Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 5

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  model selection
help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1
Publication available in full text mode
Content available

Best Model Selection for Determinants of Students’ Academic Performance at Tertiary Level in Azad Jammu and Kashmir, Pakistan

100%
Hussain K., Farooq S., Akhtar N., Abbassi F. A.
The New Educational Review
|
2018
|
vol. 51
66-77
EN
The presented study is intended to suggest the best model to predict students’ academic performance at university level. For this purpose, primary data was collected from 400 undergraduate and graduate students of eight departments of Mirpur University of Science and Technology (MUST), which were selected through stratified random sampling. CGPA is used as an indicator of students’ academic performance. Stepwise linear regression is used to select the best model to predict students’ academic performance at tertiary level. The final model selected through stepwise regression includes six variables: the student’s IQ, ownership of AC, gender, geographic location, self-study hours and ownership of fridge as significant predictors of students’ academic performance at tertiary level. IQ, ownership of assets and self-study hours are found to have a positive effect on CGPA while being male and the distance of the household to nearest market are found to have a negative effect on CGPA.
2
Publication available in full text mode
Content available

Variational Approximations for Selecting Hierarchical Models of Circular Data in a Small Area Estimation Application

100%
Hernandez-Stumpfhauser D., Breidt F. J., Opsomer J. D.
Statistics in Transition new series
|
2016
|
vol. 17
|
issue 1
91-104
EN
We consider hierarchical regression models for circular data using the projected normal distribution, applied in the development of weights for the Access Point Angler Intercept Survey, a recreational angling survey conducted by the US National Marine Fisheries Service. Weighted estimates of recreational fish catch are used in stock assessments and fisheries regulation. The construction of the survey weights requires the distribution of daily departure times of anglers from fishing sites, within spatio-temporal domains subdivided by the mode of fishing. Because many of these domains have small sample sizes, small area estimation methods are developed. Bayesian inference for the circular distributions on the 24-hour clock is conducted, based on a large set of observed daily departure times from another National Marine Fisheries Service study, the Coastal Household Telephone Survey. A novel variational/Laplace approximation to the posterior distribution allows fast comparison of a large number of models in this context, by dramatically speeding up computations relative to the fast Markov Chain Monte Carlo method while giving virtually identical results.
3
Publication available in full text mode
Content available

DISCRIMINANT STEPWISE PROCEDURE

100%
Kubus M.
Acta Universitatis Lodziensis. Folia Oeconomica
|
2014
|
vol. 3
|
issue 302
EN
Stepwise procedure is now probably the most popular tool for automatic feature selection. In the most cases it represents model selection approach which evaluates various feature subsets (so called wrapper). In fact it is heuristic search technique which examines the space of all possible feature subsets. This method is known in the literature under different names and variants. We organize the concepts and terminology, and show several variants of stepwise feature selection from a search strategy point of view. Short review of implementations in R will be given.
4
Publication available in full text mode
Content available

On Model Selection in Some Regularized Linear Regression Methods

88%
Kubus M., Opole University of Technology D. o. M. a. A. C. S.
Acta Universitatis Lodziensis. Folia Oeconomica
|
2013
|
vol. 285
EN
A dynamic development of various regularization formulas in linear models has been observed recently. Penalizing the values of coefficients affects decreasing of the variance (shrinking coefficients to zero) and feature selection (setting zero for some coefficients). Feature selection via regularized linear models is preferred over popular wrapper methods in high dimension due to less computational burden as well as due to the fact that it is less prone to overfitting. However, estimated coefficients (and as a result quality of the model) depend on tuning parameters. Using model selection criteria available in R implementation does not guarantee that optimal model will be chosen. Having done simulation study we propose to use EDC criterion as an alternative.
PL
W ostatnich latach można zaobserwować dynamiczny rozwój różnych postaci regularyzacji w modelach liniowych. Wprowadzenie kary za duże wartości współczynników skutkuje zmniejszeniem wariancji (wartości współczynników są ,,przyciągane” do zera) oraz eliminacją niektórych zmiennych (niektóre współczynniki się zerują). Selekcja zmiennych za pomocą regularyzowanych modeli liniowych jest w problemach wielowymiarowych preferowana wobec popularnego podejścia polegającego na przeszukiwaniu przestrzeni cech i ocenie podzbiorów zmiennych za pomocą kryterium jakości modelu (wrappers). Przyczyną są mniejsze koszty obliczeń i mniejsza podatność na nadmierne dopasowanie. Jednakże wartości estymowanych współczynników (a więc także jakość modelu) zależą od parametrów regularyzacji. Zaimplementowane w tym celu w programie R kryteria jakości modelu nie gwarantują wyboru modelu optymalnego. Na podstawie przeprowadzonych symulacji w artykule proponuje się zastosowanie kryterium EDC.
5
Publication available in full text mode
Content available

Metoda Hellwiga jako kryterium doboru zmiennych do modeli szeregów czasowych

75%
Serwa D.
Metody Ilościowe w Badaniach Ekonomicznych
|
2011
|
vol. 12
|
issue 2
312-321
PL
Celem pracy jest rozstrzygnięcie, czy metoda Hellwiga jest użyteczna w odniesieniu do konstruowania modeli szeregów czasowych i w jakim zakresie jest ona konkurencyjna wobec innych metod, na przykład wykorzystujących kryteria informacyjne Schwarza i Akaike. Okazuje się, że metoda Hellwiga w pewnych, często w praktyce ekonometrycznej występujących przypadkach, nie prowadzi do wyboru odpowiedniego modelu.
EN
We check if Hellwig method is useful in building time-series models and if it performs better than other statistical methods, including Akaike and Schwarz information criteria. We find that the Hellwig method often leads to incorrect model specifications.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.