Table 2: Results of fitting a linear dose response using binary regression.

Dose masking schemeERRa
(per Gray)
Standard errorDevianceLR statistic
( 𝑃 value)
Relative bias (%)MSE

None0.52350.1548826.369.27 (0.0023)0.0240
Rounded to three decimal digits0.52370.1548826.359.28 (0.0023)0.0380.0240
Rounded to two decimal digits0.52350.1547826.359.28 (0.0023)00.0239
Rounded to nearest centiGray0.52350.1548826.369.27 (0.0023)00.0240
Rounded to nearest deciGray0.52280.1547826.369.27 (0.0023)0.130.0239
Stratifiedb0.53200.1553826.119.52 (0.0020)1.60.0242
Randomizedc
 ± 0.001 0.5235 0.1548 826.36 9.27 0.015 0.0240
  (min, max)(0.5234, 0.5238)(0.1548, 0.1549)(0.0023)(0, 0.057) (0.02397, 0.02398)
 ± 0.010.52390.155826.369.280.160.0240
  (min, max)(0.5226, 0.5266)(0.1548,0.1551)(0.0023)(0, 0.59)(0.02396, 0.02407)
 ± 0.10.52710.155826.339.311.60.0243
  (min, max)(0.5159, 0.5573)(0.1537,0.1584)(0.0023)(1.4, 6.5)(0.02415, 0.02557)

aERR: excess relative risk (relative risk—1). Precision is overrepresented for comparison.
bDoses were stratified according to the categories used in Life Span Study Report 13 [27]. The dose value assigned to each individual was the mean of all database AHS stomach dose values in that group.
cA random uniform deviate between the specified range was added to the dose; if this operation resulted in a negative value, the masked dose was set to zero. Results are the averages from 500 simulations.