[300-500 kcal’s generally touted for muscle preservation for those not on steroids by the internet, but that’s still pretty slow and not obvious weightloss against a backdrop of fluctuating water weight]
It is obvious if you weigh yourself every day for a couple months or longer and you know how to do stats.
(FWIW, my weight since 12 February fits to a straight line a + bx where a = (93.74 ± 0.19) kg, b = (−0.018 ± 0.007) kg/day, and x is the time elapsed since 12 February; the RMS of residuals is 0.68 kg. Approximating the posterior pdf of b as a Gaussian, which ought to be close enough given 46 degrees of freedom, I’m 99.42% sure that b < 0.)
Haha, well yeah. Though you should hardly need stats if you’re recording over a period of months (“golly, I wonder if my 40 lb weight change these past 6 months is just me being dehydrated right now? Maybe I should wait till after I drink my morning 4 gallons just to be sure”). I meant it more on time scales of “between 1 week and 2 weeks”, or for where weight loss was very minor due to a tiny caloric deficit.
With more precise measurement (eg, via bodpod) of body composition you would better be able to track smaller changes, too.
I suspect you’re basically correct, but I would not take the stats results at face value. There are many possible problems resulting from the physical and electrical properties of the scale you’re using, that I would not expect to be well behaved in a stats sense. In particular: quantization errors, non-linearity / non-monotonicity of the scale A/D converter (depends strongly on type of A/D used), temperature dependence of both the scale strain gauges and A/D, etc.
The general rule here is that trying to get too many more bits of precision out of a measuring device than it is intended to provide is tricky.
You could calibrate the scale in a number of ways; easiest would probably be to check that it gives consistent readings over time for a fixed weight that’s not too small compared to you. You could simply weigh the fixed weight, or you could weigh you and (you + weight).
You’re right, any time-varying systematic error (due to temperature, ageing of the scale, etc.) would screw up the analysis. (Quantization errors shouldn’t matter that much so long as they’re much smaller than day-to-day fluctuations.)
It is obvious if you weigh yourself every day for a couple months or longer and you know how to do stats.
(FWIW, my weight since 12 February fits to a straight line a + bx where a = (93.74 ± 0.19) kg, b = (−0.018 ± 0.007) kg/day, and x is the time elapsed since 12 February; the RMS of residuals is 0.68 kg. Approximating the posterior pdf of b as a Gaussian, which ought to be close enough given 46 degrees of freedom, I’m 99.42% sure that b < 0.)
Haha, well yeah. Though you should hardly need stats if you’re recording over a period of months (“golly, I wonder if my 40 lb weight change these past 6 months is just me being dehydrated right now? Maybe I should wait till after I drink my morning 4 gallons just to be sure”). I meant it more on time scales of “between 1 week and 2 weeks”, or for where weight loss was very minor due to a tiny caloric deficit.
With more precise measurement (eg, via bodpod) of body composition you would better be able to track smaller changes, too.
Excellent point.
I suspect you’re basically correct, but I would not take the stats results at face value. There are many possible problems resulting from the physical and electrical properties of the scale you’re using, that I would not expect to be well behaved in a stats sense. In particular: quantization errors, non-linearity / non-monotonicity of the scale A/D converter (depends strongly on type of A/D used), temperature dependence of both the scale strain gauges and A/D, etc.
The general rule here is that trying to get too many more bits of precision out of a measuring device than it is intended to provide is tricky.
You could calibrate the scale in a number of ways; easiest would probably be to check that it gives consistent readings over time for a fixed weight that’s not too small compared to you. You could simply weigh the fixed weight, or you could weigh you and (you + weight).
You’re right, any time-varying systematic error (due to temperature, ageing of the scale, etc.) would screw up the analysis. (Quantization errors shouldn’t matter that much so long as they’re much smaller than day-to-day fluctuations.)