We often are faced with the situation in which we have trend data for predictor variables and trend data for outcome variables, but the predictor and outcome variables are not linked at the level of the individual survey participant.
Missing data in predictor variables also do not cause bias in analyses of complete cases if the reasons for the missing data are unrelated to the outcome.
In case of substantial missing data in predictor variables leading to power loss in the multivariable analysis, the technique of multiple imputation for dealing with missing data will be applied.
Data on predictor variables were nearly complete (<4% missing) for all variables except arterial blood gases, albumin and blood urea nitrogen which were missing in 70%, 68% and 11% of cases.
Hayashi's Quantification II is a method of multivariate discrimination analysis to manipulate attribute data as predictor variables.
This was then used alongside the other GP data derived predictor variables to calculate the risk scores.
Of the 1285 participants screened in the Bellville South cohort, 383 were excluded because of missing data on predictor variables or renal function.
Since it uses only the covariate information associated with the missingness but ignores the correlation among variables, it may produce badly biased estimates of regression coefficients when data on predictor variables are missing.
Developing a model with many variables, in the presence of missing data, when predictor variables include not only main effects but also interactions that are not pre-selected, presents a challenge, and not extensively reported in the literature.
For the weekly incidence data, the predictor variables used were past incidence rate, rainfall, day temperature, night temperature, NDVI, EVI, SSTA, and SOI, where each had 13 weekly values (i.e., weeks T-12, T-11, …, T-1, T).
