Comparison of Different LGM-Based Methods with MAR and MNAR Dropout Data
The missing not at random (MNAR) mechanism may bias parameter estimates and even distort study results. This study compared the maximum likelihood (ML) selection model based on missing at random (MAR) mechanism and the Diggle–Kenward selection model based on MNAR mechanism for handling missing data...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2017-05-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/article/10.3389/fpsyg.2017.00722/full |
| _version_ | 1818522279822229504 |
|---|---|
| author | Meijuan Li Meijuan Li Nan Chen Yang Cui Hongyun Liu Hongyun Liu |
| author_facet | Meijuan Li Meijuan Li Nan Chen Yang Cui Hongyun Liu Hongyun Liu |
| author_sort | Meijuan Li |
| collection | DOAJ |
| description | The missing not at random (MNAR) mechanism may bias parameter estimates and even distort study results. This study compared the maximum likelihood (ML) selection model based on missing at random (MAR) mechanism and the Diggle–Kenward selection model based on MNAR mechanism for handling missing data through a Monte Carlo simulation study. Four factors were considered, including the missingness mechanism, the dropout rate, the distribution shape (i.e., skewness and kurtosis), and the sample size. The results indicated that: (1) Under the MAR mechanism, the Diggle–Kenward selection model yielded similar estimation results with the ML approach; Under the MNAR mechanism, the results of ML approach were underestimated, especially for the intercept mean and intercept slope (μi and μs). (2) Under the MAR mechanism, the 95% CP of the Diggle–Kenward selection model was lower than that of the ML method; Under the MNAR mechanism, the 95% CP for the two methods were both under the desired level of 95%, but the Diggle–Kenward selection model yielded much higher coverage probabilities than the ML method. (3) The Diggle–Kenward selection model was easier to be influenced by the non-normal degree of target variable's distribution than the ML approach. The level of dropout rate was the major factor affecting the parameter estimation precision, and the dropout rate-induced difference of two methods can be ignored only when the dropout rate falls below 10%. |
| first_indexed | 2024-12-11T05:31:10Z |
| format | Article |
| id | doaj.art-587f57e725e74d2fac399b241cb20406 |
| institution | Directory Open Access Journal |
| issn | 1664-1078 |
| language | English |
| last_indexed | 2024-12-11T05:31:10Z |
| publishDate | 2017-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj.art-587f57e725e74d2fac399b241cb204062022-12-22T01:19:24ZengFrontiers Media S.A.Frontiers in Psychology1664-10782017-05-01810.3389/fpsyg.2017.00722249511Comparison of Different LGM-Based Methods with MAR and MNAR Dropout DataMeijuan Li0Meijuan Li1Nan Chen2Yang Cui3Hongyun Liu4Hongyun Liu5Collaborative Innovation Center of Assessment Toward Basic Education Quality, Beijing Normal UniversityBeijing, ChinaEducational Supervision and Quality Assessment Research Center, Beijing Academy of Educational SciencesBeijing, ChinaSchool of Psychology, Beijing Normal UniversityBeijing, ChinaCollaborative Innovation Center of Assessment Toward Basic Education Quality, Beijing Normal UniversityBeijing, ChinaSchool of Psychology, Beijing Normal UniversityBeijing, ChinaBeijing Key Laboratory of Applied Experimental Psychology, School of Psychology, Beijing Normal UniversityBeijing, ChinaThe missing not at random (MNAR) mechanism may bias parameter estimates and even distort study results. This study compared the maximum likelihood (ML) selection model based on missing at random (MAR) mechanism and the Diggle–Kenward selection model based on MNAR mechanism for handling missing data through a Monte Carlo simulation study. Four factors were considered, including the missingness mechanism, the dropout rate, the distribution shape (i.e., skewness and kurtosis), and the sample size. The results indicated that: (1) Under the MAR mechanism, the Diggle–Kenward selection model yielded similar estimation results with the ML approach; Under the MNAR mechanism, the results of ML approach were underestimated, especially for the intercept mean and intercept slope (μi and μs). (2) Under the MAR mechanism, the 95% CP of the Diggle–Kenward selection model was lower than that of the ML method; Under the MNAR mechanism, the 95% CP for the two methods were both under the desired level of 95%, but the Diggle–Kenward selection model yielded much higher coverage probabilities than the ML method. (3) The Diggle–Kenward selection model was easier to be influenced by the non-normal degree of target variable's distribution than the ML approach. The level of dropout rate was the major factor affecting the parameter estimation precision, and the dropout rate-induced difference of two methods can be ignored only when the dropout rate falls below 10%.http://journal.frontiersin.org/article/10.3389/fpsyg.2017.00722/fulllatent growth modelmissing at random (MAR)missing not at random (MNAR)Diggle–Kenward selection modelmaximum likelihood approach |
| spellingShingle | Meijuan Li Meijuan Li Nan Chen Yang Cui Hongyun Liu Hongyun Liu Comparison of Different LGM-Based Methods with MAR and MNAR Dropout Data Frontiers in Psychology latent growth model missing at random (MAR) missing not at random (MNAR) Diggle–Kenward selection model maximum likelihood approach |
| title | Comparison of Different LGM-Based Methods with MAR and MNAR Dropout Data |
| title_full | Comparison of Different LGM-Based Methods with MAR and MNAR Dropout Data |
| title_fullStr | Comparison of Different LGM-Based Methods with MAR and MNAR Dropout Data |
| title_full_unstemmed | Comparison of Different LGM-Based Methods with MAR and MNAR Dropout Data |
| title_short | Comparison of Different LGM-Based Methods with MAR and MNAR Dropout Data |
| title_sort | comparison of different lgm based methods with mar and mnar dropout data |
| topic | latent growth model missing at random (MAR) missing not at random (MNAR) Diggle–Kenward selection model maximum likelihood approach |
| url | http://journal.frontiersin.org/article/10.3389/fpsyg.2017.00722/full |
| work_keys_str_mv | AT meijuanli comparisonofdifferentlgmbasedmethodswithmarandmnardropoutdata AT meijuanli comparisonofdifferentlgmbasedmethodswithmarandmnardropoutdata AT nanchen comparisonofdifferentlgmbasedmethodswithmarandmnardropoutdata AT yangcui comparisonofdifferentlgmbasedmethodswithmarandmnardropoutdata AT hongyunliu comparisonofdifferentlgmbasedmethodswithmarandmnardropoutdata AT hongyunliu comparisonofdifferentlgmbasedmethodswithmarandmnardropoutdata |