Density ratio model selection. (English) Zbl 1127.62035
Summary: The density ratio model presumes that the log-likelihood ratio of two unknown densities is of some known parametric linear form. However, the choice of the functional form has an impact on both estimation and testing. The problem of over/underfitting in the context of the density ratio model is examined and the theory shows that bias and loss of efficiency are introduced when the model is misspecified. The problem of identifying the appropriate functional form for an application of the density ratio model is addressed by means of model selection criteria, which perform reasonably well. Several simulations integrate the presentation.
MSC:
| 62G08 | Nonparametric regression and quantile regression |
| 62G20 | Asymptotic properties of nonparametric inference |
| 62G05 | Nonparametric estimation |
| 62H12 | Estimation in multivariate analysis |
References:
| [1] | DOI: 10.1093/biomet/84.3.609 · Zbl 0888.62045 · doi:10.1093/biomet/84.3.609 |
| [2] | DOI: 10.1093/biomet/85.3.619 · Zbl 0954.62053 · doi:10.1093/biomet/85.3.619 |
| [3] | DOI: 10.1093/biomet/59.1.19 · Zbl 0231.62080 · doi:10.1093/biomet/59.1.19 |
| [4] | DOI: 10.1093/biomet/66.1.17 · Zbl 0399.62029 · doi:10.1093/biomet/66.1.17 |
| [5] | Breslow N. E., Statistical Methods in Cancer Research 1 (1980) |
| [6] | Cox D. R., The Analysis of Binary Data, 2. ed. (1989) · Zbl 0729.62004 |
| [7] | DOI: 10.1093/biomet/66.3.403 · Zbl 0428.62078 · doi:10.1093/biomet/66.3.403 |
| [8] | DOI: 10.1093/biomet/66.1.27 · Zbl 0448.62082 · doi:10.1093/biomet/66.1.27 |
| [9] | DOI: 10.1214/aos/1176345802 · Zbl 0491.62034 · doi:10.1214/aos/1176345802 |
| [10] | DOI: 10.1214/aos/1176346585 · Zbl 0578.62047 · doi:10.1214/aos/1176346585 |
| [11] | DOI: 10.1214/aos/1176350948 · Zbl 0668.62024 · doi:10.1214/aos/1176350948 |
| [12] | DOI: 10.1093/biomet/86.1.27 · Zbl 0917.62061 · doi:10.1093/biomet/86.1.27 |
| [13] | DOI: 10.1214/aos/1016120368 · Zbl 1106.60302 · doi:10.1214/aos/1016120368 |
| [14] | DOI: 10.1198/00401700152404327 · Zbl 1072.62583 · doi:10.1198/00401700152404327 |
| [15] | Fokianos K., Annals of the Institute for Statistical Mathematics |
| [16] | DOI: 10.1093/biomet/75.2.237 · Zbl 0641.62032 · doi:10.1093/biomet/75.2.237 |
| [17] | DOI: 10.1201/9781420036152 · doi:10.1201/9781420036152 |
| [18] | DOI: 10.1214/aos/1176325370 · Zbl 0799.62049 · doi:10.1214/aos/1176325370 |
| [19] | Akaike H., Second International Symposium in Information Theory pp 267– (1973) |
| [20] | DOI: 10.1214/aos/1176344136 · Zbl 0379.62005 · doi:10.1214/aos/1176344136 |
| [21] | Hannan E. J., Journal Royal Statistical Society, Series B 41 pp 190– (1979) |
| [22] | DOI: 10.1093/biomet/76.2.297 · Zbl 0669.62085 · doi:10.1093/biomet/76.2.297 |
| [23] | Choi B., ARMA Model Identification (1992) · Zbl 0754.62071 |
| [24] | Hong H., Econometric Theory 19 pp 923– (2003) |
| [25] | DOI: 10.1016/S0304-4076(00)00077-4 · Zbl 0967.62095 · doi:10.1016/S0304-4076(00)00077-4 |
| [26] | Box G. E.P., Journal of the Royal Statistical Society, Series B 26 pp 211– (1964) |
| [27] | Hastie T. J., Generalized Additive Models (1990) · Zbl 0747.62061 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
