Pregled bibliografske jedinice broj: 1035930
Estimation of random accuracy and its use in validation of predictive quality of classification models within predictive challenges
Estimation of random accuracy and its use in validation of predictive quality of classification models within predictive challenges // Croatica chemica acta, 92 (2019), 3; 379-391 doi:10.5562/cca3551 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 1035930 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Estimation of random accuracy and its use in
validation of predictive quality of classification
models within predictive challenges
Autori
Lučić, Bono ; Batista, Jadranko ; Bojović, Viktor ; Lovrić, Mario ; Sović Kržić, Ana ; Bešlo, Drago ; Nadramija, Damir ; Vikić-Topić, Dražen
Izvornik
Croatica chemica acta (0011-1643) 92
(2019), 3;
379-391
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
model validation ; QSPR ; QSAR ; two-class variable ; classification model ; contingency table ; estimation ; prediction ; test set ; correlation coefficient ; predictive error ; classification accuracy ; model ranking ; random accuracy
Sažetak
Shortcomings of the correlation coefficient (Pearson's) as a measure for estimating and calculating the accuracy of predictive model properties are analysed. Here we discuss two such cases that can often occur in the application of the model in predicting properties of a new external set of compounds. The first problem in using the correlation coefficient is its insensitivity to the systemic error that must be expected in predicting properties of a novel external set of compounds, which is not a random sample selected from the training set. The second problem is that an external set can be arbitrarily large or small and have an arbitrary and uneven distribution of the measured value of the target variable, whose values are not known in advance. In these conditions, the correlation coefficient can be an overoptimistic measure of agreement of predicted values with the corresponding experimental values and can lead to a highly optimistic conclusion about the predictive ability of the model. Due to these shortcomings of the correlation coefficient, the use of standard error (root-mean-square-error) of prediction is suggested as a better quality measure of predictive capabilities of a model. In the case of classification models, the use of the difference between the real accuracy and the most probable random accuracy of the model shows very good characteristics in ranking different models according to predictive quality, having at the same time an obvious interpretation.
Izvorni jezik
Engleski
Znanstvena područja
Kemija, Računarstvo, Interdisciplinarne biotehničke znanosti
Napomena
HrZZ and EU-ESF, Basic grant of MZO/RBI to Bono
Lučić and SCE for Marine Bioprospecting–BioProCro
(KK.01.1.1.01)
POVEZANOST RADA
Projekti:
EK-KF-KK.01.1.1.01.0002 - Bioprospecting Jadranskog mora (Jerković, Igor; Dragović-Uzelac, Verica; Šantek, Božidar; Čož-Rakovac, Rozelinda; Kraljević Pavelić, Sandra; Jokić, Stela, EK ) ( CroRIS)
Basic grant of MZO/RBI to Bono Lučić and Croatian Science Foundation (DOK-01-2018)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Fakultet agrobiotehničkih znanosti Osijek,
Institut "Ruđer Bošković", Zagreb,
Dječja bolnica Srebrnjak
Profili:
Bono Lučić (autor)
Damir Nadramija (autor)
Dražen Vikić-Topić (autor)
Drago Bešlo (autor)
Ana Sović (autor)
Mario Lovrić (autor)
Viktor Bojović (autor)
Citiraj ovu publikaciju:
Časopis indeksira:
- Current Contents Connect (CCC)
- Web of Science Core Collection (WoSCC)
- Science Citation Index Expanded (SCI-EXP)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus