Limits...
Efficient estimation of smooth distributions from coarsely grouped data.

Rizzi S, Gampe J, Eilers PH - Am. J. Epidemiol. (2015)

Bottom Line: This maximization is performed efficiently by a version of the iteratively reweighted least-squares algorithm.Optimal values of the smoothing parameter are chosen by minimizing Akaike's Information Criterion.Wide, open-ended intervals can be handled properly.

View Article: PubMed Central - PubMed

Show MeSH

Related in: MedlinePlus

Gompertz distribution with grouping width 5 and sample size (A and C, n = 200; B and D, n = 1,000). The solid black line gives the standard deviation of 500 penalized composite link model estimates obtained in this setting. The gray lines summarize the distribution of the 500 estimates of the standard error derived from the sandwich estimator (A and B) and from the Bayesian estimator (C and D), with median (solid gray line), 25%–75% quantiles (dashed gray lines), and 1%–99% quantiles (dotted gray lines), respectively.
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4493979&req=5

KWV020F5: Gompertz distribution with grouping width 5 and sample size (A and C, n = 200; B and D, n = 1,000). The solid black line gives the standard deviation of 500 penalized composite link model estimates obtained in this setting. The gray lines summarize the distribution of the 500 estimates of the standard error derived from the sandwich estimator (A and B) and from the Bayesian estimator (C and D), with median (solid gray line), 25%–75% quantiles (dashed gray lines), and 1%–99% quantiles (dotted gray lines), respectively.


Efficient estimation of smooth distributions from coarsely grouped data.

Rizzi S, Gampe J, Eilers PH - Am. J. Epidemiol. (2015)

Gompertz distribution with grouping width 5 and sample size (A and C, n = 200; B and D, n = 1,000). The solid black line gives the standard deviation of 500 penalized composite link model estimates obtained in this setting. The gray lines summarize the distribution of the 500 estimates of the standard error derived from the sandwich estimator (A and B) and from the Bayesian estimator (C and D), with median (solid gray line), 25%–75% quantiles (dashed gray lines), and 1%–99% quantiles (dotted gray lines), respectively.
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4493979&req=5

KWV020F5: Gompertz distribution with grouping width 5 and sample size (A and C, n = 200; B and D, n = 1,000). The solid black line gives the standard deviation of 500 penalized composite link model estimates obtained in this setting. The gray lines summarize the distribution of the 500 estimates of the standard error derived from the sandwich estimator (A and B) and from the Bayesian estimator (C and D), with median (solid gray line), 25%–75% quantiles (dashed gray lines), and 1%–99% quantiles (dotted gray lines), respectively.
Bottom Line: This maximization is performed efficiently by a version of the iteratively reweighted least-squares algorithm.Optimal values of the smoothing parameter are chosen by minimizing Akaike's Information Criterion.Wide, open-ended intervals can be handled properly.

View Article: PubMed Central - PubMed

Show MeSH
Related in: MedlinePlus