Approximation to Multivariate Normal Higher Dimensional Probabilities in Mixed - Data Model with Missing Responses
Multivariate data with mixed ordinal and continuous responses with the possibility of nonignorable missingness are often common in follow up social studies and their analysis need to be promoted. One of the standard methods of analysis is based on joint modelling. In this method, we use that simultaneously allow modelling non-ignorable mechanism and a full likelihood-based approach is used to obtain maximum likelihood estimates of parameters of joint modelling. In this approach, when the dimension of the vector responses are increased, includes somehow troubling computations which are often time-consuming. Another alternative is an approximation for multivariate normal probabilities for higher dimensional regions, based conditional expectations in joint modelling. A comparison between approximation method and full likelihood-based approach is used to obtain maximum likelihood estimates of parameters of joint modelling. To illustrate the utility of the proposed model, a large data set excerpted from the British Household Panel Survey (BHPS) is analyzed. For these data, the simultaneous effects of some covariates on life satisfaction, income and the amount of money spent on leisure activities per month as three mixed correlated responses are explored.
Samani, E. B.
Approximation to Multivariate Normal Higher Dimensional Probabilities in Mixed - Data Model with Missing Responses,
Applications and Applied Mathematics: An International Journal (AAM), Vol. 13,
1, Article 2.
Available at: https://digitalcommons.pvamu.edu/aam/vol13/iss1/2