Research Article
BibTex RIS Cite

İkili yanıt değişkenine sahip modellerin yeterliliklerine ilişkin benzetim çalışması – parametrik olmayan yöntemler

Year 2017, Volume: 21 Issue: 2, 169 - 177, 01.04.2017
https://doi.org/10.16984/saufenbilder.297002

Abstract

  



Regresyon modelleri; birçok
açıklayıcı değişkenin önemini ortaya koyabilmek için tahmin, sınıflama, ve
analitik veri araçlarını kullanarak, veri analizinde etkili bir rol
oynamaktadır. Oldukça basit olmasına rağmen klasik doğrusal model, gerçek
hayattaki örneklerin doğrusal olmaması nedeniyle sıkça yetersiz kalmaktadır.
Bu çalışmada, çoklu doğrusal regresyon analizi varsayımlarından biri olan;
bağımlı değişkenin açıklayıcı değişkenler ile arasındaki ilişkinin belli bir
matematiksel forma uymasının zorunlu olmadığı parametrik olmayan bir
değerlendirme süreci ele alınacaktır. Bu anlamda bağımlı değişkenin iki
düzeyli değerler aldığı, daha çok neden-sonuç ilişkilerinin ortaya koyulması
amacıyla kullanılan klasik lojistik regresyon modelinin yerine, bağımlı
değişken ile açıklayıcı değişkenlerin aralarında var olan ilişki bir benzetim
çalışması kapsamında; genelleştirilmiş doğrusal model, toplamsal lojistik
regresyon model ve karar ağaçları ile incelenecektir. Benzetim çalışmasında
söz konusu olan yöntemler ile küçük, orta ve büyük ölçekli veri kümelerinde
çoklu bağlantının etkileri incelenecek ve bu yöntemler birbirleriyle
karşılaştırılacaktır.

References

  • [1] A. Erar, “Çoklu bağlantı varlığında doğrusal regresyon modellerinde değişken seçimi” Ankara, Hacettepe Üniversitesi, İstatistik Bölümü, 1994.
  • [2] A. Erar, “Bağlanım (Regresyon) Çözümlemesi Ders Notları” İstanbul, Mimar Sinan Güzel Sanatlar Üniversitesi, 2006.
  • [3] B. Kan Kılınç, “Yanıt Yüzeyi Modellerine MARS Yaklaşımı”, Eskişehir, Anadolu Üniversitesi, İstatistik Bölümü, 2010.
  • [4] Y. Kaşko, “Çoklu Bağlantı Durumunda İkili Lojistik Regresyon Modelinde Gerçekleşen 1.Tip Hata ve Testin Gücü”, Ankara, Ankara Üniversitesi, Biyometri ve Genetik Anabilim Dalı, 2007.
  • [5] G. Wahba and J. Wendelberger, “Some new mathematical methods for variational objective analysis using splines and cross validation”, Monthly Weather Review, vol.108, pp. 1122-1145, 1980.
  • [6] S. Wood, “Generalized Additive Models: An introduction to R”, Chapman and Hall/CRC, 2006.
  • [7] L. Breiman, J. Friedman, R. Olshen, and C. Stone, “Classification and Regression Trees”, Wadsworth, 1984.
  • [8] H. Christian, “Smoothing by spline functions”, Journal of Numerische Mathematic, vol.10, no.3, pp. 177-183, 1967.
  • [9] J. Duchon, “Splines minimizing rotation-invariant semi-norms in Sobolev spaces”, Constructive Theory of Functions of Several Variables, Springer, 1977.
  • [10] R. De Veaux and L. Ungar, “Multicollinearity: A tail of two nonparametric regressions”, Lecture Notes in Statistics: Selecting Models from Data, pp. 393-402, 2007.
  • [11] M. Hutchinson and R. Bischof, “A new method for estimating the spatial distribution of mean seasonal and annual rainfall applied to the Huner Valley, New South Wales”, Australian Meteorological Magazine , vol.31, no.3, pp.179-184, 1983.
  • [12] T. Hastie, R. Tibshirani and F. Friedman, “The Elements of Statistical Learning”, Springer, 2009.
  • [13] S. Kovalchik and R. Varadhan, “Fitting additive binomial regression models with the R package blm”, Journal of Statistical Software, vol.54, no.1, pp.1-18, 2013.
  • [14] L. Ma and X. Yan, “Examining the nonparametric effect of drivers' age in rear-end accidents through an additive logistic regression model”, Accident Analysis and Prevention, vol.67, pp.129-136, 2014.
  • [15] D. McFadden, “Conditional logit analysis of qualitative choice behavior”, Frontiers in Econometrics ,Academic Press, pp.105-142, 1974.
  • [16] J. Meinguet, “Multivariate interpolation at arbitrary points made simple”, Journal of Applied Mathematics and Physics, vol.30, pp.370-384,1979.
  • [17] C. Montgomery, E. Peck and G. Vining, “ Introduction to Linear Regression Analysis”, Wiley, 2012.
  • [18] W. Press, B. Flannery, S. Teukolsky and W. Vetterling, “Cubic Spline Interpolation. The Art of Scientific Computing”, Cambridge University Press, 1992.
  • [19] S. Silvey, “Multicollinearity and imprecise information”, Journal of Royal Statistics Society vol.31, pp.539-552, 1969.
  • [20] J. Shen and S. Gao, “A solution to seperation and multicollinearity in multiple logistic regression”, Journal of Data Science, vol.6, no.4, pp.515-531, 2008.
  • [21] B. Ripley, “Pattern Recognation and Neural Networks”, Cambridge University Press, 1996.

Comparative simulation study for model adequancy with binary response variable under multicollinearity – nonparametric approaches

Year 2017, Volume: 21 Issue: 2, 169 - 177, 01.04.2017
https://doi.org/10.16984/saufenbilder.297002

Abstract

Regression
models used to explore the importance of several explanatory variables in
estimation, classification and analytical tools play an efficient role for many
data analysis. Although the classical linear model is quite easy to use, it is
often not sufficient for many real data sets as the relationships between
variables do not hold the assumption of the linearity of the relationship
between dependent and explanatory variables. Under this study, a nonparametric
model fitting that does not require to form a strict mathematical relationship
between dependent and explanatory variables will be discussed on the contrary
the assumption in multiple linear regression. In this study, the relationship
between a binary dependent variable and the explanatory variables will be
examined in a conducted simulation study by using generalized linear, the
additive logistic regression in case of classical logistic regression model and
decision trees to explore the cause and effect relationship. The methods in question
and the simulation study will be performed for small, medium and large data
sets when multicollinearity problem exists and will be compared with each
other. 

References

  • [1] A. Erar, “Çoklu bağlantı varlığında doğrusal regresyon modellerinde değişken seçimi” Ankara, Hacettepe Üniversitesi, İstatistik Bölümü, 1994.
  • [2] A. Erar, “Bağlanım (Regresyon) Çözümlemesi Ders Notları” İstanbul, Mimar Sinan Güzel Sanatlar Üniversitesi, 2006.
  • [3] B. Kan Kılınç, “Yanıt Yüzeyi Modellerine MARS Yaklaşımı”, Eskişehir, Anadolu Üniversitesi, İstatistik Bölümü, 2010.
  • [4] Y. Kaşko, “Çoklu Bağlantı Durumunda İkili Lojistik Regresyon Modelinde Gerçekleşen 1.Tip Hata ve Testin Gücü”, Ankara, Ankara Üniversitesi, Biyometri ve Genetik Anabilim Dalı, 2007.
  • [5] G. Wahba and J. Wendelberger, “Some new mathematical methods for variational objective analysis using splines and cross validation”, Monthly Weather Review, vol.108, pp. 1122-1145, 1980.
  • [6] S. Wood, “Generalized Additive Models: An introduction to R”, Chapman and Hall/CRC, 2006.
  • [7] L. Breiman, J. Friedman, R. Olshen, and C. Stone, “Classification and Regression Trees”, Wadsworth, 1984.
  • [8] H. Christian, “Smoothing by spline functions”, Journal of Numerische Mathematic, vol.10, no.3, pp. 177-183, 1967.
  • [9] J. Duchon, “Splines minimizing rotation-invariant semi-norms in Sobolev spaces”, Constructive Theory of Functions of Several Variables, Springer, 1977.
  • [10] R. De Veaux and L. Ungar, “Multicollinearity: A tail of two nonparametric regressions”, Lecture Notes in Statistics: Selecting Models from Data, pp. 393-402, 2007.
  • [11] M. Hutchinson and R. Bischof, “A new method for estimating the spatial distribution of mean seasonal and annual rainfall applied to the Huner Valley, New South Wales”, Australian Meteorological Magazine , vol.31, no.3, pp.179-184, 1983.
  • [12] T. Hastie, R. Tibshirani and F. Friedman, “The Elements of Statistical Learning”, Springer, 2009.
  • [13] S. Kovalchik and R. Varadhan, “Fitting additive binomial regression models with the R package blm”, Journal of Statistical Software, vol.54, no.1, pp.1-18, 2013.
  • [14] L. Ma and X. Yan, “Examining the nonparametric effect of drivers' age in rear-end accidents through an additive logistic regression model”, Accident Analysis and Prevention, vol.67, pp.129-136, 2014.
  • [15] D. McFadden, “Conditional logit analysis of qualitative choice behavior”, Frontiers in Econometrics ,Academic Press, pp.105-142, 1974.
  • [16] J. Meinguet, “Multivariate interpolation at arbitrary points made simple”, Journal of Applied Mathematics and Physics, vol.30, pp.370-384,1979.
  • [17] C. Montgomery, E. Peck and G. Vining, “ Introduction to Linear Regression Analysis”, Wiley, 2012.
  • [18] W. Press, B. Flannery, S. Teukolsky and W. Vetterling, “Cubic Spline Interpolation. The Art of Scientific Computing”, Cambridge University Press, 1992.
  • [19] S. Silvey, “Multicollinearity and imprecise information”, Journal of Royal Statistics Society vol.31, pp.539-552, 1969.
  • [20] J. Shen and S. Gao, “A solution to seperation and multicollinearity in multiple logistic regression”, Journal of Data Science, vol.6, no.4, pp.515-531, 2008.
  • [21] B. Ripley, “Pattern Recognation and Neural Networks”, Cambridge University Press, 1996.
There are 21 citations in total.

Details

Subjects Industrial Engineering
Journal Section Research Articles
Authors

Betül Kan Kılınç This is me

Mustafa Çavuş

Publication Date April 1, 2017
Submission Date June 22, 2016
Acceptance Date November 23, 2016
Published in Issue Year 2017 Volume: 21 Issue: 2

Cite

APA Kan Kılınç, B., & Çavuş, M. (2017). Comparative simulation study for model adequancy with binary response variable under multicollinearity – nonparametric approaches. Sakarya University Journal of Science, 21(2), 169-177. https://doi.org/10.16984/saufenbilder.297002
AMA Kan Kılınç B, Çavuş M. Comparative simulation study for model adequancy with binary response variable under multicollinearity – nonparametric approaches. SAUJS. April 2017;21(2):169-177. doi:10.16984/saufenbilder.297002
Chicago Kan Kılınç, Betül, and Mustafa Çavuş. “Comparative Simulation Study for Model Adequancy With Binary Response Variable under Multicollinearity – Nonparametric Approaches”. Sakarya University Journal of Science 21, no. 2 (April 2017): 169-77. https://doi.org/10.16984/saufenbilder.297002.
EndNote Kan Kılınç B, Çavuş M (April 1, 2017) Comparative simulation study for model adequancy with binary response variable under multicollinearity – nonparametric approaches. Sakarya University Journal of Science 21 2 169–177.
IEEE B. Kan Kılınç and M. Çavuş, “Comparative simulation study for model adequancy with binary response variable under multicollinearity – nonparametric approaches”, SAUJS, vol. 21, no. 2, pp. 169–177, 2017, doi: 10.16984/saufenbilder.297002.
ISNAD Kan Kılınç, Betül - Çavuş, Mustafa. “Comparative Simulation Study for Model Adequancy With Binary Response Variable under Multicollinearity – Nonparametric Approaches”. Sakarya University Journal of Science 21/2 (April 2017), 169-177. https://doi.org/10.16984/saufenbilder.297002.
JAMA Kan Kılınç B, Çavuş M. Comparative simulation study for model adequancy with binary response variable under multicollinearity – nonparametric approaches. SAUJS. 2017;21:169–177.
MLA Kan Kılınç, Betül and Mustafa Çavuş. “Comparative Simulation Study for Model Adequancy With Binary Response Variable under Multicollinearity – Nonparametric Approaches”. Sakarya University Journal of Science, vol. 21, no. 2, 2017, pp. 169-77, doi:10.16984/saufenbilder.297002.
Vancouver Kan Kılınç B, Çavuş M. Comparative simulation study for model adequancy with binary response variable under multicollinearity – nonparametric approaches. SAUJS. 2017;21(2):169-77.