Estimation of response from longitudinal binary data with nonignorable missing values in migraine trials
In migraine trials pain relief responses from a headache at specific time points and sustained pain relief response over a period of time are important efficacy measures. When there are missing records of individual time point pain scores and/or headache recurrences during a migraine trial, the comm...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2016-12-01
|
| Series: | Contemporary Clinical Trials Communications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2451865415300259 |
| _version_ | 1819225686317989888 |
|---|---|
| author | Fang Fang Xiaoyin Fan Ying Zhang |
| author_facet | Fang Fang Xiaoyin Fan Ying Zhang |
| author_sort | Fang Fang |
| collection | DOAJ |
| description | In migraine trials pain relief responses from a headache at specific time points and sustained pain relief response over a period of time are important efficacy measures. When there are missing records of individual time point pain scores and/or headache recurrences during a migraine trial, the common approach used in practice to estimate the sustained response is statistically inconsistent even if the data are missing completely at random. Methods dealing with nonignorable longitudinal missing data usually assume certain models for the missing mechanism which can not be checked as they involve unobserved data. Taking advantage of the specific definition of the ‘sustained pain relief’ response, we propose two estimating methods based on intuitive imputation, which do not require model assumptions on the missing probability or specification of the correlation structure among the longitudinal observations. The consistency of the proposed methods is discussed in theory and their empirical performances are assessed through intensive simulation studies. The simulation results show that the proposed methods perform well in terms of reducing bias and mean square error except in several extreme cases which are unlikely to happen in real trials. The application of the proposed methods is illustrated in a real data analysis. |
| first_indexed | 2024-12-23T10:13:32Z |
| format | Article |
| id | doaj.art-17d6ffab9c7d41b7b6a7ce7303322a7e |
| institution | Directory Open Access Journal |
| issn | 2451-8654 |
| language | English |
| last_indexed | 2024-12-23T10:13:32Z |
| publishDate | 2016-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Contemporary Clinical Trials Communications |
| spelling | doaj.art-17d6ffab9c7d41b7b6a7ce7303322a7e2022-12-21T17:50:53ZengElsevierContemporary Clinical Trials Communications2451-86542016-12-014C909810.1016/j.conctc.2016.06.011Estimation of response from longitudinal binary data with nonignorable missing values in migraine trialsFang Fang0Xiaoyin Fan1Ying Zhang2East China Normal University, Shanghai, 200241, ChinaNovartis Pharmaceuticals, 45 Sidney Street, Cambridge, MA, 02139, USAMerck Research Laboratories, 351 North Sumneytown Pike, North Wales, PA, 19454, USAIn migraine trials pain relief responses from a headache at specific time points and sustained pain relief response over a period of time are important efficacy measures. When there are missing records of individual time point pain scores and/or headache recurrences during a migraine trial, the common approach used in practice to estimate the sustained response is statistically inconsistent even if the data are missing completely at random. Methods dealing with nonignorable longitudinal missing data usually assume certain models for the missing mechanism which can not be checked as they involve unobserved data. Taking advantage of the specific definition of the ‘sustained pain relief’ response, we propose two estimating methods based on intuitive imputation, which do not require model assumptions on the missing probability or specification of the correlation structure among the longitudinal observations. The consistency of the proposed methods is discussed in theory and their empirical performances are assessed through intensive simulation studies. The simulation results show that the proposed methods perform well in terms of reducing bias and mean square error except in several extreme cases which are unlikely to happen in real trials. The application of the proposed methods is illustrated in a real data analysis.http://www.sciencedirect.com/science/article/pii/S2451865415300259Longitudinal binary dataNonignorable missingComplete-case analysisImputationBootstrap |
| spellingShingle | Fang Fang Xiaoyin Fan Ying Zhang Estimation of response from longitudinal binary data with nonignorable missing values in migraine trials Contemporary Clinical Trials Communications Longitudinal binary data Nonignorable missing Complete-case analysis Imputation Bootstrap |
| title | Estimation of response from longitudinal binary data with nonignorable missing values in migraine trials |
| title_full | Estimation of response from longitudinal binary data with nonignorable missing values in migraine trials |
| title_fullStr | Estimation of response from longitudinal binary data with nonignorable missing values in migraine trials |
| title_full_unstemmed | Estimation of response from longitudinal binary data with nonignorable missing values in migraine trials |
| title_short | Estimation of response from longitudinal binary data with nonignorable missing values in migraine trials |
| title_sort | estimation of response from longitudinal binary data with nonignorable missing values in migraine trials |
| topic | Longitudinal binary data Nonignorable missing Complete-case analysis Imputation Bootstrap |
| url | http://www.sciencedirect.com/science/article/pii/S2451865415300259 |
| work_keys_str_mv | AT fangfang estimationofresponsefromlongitudinalbinarydatawithnonignorablemissingvaluesinmigrainetrials AT xiaoyinfan estimationofresponsefromlongitudinalbinarydatawithnonignorablemissingvaluesinmigrainetrials AT yingzhang estimationofresponsefromlongitudinalbinarydatawithnonignorablemissingvaluesinmigrainetrials |