Computational Statistics

, Volume 16, Issue 4, pp 481–504 | Cite as

Influence on Smoothness in Penalized Likelihood Regression for Binary Data

  • Robert Jernigan
  • Julie O’Connell


Penalized likelihood is a nonparametric regression technique which can be used to estimate a mean function for binary data. We wish to measure the sensitivity of the smoothing parameter to gross changes in the data when the optimal value of the smoothing parameter is selected using generalized cross-validation. Since penalized likelihood curve fitting requires both a grid search to determine the optimal value of the smoothing parameter and iterative solution for each grid point, naive calculations to determine the change in the optimal value of the smoothing parameter when each data value is modified are computationally intensive and time-consuming. We have developed techniques based on mathematical and numerical approximations for measuring sensitivity in penalized likelihood regression with binary data. These techniques have been applied to selected data sets to compute change in the smoothing parameter resulting from changes in individual data values.


Smoothing parameter Sensitivity Gross change Cross-validation Smoothing spline Logistic regression 


  1. Bumpus, H. (1899), “The elimination of the unfit as illustrated by the introduced sparrow, Passer domesticus”, Biological lectures of Woods Hole Marine Biology Station 6, 209–226.Google Scholar
  2. Cox, D. O’Sullivan, F. (1990), “Asymptotic analysis of penalized likelihood and related estimators”, The Annals of Statistics 18(4), 1676–1695.MathSciNetCrossRefGoogle Scholar
  3. Culver, D., Jernigan, R., O’Connell J. Kane, T. (1993) “The geometry of natural selection in cave and spring populations of the amphipod Gammarus minus”, Biological Journal of the Linnean Society 52, 49–67.CrossRefGoogle Scholar
  4. Draper, N. Smith, H. (1981), Applied Regression Analysis, 2nd ed., Wiley, NY Gu, C. Wahba, G. (1992), “Smoothing splines and analysis of variance in function spaces”, Technical Report No. 898, Department of Statistics, University of Wisconsin.Google Scholar
  5. Hastie, T. Tibshirani, R. (1990), Generalized Additive Models, Chapman and Hall.Google Scholar
  6. Hocking, R. (1985), The Analysis of Linear Models, Brooks-Cole, Monterey, CA.zbMATHGoogle Scholar
  7. McCullagh, P. Nelder, J., FRS (1989), Generalized Linear Models, Chapman Hall.Google Scholar
  8. Nychka, D. (1991), “Choosing a range for the amount of smoothing in nonparametric regression”, Journal of the American Statistical Association 86(415), 653–664.MathSciNetCrossRefGoogle Scholar
  9. O’Sullivan, F., Yandell, B. Raynor, W. (1986), “Automatic smoothing of regression functions in generalized linear models”, Journal of the American Statistical Association 81(393), 96–103.MathSciNetCrossRefGoogle Scholar
  10. Tapia, J. Thompson, R. (1990), Nonparametric Function Estimation, Modeling, and Simulation, SIAM, Philadelphia.zbMATHGoogle Scholar
  11. Thomas, W. (1991), “Influence diagnostics for the cross-validated smoothing parameter in spline smoothing”, Journal of the American Statistical Association 86(415) 693–698.MathSciNetCrossRefGoogle Scholar
  12. Wahba, G. (1990), Spline Models in Statistics, SIAM.Google Scholar
  13. Xiang, D. and Wahba, G. (1993) “Generalized approximate cross validation for generalized smoothing spline”, Department of Statistics, University of Wisconsin.Google Scholar

Copyright information

© Physica-Verlag 2001

Authors and Affiliations

  • Robert Jernigan
    • 1
  • Julie O’Connell
    • 1
  1. 1.Department of Mathematics and StatisticsAmerican UniversityWashingtonUSA

Personalised recommendations