## biased sample!

Posted in Statistics with tags , , , , , , , , , , , on May 21, 2019 by xi'an

A chance occurrence led me to this thread on R-devel about R sample function generating a bias by taking the integer part of the continuous uniform generator… And then to the note by Kellie Ottoboni and Philip Stark analysing the reason, namely the fact that R uniform [0,1) pseudo-random generator is not perfectly continuously uniform but discrete, by the nature of numbers on a computer. Knuth (1997) showed that in this case the range of probabilities is larger than (1,1), the largest range being (1,1.03). As noted in the note, exploiting directly the pseudo-random bits of the pseudo-random generator. Shocking, isn’t it!  A fast and bias-free alternative suggested by Lemire is available as dqsample::sample

As an update of June 2019, sample is now fixed.

## visualising bias and unbiasedness

Posted in Books, Kids, pictures, R, Statistics, University life with tags , , , , , , , , , on April 29, 2019 by xi'an

A question on X validated led me to wonder at the point made by Christopher Bishop in his Pattern Recognition and Machine Learning book about the MLE of the Normal variance being biased. As it is illustrated by the above graph that opposes the true and green distribution of the data (made of two points) against the estimated and red distribution. While it is true that the MLE under-estimates the variance on average, the pictures are cartoonist caricatures in their deviance permanence across three replicas. When looking at 10⁵ replicas, rather than three, and at samples of size 10, rather than 2, the distinction between using the MLE (left) and the unbiased estimator of σ² (right).

When looking more specifically at the case n=2, the humongous variability of the density estimate completely dwarfs the bias issue:

Even when averaging over all 10⁵ replications, the difference is hard to spot (and both estimations are more dispersed than the truth!):

## no country for old biases

Posted in Books, Kids, Statistics with tags , , , , , on March 20, 2018 by xi'an

Following a X validated question, I read a 1994 paper by Phil Dawid on the selection paradoxes in Bayesian statistics, which first sounded like another version of the stopping rule paradox. And upon reading, less so. As described above, the issue stands with drawing inference on the index and value, (i⁰,μ⁰), of the largest mean of a sample of Normal rvs. What I find surprising in Phil’s presentation is that the Bayesian analysis does not sound that Bayesian. If given the whole sample, a Bayesian approach should produce a posterior distribution on (i⁰,μ⁰), rather than follow estimation steps, from estimating i⁰ to estimating the associated mean. And if needed, estimators should come from the definition of a particular loss function. When, instead, given the largest point in the sample, and only that point, its distribution changes, so I am fairly bemused by the statement that no adjustment is needed.

The prior modelling is also rather surprising in that the priors on the means should be joint rather than a product of independent Normals, since these means are compared and hence comparable. For instance a hierarchical prior seems more appropriate, with location and scale to be estimated from the whole data. Creating a connection between the means… A relevant objection to the use of independent improper priors is that the maximum mean μ⁰ then does not have a well-defined measure. However, I do not think a criticism of some priors versus other is a relevant attack on this “paradox”.

Posted in Books, Kids, Statistics, University life with tags , , , , , , , , , , on December 5, 2017 by xi'an

I am a PhD student in biostatistics, and an avid reader of your work. I recently came across this blog post, where you review a text on statistical paradoxes, and I was struck by this section:

“For instance, the author considers the MLE being biased to be a paradox (p.117), while omitting the much more substantial “paradox” of the non-existence of unbiased estimators of most parameters—which simply means unbiasedness is irrelevant. Or the other even more puzzling “paradox” that the secondary MLE derived from the likelihood associated with the distribution of a primary MLE may differ from the primary. (My favourite!)”

I found this section provocative, but I am unclear on the nature of these “paradoxes”. I reviewed my stat inference notes and came across the classic example that there is no unbiased estimator for 1/p w.r.t. a binomial distribution, but I believe you are getting at a much more general result. If it’s not too much trouble, I would sincerely appreciate it if you could point me in the direction of a reference or provide a bit more detail for these two “paradoxes”.

The text is Chang’s Paradoxes in Scientific Inference, which I indeed reviewed negatively. To answer about the bias “paradox”, it is indeed a neglected fact that, while the average of any transform of a sample obviously is an unbiased estimator of its mean (!), the converse does not hold, namely, an arbitrary transform of the model parameter θ is not necessarily enjoying an unbiased estimator. In Lehmann and Casella, Chapter 2, Section 4, this issue is (just slightly) discussed. But essentially, transforms that lead to unbiased estimators are mostly the polynomial transforms of the mean parameters… (This also somewhat connects to a recent X validated question as to why MLEs are not always unbiased. Although the simplest explanation is that the transform of the MLE is the MLE of the transform!) In exponential families, I would deem the range of transforms with unbiased estimators closely related to the collection of functions that allow for inverse Laplace transforms, although I cannot quote a specific result on this hunch.

The other “paradox” is that, if h(X) is the MLE of the model parameter θ for the observable X, the distribution of h(X) has a density different from the density of X and, hence, its maximisation in the parameter θ may differ. An example (my favourite!) is the MLE of ||a||² based on x N(a,I) which is ||x||², a poor estimate, and which (strongly) differs from the MLE of ||a||² based on ||x||², which is close to (1-p/||x||²)²||x||² and (nearly) admissible [as discussed in the Bayesian Choice].

Posted in Books, Statistics, University life with tags , , , , , , , , , , on October 27, 2016 by xi'an

In the March 2016 issue of JASA that currently sits on my desk, there is a paper by Liang, Jim, Song and Liu on the adaptive exchange algorithm, which aims at handling posteriors for sampling distributions with intractable normalising constants. The concept behind the algorithm is the exchange principle initiated by Jesper Møller and co-authors in 2006, where an auxiliary pseudo-observation is simulated for the missing constants to vanish in a Metropolis-Hastings ratio. (The name exchangeable was introduced in a subsequent paper by Iain Murray, Zoubin Ghahramani and David MacKay, also in 2006.)

The crux of the method is to run an iteration as [where y denotes the observation]

1. Proposing a new value θ’ of the parameter from a proposal q(θ’|θ);
2. Generate a pseudo-observation z~ƒ(z|θ’);
3. Accept with probability

$\dfrac{\pi(\theta')f(y|\theta')}{\pi(\theta)f(y|\theta)}\dfrac{q(\theta|\theta')f(z|\theta)}{q(\theta'|\theta)f(z|\theta')}$

which has the appeal to cancel all normalising constants. And the repeal of requiring an exact simulation from the very distribution with the missing constant, ƒ(.|θ). Which means that in practice a finite number of MCMC steps will be used and will bias the outcome. The algorithm is unusual in that it replaces the exact proposal q(θ’|θ) with an unbiased random version q(θ’|θ)ƒ(z|θ’), z being just an augmentation of the proposal. (The current JASA paper by Liang et al. seems to confuse augment and argument, see p.378.)

To avoid the difficulty in simulating from ƒ(.|θ), the authors draw pseudo-observations from sampling distributions with a finite number m of parameter values under the [unrealistic] assumption (A⁰) that this collection of values provides an almost complete cover of the posterior support. One of the tricks stands with an auxiliary [time-heterogeneous] chain of pseudo-observations generated by single Metropolis steps from one of these m fixed targets. These pseudo-observations are then used in the main (or target) chain to define the above exchange probability. The auxiliary chain is Markov but time-heterogeneous since the probabilities of accepting a move are evolving with time according to a simulated annealing schedule. Which produces a convergent estimate of the m normalising constants. The main chain is not Markov in that it depends on the whole history of the auxiliary chain [see Step 5, p.380]. Even jointly the collection of both chains is not Markov. The paper prefers to consider the process as an adaptive Markov chain. I did not check the rather intricate in details, so cannot judge of the validity of the overall algorithm; I simply note that one condition (A², p.383) is incredibly strong in that it assumes the Markov transition kernel to be Doeblin uniformly on any compact set of the calibration parameters. However, the major difficulty with this approach seems to be in its delicate calibration. From providing a reference set of m parameter values scanning the posterior support to picking transition kernels on both the parameter and the sample spaces, to properly cooling the annealing schedule [always a fun part!], there seems to be [from my armchair expert’s perspective, of course!] a wide range of opportunities for missing the target or running into zero acceptance problems. Both examples analysed in the paper, the auto-logistic and the auto-normal models, are actually of limited complexity in that they depend on a few parameters, 2 and 4 resp., and enjoy sufficient statistics, of dimensions 2 and 4 as well. Hence simulating (pseudo-)realisations of those sufficient statistics should be less challenging than the original approach replicating an entire vector of thousands of dimensions.

## automatic variational ABC

Posted in pictures, Statistics with tags , , , , , , , , , , on July 8, 2016 by xi'an

“Stochastic Variational inference is an appealing alternative to the inefficient sampling approaches commonly used in ABC.”

Moreno et al. [including Ted Meeds and Max Welling] recently arXived a paper merging variational inference and ABC. The argument for turning variational is computational speedup. The traditional (in variational inference) divergence decomposition of the log-marginal likelihood is replaced by an ABC version, parameterised in terms of intrinsic generators (i.e., generators that do not depend on cyber-parameters, like the U(0,1) or the N(0,1) generators). Or simulation code in the authors’ terms. Which leads to the automatic aspect of the approach. In the paper the derivation of the gradient is indeed automated.

“One issue is that even assuming that the ABC likelihood is an unbiased estimator of the true likelihood (which it is not), taking the log introduces a bias, so that we now have a biased estimate of the lower bound and thus biased gradients.”

I wonder how much of an issue this is, since we consider the variational lower bound. To be optimised in terms of the parameters of the variational posterior. Indeed, the endpoint of the analysis is to provide an optimal variational approximation, which remains an approximation whether or not the likelihood estimator is unbiased. A more “severe” limitation may be in the inversion constraint, since it seems to eliminate Beta or Gamma distributions. (Even though calling qbeta(runif(1),a,b) definitely is achievable… And not rejected by a Kolmogorov-Smirnov test.)

Incidentally, I discovered through the paper the existence of the Kumaraswamy distribution, which main appeal seems to be the ability to produce a closed-form quantile function, while bearing some resemblance with the Beta distribution. (Another arXival by Baltasar Trancón y Widemann studies some connections between those, but does not tell how to select the parameters to optimise the similarity.)

## the penalty method

Posted in Statistics, University life with tags , , , , , , , , , , on July 7, 2016 by xi'an

“In this paper we will make conceptually simple generalization of Metropolis algorithm, by adjusting the acceptance ratio formula so that the transition probabilities are unaffected by the fluctuations in the estimate of [the acceptance ratio]…”

Last Friday, in Paris-Dauphine, my PhD student Changye Wu showed me a paper of Ceperley and Dewing entitled the penalty method for random walks with uncertain energies. Of which I was unaware of (and which alas pre-dated a recent advance made by Changye).  Despite its physics connections, the paper is actually about estimating a Metropolis-Hastings acceptance ratio and correcting the Metropolis-Hastings move for this estimation. While there is no generic solution to this problem, assuming that the logarithm of the acceptance ratio estimate is Gaussian around the true log acceptance ratio (and hence unbiased) leads to a log-normal correction for the acceptance probability.

“Unfortunately there is a serious complication: the variance needed in the noise penalty is also unknown.”

Even when the Gaussian assumption is acceptable, there is a further issue with this approach, namely that it also depends on an unknown variance term. And replacing it with an estimate induces further bias. So it may be that this method has not met with many followers because of those two penalising factors. Despite precluding the pseudo-marginal approach of Mark Beaumont (2003) by a few years, with the later estimating separately numerator and denominator in the Metropolis-Hastings acceptance ratio. And hence being applicable in a much wider collection of cases. Although I wonder if some generic approaches like path sampling or the exchange algorithm could be applied on a generic basis… [I just realised the title could be confusing in relation with the current football competition!]