Issues of methods and interpretation in the National Cancer Institute formaldehyde cohort study.

continuous exposure relationship was quadratic, the continuous model including the unexposed subjects could yield a marginally statistically significant positive slope in conjunction with no apparent trend or a U-shaped relationship in the RRs across the four exposure categories.

also in 639 other papers

Also, given that these p-values are 2-sided and a large number of person-years were accrued in the FA-unexposed category, it is also possible that these p-values indicate a nearly statistically significant inverse trend.

also in 175 other papers