Cite

    Raebel, M. A., Shetterly, S., Lu, C. Y., Flory, J., Gagne, J. J., Harrell, F. E., Haynes, K., Herrinton, L. J., Patorno, E., Popovic, J., Selvan, M., Shoaibi, A., Wang, X., & Roy, J. (2016). methods for using clinical laboratory test results as baseline confounders in multi‐site observational database studies when missing data are expected. Pharmacoepidemiology and drug safety, 25(7), 798–814. http://access.bl.uk/ark:/81055/vdc_100034749615.0x00002a