Flexible smoothing with B-splines and penalties

Eilers, Paul H.C.; Marx, Brian D.

doi:10.1214/ss/1038425655

Cited by 3,111 publications

(2,999 citation statements)

References 57 publications

Supporting

Mentioning

2,978

Contrasting

Unclassified

Order By: Relevance

“…For the definition of B-splines see, for example, Dierckx (1993). The corresponding penalty that is used within the framework of penalized splines (P-splines; Eilers and Marx, 1996) is…”

Section: Variable Selection By Regularizationmentioning

confidence: 99%

“…, k and by specifying suitable design matrices. The second approach (denoted by glmmLasso smooth ) fits a GLMM together with a smooth baseline hazard based on penalized B-spline expansion (Eilers and Marx, 1996). For both L 1 -regularized approaches the optimal tuning parameter λ has been determined using the Bayesian Information Criterion (BIC, see Schwarz, 1978).…”

Section: Simulation Studymentioning

confidence: 99%

See 1 more Smart Citation

Variable selection in discrete survival models including heterogeneity

Groll

Tutz

2016

Lifetime Data Anal

View full text Add to dashboard Cite

Several variable selection procedures are available for continuous time-toevent data. However, if time is measured in a discrete way and therefore many ties occur models for continuous time are inadequate. We propose penalized likelihood methods that perform efficient variable selection in discrete survival modeling with explicit modeling of the heterogeneity in the population. The method is based on a combination of ridge and lasso type penalties that are tailored to the case of discrete survival. The performance is studied in simulation studies and an application to the birth of the first child.

show abstract

“…For the definition of B-splines see, for example, Dierckx (1993). The corresponding penalty that is used within the framework of penalized splines (P-splines; Eilers and Marx, 1996) is…”

Section: Variable Selection By Regularizationmentioning

confidence: 99%

Section: Simulation Studymentioning

confidence: 99%

Variable selection in discrete survival models including heterogeneity

Groll

Tutz

2016

Lifetime Data Anal

View full text Add to dashboard Cite

show abstract

“…We employ a parsimonious approach known as penalized regression splines (p-splines) that is relatively common in the statistical literature, but is somewhat less well known in econometrics. In its present form, this approach was first proposed by Eilers and Marx (1996) and Ruppert and Carroll (1997) 7 . In the interests of exposition, I describe a simplified version of (2) …”

Section: Appendix Amentioning

confidence: 99%

Driven to drink: Sin taxes near a border

Beatty

Larsen

Sommervoll

2009

Journal of Health Economics

View full text Add to dashboard Cite

Abstract:This paper investigates household purchasing behavior in response to differing alcohol and tobacco taxes near an international border. Our study suggests that large tax differentials near borders induce economically important tax avoidance behavior that may limit a government's ability to raise revenue and potentially undermine the pursuit of important health and social policy goals. We match novel supermarket scanner and consumer expenditure data to measure the size and scope of the effect for households and stores. We find that stores near/far from the international border have statistically significantly lower/higher sales of beer and tobacco than comparable stores far/near the border. Moreover, we find that households near the border report higher consumption of these same goods. This is consistent with households facing lower prices. Finally, we find measures of externalities associated with the consumption of alcohol and tobacco are higher near the border.

show abstract

“…25, 12.75,…54.75. I use quadratic B-spline basis functions (BOOR, 1978;EILERS;MARX, 1996) over uniform knots at two-year intervals. 1 When fertility data is reported as averages for age groups (call the groups A 1 …A g ), we need multipliers for aggregating f. The Nx1 vector f is related to the gx1 vector of group averages (called y from here on) by:…”

Section: Notation and Derivation Of The Calibrated Spline Estimatormentioning

confidence: 99%

Calibrated spline estimation of detailed fertility schedules from abridged data¹

Schmertmann¹

2014

Rev. bras. estud. popul.

View full text Add to dashboard Cite

Flexible smoothing with B-splines and penalties

Cited by 3,111 publications

References 57 publications

Variable selection in discrete survival models including heterogeneity

Variable selection in discrete survival models including heterogeneity

Driven to drink: Sin taxes near a border

Calibrated spline estimation of detailed fertility schedules from abridged data¹

Contact Info

Product

Resources

About