Complex surveys play an important role in providing critical information for policy makers as well as the general public. Surveys and survey data are also widely used in many scientific areas, such as public health and social science research. How to best handle missing data in surveys has been one of the focal points of research in the past three decades, with the ultimate prize in achieving reliable and efficient use of information from complex surveys. Most household and social surveys around the world are experiencing higher refusal rates leading to appreciable amounts of missing data. Dropout or noncompliance in clinical trials may also lead to missing responses for some subjects. Missing data tend to induce biases and inefficient estimates. In the past two decades, there has been an extensive development of new methods and procedures to deal with missing data.
The proposed spring school is part of the activities of the Collaborative Research Team (CRT) on Statistical Inference for Complex Surveys with Missing Observations funded by the Canadian Statistical Science Institute (CANSSI). The spring school is envisioned as providing training for graduate students, postdoctoral fellows, statisticians working in the industry (for example, Statistics Canada) and young researchers interested in the topic of missing survey data. This training program is also designed to provide useful background and the current state-of-the-art research outputs on analysis of survey data with missing observations for students and postdoctoral fellows involved in the CANSSI CRT project. It is hoped that the spring school will serve as a starting or enhancing point for young statisticians to equip themselves with tools for analyzing missing survey data and to pursue research in this evolving field of both theoretical and practical importance.