Cite Article
A Latent Class Model for Multivariate Binary Data Subject to Missingness
Choose citation formatBibTeX
@article{IJASEIT14910, author = {Samah Zakaria and Mai Sherif Hafez and Ahmed M. Gad}, title = {A Latent Class Model for Multivariate Binary Data Subject to Missingness}, journal = {International Journal on Advanced Science, Engineering and Information Technology}, volume = {11}, number = {5}, year = {2021}, pages = {1832--1840}, keywords = {binary variables; latent class model; item non-response; non-random missingness; response propensity.}, abstract = {When researchers are interested in measuring social phenomena that cannot be measured using a single variable, the appropriate statistical tool to be used is a latent variable model. A number of manifest variables is used to define the latent phenomenon. The manifest variables may be incomplete due to different forms of non-response that may or may not be random. In such cases, especially when the missingness is nonignorable, it is inevitable to include a missingness mechanism in the model to obtain valid estimates for parameters. In social surveys, categorical items can be considered the most common type of variable. We thus propose a latent class model where two categorical latent variables are defined; one represents the latent phenomenon of interest, and another represents a respondent’s propensity to respond to survey items. All manifest items are considered to be categorical. The proposed model incorporates a missingness mechanism that accounts for forms of missingness that may not be random by allowing the latent response propensity class to depend on the latent phenomenon under consideration, given a set of covariates. The Expectation-Maximization (EM) algorithm is used for estimating the proposed model. The proposed model is used to analyze data from 2014 Egyptian Demographic and Health Survey (EDHS14). Missing data is artificially created in order to study results under the three types of missingness: missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR).}, issn = {2088-5334}, publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development}, url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=14910}, doi = {10.18517/ijaseit.11.5.14910} }
EndNote
%A Zakaria, Samah %A Hafez, Mai Sherif %A Gad, Ahmed M. %D 2021 %T A Latent Class Model for Multivariate Binary Data Subject to Missingness %B 2021 %9 binary variables; latent class model; item non-response; non-random missingness; response propensity. %! A Latent Class Model for Multivariate Binary Data Subject to Missingness %K binary variables; latent class model; item non-response; non-random missingness; response propensity. %X When researchers are interested in measuring social phenomena that cannot be measured using a single variable, the appropriate statistical tool to be used is a latent variable model. A number of manifest variables is used to define the latent phenomenon. The manifest variables may be incomplete due to different forms of non-response that may or may not be random. In such cases, especially when the missingness is nonignorable, it is inevitable to include a missingness mechanism in the model to obtain valid estimates for parameters. In social surveys, categorical items can be considered the most common type of variable. We thus propose a latent class model where two categorical latent variables are defined; one represents the latent phenomenon of interest, and another represents a respondent’s propensity to respond to survey items. All manifest items are considered to be categorical. The proposed model incorporates a missingness mechanism that accounts for forms of missingness that may not be random by allowing the latent response propensity class to depend on the latent phenomenon under consideration, given a set of covariates. The Expectation-Maximization (EM) algorithm is used for estimating the proposed model. The proposed model is used to analyze data from 2014 Egyptian Demographic and Health Survey (EDHS14). Missing data is artificially created in order to study results under the three types of missingness: missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR). %U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=14910 %R doi:10.18517/ijaseit.11.5.14910 %J International Journal on Advanced Science, Engineering and Information Technology %V 11 %N 5 %@ 2088-5334
IEEE
Samah Zakaria,Mai Sherif Hafez and Ahmed M. Gad,"A Latent Class Model for Multivariate Binary Data Subject to Missingness," International Journal on Advanced Science, Engineering and Information Technology, vol. 11, no. 5, pp. 1832-1840, 2021. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.11.5.14910.
RefMan/ProCite (RIS)
TY - JOUR AU - Zakaria, Samah AU - Hafez, Mai Sherif AU - Gad, Ahmed M. PY - 2021 TI - A Latent Class Model for Multivariate Binary Data Subject to Missingness JF - International Journal on Advanced Science, Engineering and Information Technology; Vol. 11 (2021) No. 5 Y2 - 2021 SP - 1832 EP - 1840 SN - 2088-5334 PB - INSIGHT - Indonesian Society for Knowledge and Human Development KW - binary variables; latent class model; item non-response; non-random missingness; response propensity. N2 - When researchers are interested in measuring social phenomena that cannot be measured using a single variable, the appropriate statistical tool to be used is a latent variable model. A number of manifest variables is used to define the latent phenomenon. The manifest variables may be incomplete due to different forms of non-response that may or may not be random. In such cases, especially when the missingness is nonignorable, it is inevitable to include a missingness mechanism in the model to obtain valid estimates for parameters. In social surveys, categorical items can be considered the most common type of variable. We thus propose a latent class model where two categorical latent variables are defined; one represents the latent phenomenon of interest, and another represents a respondent’s propensity to respond to survey items. All manifest items are considered to be categorical. The proposed model incorporates a missingness mechanism that accounts for forms of missingness that may not be random by allowing the latent response propensity class to depend on the latent phenomenon under consideration, given a set of covariates. The Expectation-Maximization (EM) algorithm is used for estimating the proposed model. The proposed model is used to analyze data from 2014 Egyptian Demographic and Health Survey (EDHS14). Missing data is artificially created in order to study results under the three types of missingness: missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR). UR - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=14910 DO - 10.18517/ijaseit.11.5.14910
RefWorks
RT Journal Article ID 14910 A1 Zakaria, Samah A1 Hafez, Mai Sherif A1 Gad, Ahmed M. T1 A Latent Class Model for Multivariate Binary Data Subject to Missingness JF International Journal on Advanced Science, Engineering and Information Technology VO 11 IS 5 YR 2021 SP 1832 OP 1840 SN 2088-5334 PB INSIGHT - Indonesian Society for Knowledge and Human Development K1 binary variables; latent class model; item non-response; non-random missingness; response propensity. AB When researchers are interested in measuring social phenomena that cannot be measured using a single variable, the appropriate statistical tool to be used is a latent variable model. A number of manifest variables is used to define the latent phenomenon. The manifest variables may be incomplete due to different forms of non-response that may or may not be random. In such cases, especially when the missingness is nonignorable, it is inevitable to include a missingness mechanism in the model to obtain valid estimates for parameters. In social surveys, categorical items can be considered the most common type of variable. We thus propose a latent class model where two categorical latent variables are defined; one represents the latent phenomenon of interest, and another represents a respondent’s propensity to respond to survey items. All manifest items are considered to be categorical. The proposed model incorporates a missingness mechanism that accounts for forms of missingness that may not be random by allowing the latent response propensity class to depend on the latent phenomenon under consideration, given a set of covariates. The Expectation-Maximization (EM) algorithm is used for estimating the proposed model. The proposed model is used to analyze data from 2014 Egyptian Demographic and Health Survey (EDHS14). Missing data is artificially created in order to study results under the three types of missingness: missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR). LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=14910 DO - 10.18517/ijaseit.11.5.14910