Semiparametric maximum likelihood estimation with data missing not at random

Morikawa, Kosuke; Kim, Jae Kwang; Kano, Yutaka

doi:10.1002/cjs.11340

Cited by 32 publications

(38 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method is essentially a parametric method and requires the estimation of the parameters of a (parametric) model chosen to describe the conditional (to V =1) disease process and then the solution of an empirical mean score equation resulting from a parametric model chosen for the verification process. The method may also be used in a semiparametric context, by resorting to a nonparametric regression approach to fit the conditional disease model, as in Morikawa et al (). Clearly, this topic deserves further investigation.…”

Section: Resultsmentioning

confidence: 99%

“…Firstly, it is scarcely flexible, because identifiability is proven only for the specific parametric assumptions about the verification and the disease processes. Secondly, because of NI missingness, it does not allow a statistical check of appropriateness of such assumptions (see also; Riddles et al, ; Morikawa et al, ; Yu et al, ). Finally, as pointed out by the authors themselves, MEL of ignorable/NI parameters λ 1 and λ 2 are typically highly biased, in cases of moderate or even high sample sizes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mean score equation and instrumental variables: Another look at estimating the volume under the receiver operating characteristic surface when data are missing not at random

Duc

Adimari

Chiogna

2020

Stat

View full text Add to dashboard Cite

Evaluation of accuracy of diagnostic tests is frequently undertaken under nonignorable (NI) verification bias. Here, we discuss an approach, based on a mean score equation, aimed to estimate the volume under the receiver operating characteristic (ROC) surface of a diagnostic test under NI verification bias. The proposed approach rests on a parametric regression model for the verification process, which accommodates for possible NI missingness in the disease status of sample subjects, and may employ instrumental variables, to help avoid possible identifiability problems. The solution of the mean score equation derived from the verification model requires to preliminarily estimate the parameters of a model for the disease process, whose specification is limited to verified subjects. Verification bias‐corrected estimators, an alternative to those recently proposed in the literature and based on a full likelihood approach, are obtained from the estimated verification and disease probabilities. Consistency and asymptotic normality of the new estimators are established. Simulation experiments are conducted to evaluate their finite‐sample performances, and an application to a dataset from a research on epithelial ovarian cancer is presented. Although the narrative is driven by the three‐class case, the extension to high‐dimensional ROC analysis is also presented.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Mean score equation and instrumental variables: Another look at estimating the volume under the receiver operating characteristic surface when data are missing not at random

Duc

Adimari

Chiogna

2020

Stat

View full text Add to dashboard Cite

show abstract

“…. Morikawa et al [17] proposed a semiparametric method for (3.2) in the case of independent and identical distribution data. Based on the first-step imputation, a similar way (refer to Louis [16]) is considered to establish the estimation equation for ϕ by solving…”

Section: Semiparametric Estimationmentioning

confidence: 99%

“…Shao and Wang [22] proposed a semiparametric inverse propensity weighting method using the nonresponse instrumental variable assumption of Wang et al [24], which discussed the identification of parameter for MNAR data as well. Riddles et al [20] proposed a propensity score adjustment method for MNAR data with a specified parametric model for the conditional distribution of respondents, and Morikawa et al [17] loosen this restriction to a semiparametric estimation.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we consider the parameter estimation of Poisson INAR(1) processes with MNAR data. We propose a semiparametric likelihood estimation for nonignorable nonresponse by employing the idea of Morikawa et al [17], which is based on the first-step imputation. A parametric model for π n and a nonparametric model for the distribution of observed data are allowed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Imputation-based semiparametric estimation for INAR(1) processes with missing data

Xiong

Wang

2020

Hacettepe Journal of Mathematics and Statistics

View full text Add to dashboard Cite

In applied problems parameter estimation with missing data has risen as a hot topic. Imputation for ignorable incomplete data is one of the most popular methods in integervalued time series. For data missing not at random (MNAR), estimators directly derived by imputation will lead results that is sensitive to the failure of the effectiveness. In view of the first-order integer-valued autoregressive (INAR(1)) processes with MNAR response mechanism, we consider an imputation based semiparametric method, which recommends the complete auxiliary variable of Yule-Walker equation. Asymptotic properties of relevant estimators are also derived. Some simulation studies are conducted to verify the effectiveness of our estimators, and a real example is also presented as an illustration.

show abstract

Bayesian inference for nonprobability samples with nonignorable missingness

Liu,

Chen,

et al. 2024

Statistical Analysis

View full text Add to dashboard Cite

Nonprobability samples, especially web survey data, have been available in many different fields. However, nonprobability samples suffer from selection bias, which will yield biased estimates. Moreover, missingness, especially nonignorable missingness, may also be encountered in nonprobability samples. Thus, it is a challenging task to make inference from nonprobability samples with nonignorable missingness. In this article, we propose a Bayesian approach to infer the population based on nonprobability samples with nonignorable missingness. In our method, different Logistic regression models are employed to estimate the selection probabilities and the response probabilities; the superpopulation model is used to explain the relationship between the study variable and covariates. Further, Bayesian and approximate Bayesian methods are proposed to estimate the response model parameters and the superpopulation model parameters, respectively. Specifically, the estimating functions for the response model parameters and superpopulation model parameters are utilized to derive the approximate posterior distribution in superpopulation model estimation. Simulation studies are conducted to investigate the finite sample performance of the proposed method. The data from the Pew Research Center and the Behavioral Risk Factor Surveillance System are used to show better performance of our proposed method over the other approaches.

show abstract

Semiparametric maximum likelihood estimation with data missing not at random

Cited by 32 publications

References 34 publications

Mean score equation and instrumental variables: Another look at estimating the volume under the receiver operating characteristic surface when data are missing not at random

Mean score equation and instrumental variables: Another look at estimating the volume under the receiver operating characteristic surface when data are missing not at random

Imputation-based semiparametric estimation for INAR(1) processes with missing data

Bayesian inference for nonprobability samples with nonignorable missingness

Contact Info

Product

Resources

About