlabelled (PU) examples. This type of problem, a special case of semi-supervised data, is common in text mining, bioinformatics, and computer vision. Focusing on a generalised likelihood ratio test, we have 3 key contributions: (1) a proof that assuming all unlabelled examples are negative cases is sufficient for independence testing, but not for power analysis activities; (2) a new methodology that compensates this and enables power analysis, allowing sample size determination for observing an effect with a desired power; and finally, (3) a new capability, supervision determination, which can determine a-priori the number of labelled examples the user must collect before being able to observe a desired statistical effect. Beyond general hypothesis testing, we suggest the tools will additionally be useful for information theoretic feature selection, and Bayesian Network structure learning. © 2014 Springer-Verlag.},\n bibtype = {book},\n author = {Sechidis, K and Calvo, B and Brown, G}\n}","author_short":["Sechidis, K.","Calvo, B.","Brown, G."],"biburl":"https://bibbase.org/service/mendeley/789246de-927b-32cc-ae4f-1b7e2b31674c","bibbaseid":"sechidis-calvo-brown-statisticalhypothesistestinginpositiveunlabelleddata-2014","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0},"search_terms":["statistical","hypothesis","testing","positive","unlabelled","data","sechidis","calvo","brown"],"keywords":[],"authorIDs":[],"dataSources":["F7jCKzHzcjJZH8w9i","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"]}