Home > Publications . Search All . Browse All . Country . Browse PSC Pubs . PSC Report Series

PSC In The News

RSS Feed icon

Miller et al. find benefits of Medicaid for pregnant mothers in 1980s carry over two generations

Starr's findings account for some of the 19% black-white gap in federal sentencing

Frey says suburbs are aging, cities draw millennials

More News

Highlights

Bailey et al. find higher income among children whose parents had access to federal family planning programs in the 1960s and 70s

U-M's campus climate survey results discussed in CHE story

U-M honors James Jackson's groundbreaking work on how race impacts the health of black Americans

U-M is the only public and non-coastal university on Forbes' top-10 list for billionaire production

More Highlights

Next Brown Bag

Mon, Jan 22, 2018, noon: Narayan Sastry

Analysis of Multivariate Missing Data With Nonignorable Nonresponse

Publication Abstract

Tang, G., R. J A Little, and Trivellore Raghunathan. 2003. "Analysis of Multivariate Missing Data With Nonignorable Nonresponse." Biometrika, 90:747-764.

We consider multivariate regression analysis with missing data in the outcome variables, when the nonresponse mechanism depends on the underlying values of the responses and hence is nonignorable. Related problems include response-biased sampling where data are sampled with probability depending only on the univariate response. Our methods do not require specification of the form of the nonresponse mechanism. We show that, under certain regularity conditions, all the regression parameters can be identified from a conditional likelihood based on the complete cases, if the marginal distribution of the covariates is known. If the marginal distribution of the covariates is estimated from the data, then the regression parameters are identified from a pseudolikelihood resulting from substituting the estimated marginal distribution of the covariates in the above conditional likelihood. Simulation studies suggest that the pseudolikelihood method is approximately unbiased. In order to identify the model parameters, usually the dimension of the covariates and observed responses is required to be at least as large as the dimension of the missing responses. The method can also be modified to handle partial information about the missing-data mechanism. We also consider the special case where the missing data have a monotone pattern, where better use of the incomplete information can be made under certain assumptions.

Browse | Search : All Pubs | Next