Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: smoothing methods

Sortuj według:

Ogranicz wyniki do:

Data-driven score tests for homoscedastic linear regression model : asymptotic results

100%

Inglot T. , Ledwina T.

Probability and Mathematical Statistics

2006

tom Vol. 26, Fasc. 1

41--61

We describe and investigate new tests for testing the validity of a semiparametric random-design linear regression model. The tests were introduced in Inglot and Ledwina (2006a, b). We repeat here basic steps of the constructions. The resulting statistics are closely linked to some norms of the appropriate efficient score vector and related quantities. A useful way of deriving the efficient score vector is proposed and discussed. We introduce also a large class of estimators of the efficient score vector and prove that under the null model our constructions are asymptotically distribution free. The proof adopts and exploits some ideas and results developed in the area of semiparametric estimation. We give also the limiting distribution of the test statistics under the null hypothesis. The simulation results contained in Inglot and Ledwina (2006a, b) show the very good performance of the proposed tests.

Defect Backlog Size Prediction for Open-Source Projects with the Autoregressive Moving Average and Exponential Smoothing Models

67%

Anioła P. , Pandey S. K. , Staron M. , Ochodek M.

Annals of Computer Science and Information Systems

2023

tom Vol. 35

83--92

Context: predicting the number of defects in a defect backlog in a given time horizon can help allocate project resources and organize software development. Goal: to compare the accuracy of three defect backlog prediction methods in the context of large open-source (OSS) projects, i.e., ARIMA, Exponential Smoothing (ETS), and the state-of-the-art method developed at Ericsson AB (SM). Method: we perform a simulation study on a sample of 20 open-source projects to compare the prediction accuracy of the methods. Also, we use the Na\"{\i}ve prediction method as a baseline for sanity check. We use statistical inference tests and effect size coefficients to compare the prediction errors. Results: ARIMA, ETS, and SM were more accurate than the Na\"{\i}ve method. Also, the prediction errors were statistically lower for ETS than for SM (however, the effect size was negligible). Conclusions: ETS seems slightly more accurate than SM when predicting defect backlog size of OSS projects.