Scientific corroboration 2026-10-25
Karl Popper's appraisal of a conjecture's survival of demanding tests relative to accepted basic statements. It is a retrospective methodological assessment, distinct from a proof of truth or an inductive probability of truth.[ref]
The Logic of Scientific Discovery by Karl Popper. Sections 82–84
Scoring rule Created 2026-10-07 Updated 2026-10-14
A scoring rule turns a probability distribution forecast and an observed outcome into a number. For example, a forecast of rain with probability should express uncertainty more usefully than a bare prediction of rain. A scoring rule lets us compare such forecasts after observations arrive, and its choice determines whether exaggerating confidence pays. A proper scoring rule rewards an honest account of uncertainty in expected value.
There are two sign conventions. A reward is maximized; a loss function is minimized. The conversion reverses every comparison. Here the linear probability score is a reward, while the binary Brier score and the negative logarithmic scoring rule are losses. Calling all three a "score" without specifying the direction would hide the central difference.
Throughout the binary examples, the random variable has a Bernoulli distribution with actual success probability , and the report assigns probability to and to . The value is stipulated by this statistical model; it is not inferred from data or a claim that a forecasting system is calibrated. In practice the true predictive distribution is unknown, and the relevant is the conditional probability of success given the information available when the forecast is issued. Propriety evaluates incentives for reporting that predictive distribution; it does not supply the unknown probabilities.
Scott Sheffield Created 2026-10-13 Updated 2026-11-05
Scott Sheffield authored probability teaching material on conditional expectation, random walks and martingales. Conditional expectation supplies the common language for predictions given partial information and for processes whose current state is the best conditional prediction of a later value.[ref]
18.175 Lecture 16: Conditional expectation, random walks, martingales by Scott Sheffield. author attribution and the described mathematical development
Portrait of Scott Sheffield
. Via Wikimedia Commons; credits and usage information are on the linked source file page. Source. Secant-slope existence criterion for an adjustment coefficient Created 2026-10-06 Updated 2026-11-05
For positive claims with finite nonzero expected value , the function is continuous and strictly increasing on the positive finite-transform domain, starting at . If diverges at a finite upper endpoint, or is finite for all positive arguments, the secant slope tends to infinity. In the latter case use for some of positive tail probability. Every target with positive relative safety loading therefore has exactly one positive root.
Second-moment bound for positivity 2026-10-14
For a nonnegative random variable with positive expected value and finite second moment, write . The Cauchy-Schwarz inequality giveswhich proves the bound in second moment method. It is the zero-threshold case of the Paley-Zygmund inequality. Equality occurs when is a fixed positive value on the event and zero elsewhere, almost surely. For with a Bernoulli random variable of parameter , equals the exact positivity probability.
The variance identity turns the lower bound into a statement about variance relative to the squared mean. A small ratio forces positivity to be likely. A positive expected value alone does not do so: keeping while taking with probability and zero otherwise makes the positivity probability as small as any chosen .
Second moment bound for spectral truncation Created 2026-10-07 Updated 2026-11-05
For a fixed mean-zero variance-one real entry law, centered truncation of a Wigner matrix satisfies , where . The spectral Lipschitz bound from Frobenius distance and Markov inequality give probability at most for a spectral test-function discrepancy exceeding . Thus works uniformly in matrix size. A varying entry-law family requires uniform second-moment tail decay instead.
Second moment method Created 2026-09-24 Updated 2026-10-14
The second moment method uses a random variable's expected value and second moment to establish that a counted or measured quantity is positive with substantial probability. It is useful when a positive average alone could be caused by extremely large values on very rare outcomes. Controlling the variance rules out too much of that concentration in rare outcomes.
For a nonnegative random variable with and finite second moment, the second-moment bound for positivity givesEquivalently, . The method also includes the simpler Chebyshev's inequality bound . Thus a sequence of such random variables with has with probability tending to one. These statements require no independence assumption. The variance argument and its use for random counts are developed in Zhao's lecture notes. [ref].
For an original toy count, let count successes in ten independent Bernoulli trials with success probability . The binomial distribution givesConsequently . The exact probability is . The first moment method and union bound only give the upper bound here. First and second moments therefore answer complementary existence questions.
The second moment method certifies a positive count, while statistical dependence can change the conclusion despite an unchanged mean
. Left: exact binomial distribution probabilities of at least one success and second-moment lower bounds for ten independent trials as the success probability varies. Right: the same ten trials with either occur independently or share one common Bernoulli outcome. Both counts have mean one, but the perfectly linked count has much larger variance and only probability of being positive. All data are original specified probability models. Details.For a sum of indicator random variables, the variance of a sum isIndependence makes the covariances vanish, but the formula itself also covers dependent counts. For the same ten success probabilities, let every trial share a single Bernoulli random variable : then , with mean one, variance nine, and . The second-moment lower bound is exactly . Ignoring the positive covariances would produce the false independent-count conclusion. Zhao's discussion of sums of indicators explains why overlapping counted structures require these pairwise terms. [ref]
https://ocw.mit.edu/courses/18-226-probabilistic-methods-in-combinatorics-fall-2022/mit18_226_f22_lec06-07.pdf. Zhao, MIT 18.226, §4.1: indicator covariances and Bernoulli counts
. Section induction for the Talagrand exponential moment Created 2026-10-14 Updated 2026-11-05
Let the largest last-coordinate section have probability , and another section probability . Mix mismatch vectors from these two sections with weights . Their squared norm is at most . Hölder's inequality and induction bound that section's exponential integral by . The scalar estimate for Talagrand product induction makes it at most . Average over sections and use with to close the induction.
Selection model for publication bias 2026-10-07
A selection model combines a distribution for all study results with a probability that a result becomes available. The observed distribution is reweighted by this probability and renormalized. Assumed or estimated selection mechanisms permit sensitivity analysis of a meta-analysis, but unavailable results generally prevent a fully assumption-free correction.
Self-averaging Created 2026-10-05 Updated 2026-11-05
A sequence of observables is self-averaging when its fluctuations relative to its typical macroscopic size vanish as the system grows. One common criterion for nonzero means is , which implies in probability by Chebyshev's inequality. For independent and identically distributed variables with mean and finite variance , the sample mean has relative variance . Strong dependence or broad tails can prevent this reduction; increasing size alone is not a proof.
Self-decomposable distribution Created 2026-10-25 Updated 2026-11-05
A probability distribution is self-decomposable if, for every , an independent remainder can be chosen so that the displayed equality in probability distribution holds. A normal distribution admits a normal distribution remainder with mean and variance . For an exponential distribution of rate , choose with probability and otherwise an independent exponential distribution of rate . Its moment-generating function is ; multiplication by proves the claim using the uniqueness theorem for moment-generating functions.
Semi-log plot 2026-10-18
A semi-log plot uses a logarithmic scale on one axis and a linear scale on the other. Which axis is logarithmic matters. Plotting against makes positive exponential functions appear as straight lines; plotting against instead makes an affine function of a logarithm appear straight. The plotting operations change positions while retaining the original tick values.[ref]
Log scale. Matplotlib 3.10.7 documentation; Matplotlib 3.10.7, Log scale: Convenience functions semilogx, semilogy, and loglog; distinction between horizontal and vertical logarithmic axes
Take the original dimensionless mathematical model for . It has exponential growth, with , , and . Taking a base-ten logarithm givesThe slope in these transformed positions is , although the original relative growth rate is . Equal steps of two in multiply by . The corresponding ordinary gains increase, so the left plot bends while the right plot is straight.
The same exponential growth model bends on a linear scale and is straight on a semi-log plot with a logarithmic vertical axis
. Original exact mathematical model , not measurements. Both panels show identical values at the same . Right-hand tick labels retain the original values, with equal gaps for each doubling. The stated slope is for , not the original derivative . Details.One practical use is checking a proposed exponential distribution for failure times. For rate and , its cumulative distribution function is , so the reciprocal survival function satisfies . Estimated probabilities can therefore be placed on a logarithmic vertical axis and compared with a straight line. Agreement supports compatibility with the chosen statistical model; a roughly straight finite sample does not establish a unique physical mechanism.[ref]
8.2.2.1. Probability plotting. NIST and SEMATECH e-Handbook of Statistical Methods, §8.2.2.1 Probability plotting: Exponential Model, logarithmic vertical-axis transformation and interpretation of approximate straightness
Semimartingale stability under an absolutely continuous measure change Created 2026-10-05 Updated 2026-10-07
If is a semimartingale under and , then it is a semimartingale under . The Bichteler-Dellacherie theorem gives a short proof: terminal elementary integrals associated with uniformly small elementary predictable processes with stopping-time intervals converge to zero in -probability. Uniform convergence on compacts in probability under an absolutely continuous measure change, or its single-random-variable proof, transfers convergence to . The same good-integrator characterization now applies under . Adaptedness and càdlàg paths are preserved because -null sets remain -null; if necessary use the usual -completion of the same filtration. If the integrands are bounded only outside -null sets, clip their coefficients to the specified deterministic bounds before applying the -criterion; this preserves their -versions. Completion adds only equivalent versions of measurable coefficients. This theorem does not preserve the local martingale property.
Sensitivity analysis for unit and item nonresponse Created 2026-10-14 Updated 2026-11-05
Vary the unobserved outcome probabilities for item and unit nonresponders, and any unknown auxiliary-variable mixture, over scientifically plausible ranges. Recompute the population estimate and identify values at which substantive conclusions change. This probes untestable transport or missing at random assumptions; it is distinct from sampling uncertainty represented by a confidence interval. Letting each missing-outcome probability vary from zero to one gives worst-case identification bounds.
Sensitivity index 2026-10-25
Under an equal-variance Gaussian evidence model, is separation of signal and noise means in units of their common standard deviation. A yes/no task gives , where and are hit and false-alarm probabilities. This formula assumes the model; it does not define every possible sensory-discrimination measure.
Separation chain for two labels in a circular transposition shuffle Created 2026-10-14 Updated 2026-11-05
Place six positions on a cycle and distinguish two labels. At each step choose one of the fifteen unordered pairs of distinct positions uniformly and transpose their contents. This convention excludes identity moves. The shorter circular distance between the distinguished labels takes values . Cycle symmetry and exchangeability of the other labels make this distance a Lumped Markov chain.
Counting transpositions gives the transition matrix and Stationary distributionThe stationary weights also follow by counting unordered position pairs: six pairs have distance one, six have distance two, and three are opposite. If has every row equal to , then and . Starting with adjacent labels, the Probability of opposite labels after steps is therefore .
The parent Random transposition shuffle uses a different convention: two positions are sampled independently, allowing an identity move with Probability . Under that convention the distance transition matrix is , and the opposite-label Probability is . Explicitly stating the sampling convention prevents a spurious change in the convergence rate.
Separation in logistic regression 2026-10-14
Complete separation means that a predictor direction strictly separates the binary outcomes as displayed. In logistic regression, replacing by increases each observed-outcome probability as increases, so the log-likelihood has no finite maximizer. Weak inequalities with some equalities can similarly produce quasi-complete separation. Finite coefficient estimates and ordinary information-matrix inference therefore require an existence check rather than relying only on the formal score equations.
Sequential Bayesian photon counting 2026-10-18
Consider an original balanced-readout model, rather than a fit to the experiment. Let , with a normalized prior probability and . A detected chemical atom has outcome . Define the conditional probabilitiesHere is the accumulated quantum phase per photon, the controlled analysis quantum phase, and the fringe contrast. The two probabilities sum to one for every . Actual calibration may also require an offset and asymmetric detection errors; alone does not specify a quantum instrument.
Assume no photon number change during the record and fresh independently prepared atomic meters. For observed outcomes at recorded settings , the Born rule and Bayes' theorem giveThe posterior probability is defined only for . Summing its numerator over proves normalization. This is also the update of diagonal elements of a field density operator under a measurement in quantum mechanics; it does not assume that an initial quantum superposition was an unknown pre-existing integer. The observed settings are part of the record, especially when selected adaptively.
For an exact finite example take , , and . An outcome at has likelihood , giving . Another at gives . A subsequent at givesThus three atomic records raise the posterior probability of from to , while leaving finite uncertainty. No one of these outcomes identifies with certainty.
The periodic likelihood function imposes an identifiability limit. If for an integer , then for every setting: the posterior odds between and never change. Varying can resolve a cosine reflection ambiguity within a period, but cannot remove this exact period. Changing can supply additional information. A finite cutoff is therefore a physical assumption to justify, not evidence that excluded high photon numbers were absent. At no outcome changes the prior probability; at neither binary outcome has an exactly zero likelihood.
The no-loss assumption also has a time limit. In an original zero-temperature loss model, let . A Fock state loses its first photon at rate , so its survival probability is and its mean lifetime is for . Several records must be acquired within that lifetime to identify a plateau. When losses matter, first predict using a normalized transition matrix, then apply the atomic Bayesian inference update to . Thermal excitation requires upward transitions too. A delayed or broadened inference after a jump need not indicate that an atom caused the jump.
Sequential normal predictive monitoring Created 2026-10-14 Updated 2026-11-05
For repeated independent measurements with prior and known scales, normal-normal conjugacy gives and . The next measurement has posterior predictive distribution . Its one-sided conditional posterior-predictive false-alarm level yields the displayed limit; this is a per-measurement probability, not a simultaneous false-alarm guarantee across repeated monitoring. Predictive width tends to the irreducible measurement width, while the center adapts to the individual's data. To assess a held-out measurement, fit with earlier measurements only.
Sequential qubit measurement correlation Created 2026-10-25 Updated 2026-11-05
Prepare , measure a Pauli observable , apply a fixed unitary operator , then measure again. If the first and second eigenvalue labels are , their joint probability is . ConsequentlyThe first outcome has probability and its conditional state is by the Lüders rule. Summing times the joint probabilities and using proves the trace formula. This temporal correlation differs from the spatial correlation of two simultaneously measured qubits.



