Bioequivalence and Bioavailability Forum

Baseline correction GeoMean and Median [Regulatives / Guidelines]

posted by mittyri – Russia, 2024-11-11 12:20 (20 d 05:51 ago) – Posting: # 24271
Views: 1,607

Hi BEQool,

❝ why is geomteric mean not 0 if one of the values is 0 (or BLQ)? Are only positive values included in the calculation of geometric mean? I know that log(0) cannot be calculated but on the other hand value of 0 could be included in the calculation of geomean (equation: n-th root of the product of n values) and the geomean would be 0 regardless of other values.

While intuitively, you might think that the geometric mean of a set containing 0 should be 0 (since any product involving 0 is 0), the formal definition and intended purpose of the geometric mean don't align well with this interpretation.
Imagine 2 datasets:
c(1,1,1,1,0)
c(0,0,0,0,1)

Then both will have the same geometric mean value. It loses information about the other values and doesn't accurately reflect the "typical value" or "average rate" that the geometric mean aims to represent.

❝ We are currently studying an endogenous compound for which the endogenous baseline samples mostly below BLQ or slightly higher are expected. What is preferred for the time-averaged method in this case, to take the geometric mean or the median? In case the median is used, are BLQ values replaced with 0 not taken into account when calculating median as shown above (similar to geomean calculation)?

Regarding geometric mean: kind of tricky taking into account the information above. The median is better, but why don't you want to follow the method mentioned in BE GL at the first place (arithmetic mean)? Yes, it is bad, but at least not worse than others

❝ We were also wondering, if the pre dose sample at 0 h timepoint can be simultaneously considered as for detection of baseline concentration and also as the first PK sample? I would say that it can be used and the pro of this is that you dont have to take one more sample as well (in connection with the total volume of blood taken). On the other hand, one could argue that the same value will be taken into account twice; e.g. if we take the median for time-averaged method and this timepoint at 0h is the median, then baseline correction for the first pharmacokinetic sample would be 0 as the same value would be subtracted.

"one could argue that the same value will be taken into account twice" - employing the arithmetic mean instead would effectively mitigate this potential issue, even if it were to arise (though I believe it's unlikely given that all prerequisites are met, and the extra sample appears to be an unnecessary use of resources).

Complete thread:

• Baseline correction vs non-baseline cor­rection jag009 2015-09-15 20:29 [Regulatives / Guidelines] 
  • Baseline correction vs non-baseline correction Lucas 2015-09-16 14:16
    • Baseline correction vs non-baseline correction Relaxation 2015-09-18 10:25
  • Baseline correction or supra-thera­peu­tic dose Helmut 2015-09-16 15:16
    • Baseline correction or supra-thera­peu­tic dose Ohlbe 2015-09-16 17:55
      • Baseline profile prior to each period? Helmut 2015-09-16 18:15
      • Baseline correction examples Helmut 2015-09-17 15:44
        • Baseline correction examples Lucas 2015-09-18 14:19
          • Baseline correction examples Helmut 2015-09-18 17:28
            • Baseline correction examples Mauricio Sampaio 2016-02-07 03:05
              • Baseline correction examples Lucas 2016-02-10 11:48
                • Postmenopausal women Helmut 2016-02-10 12:26
                • Baseline correction examples Mauricio Sampaio 2016-02-11 01:38
                • Baseline correction examples Dr_Dan 2016-02-11 09:22
                  • Postmenopausal women Mauricio Sampaio 2016-02-12 03:24
                    • Postmenopausal women Dr_Dan 2016-02-15 17:45
            • Baseline correction examples BEQool 2024-11-11 07:34
              • Baseline correction GeoMean and Medianmittyri 2024-11-11 11:20
                • Geometric mean? Helmut 2024-11-11 14:53
                  • Geometric mean? BEQool 2024-11-14 08:19
                    • Geometric mean ≈ MLE of median Helmut 2024-11-14 09:54
                      • Geometric mean ≈ MLE of median Mahmoud 2024-11-15 11:26
                        • Bias? Helmut 2024-11-16 08:43
                          • Bias? Mahmoud 2024-11-16 11:12
      • Baseline; another example Helmut 2015-09-18 17:16
        • Baseline; another example nobody 2016-02-12 09:10
          • Baseline; another example Helmut 2016-02-12 13:37
            • Baseline; another example nobody 2016-02-12 14:08
              • Slowly going OT: BE study simulations Helmut 2016-02-12 15:47
                • Slowly going OT: BE study simulations nobody 2016-02-12 16:15
                  • Religious debate Helmut 2016-02-12 17:04
                    • Religious debate nobody 2016-02-12 17:26
                      • Religious debate ElMaestro 2016-02-13 12:53
                        • Religious debate nobody 2016-02-14 15:23
                • Slowly going OT: BE study simulations Ohlbe 2016-02-13 13:10
                  • Slowly going OT: BE study simulations Helmut 2016-02-13 15:02
                    • Slowly going OT: BE study simulations lizhao 2016-02-25 17:31
                      • Business as usual Helmut 2016-02-25 17:44
                        • Business as usual lizhao 2016-02-25 17:59