On a cyclic sequence of independent Bernoulli random variables with success probability , count all runs of consecutive successes, allowing overlaps and taking . The count has expected value . Its variance is the displayed expression: each starting indicator has variance ; two starts at cyclic distance have joint probability ; nonoverlapping starts are independent. There are ordered overlapping pairs at each such distance, because the two ranges do not meet when .
For , summing a geometric series gives . Markov's inequality therefore proves absence with high probability when , and Chebyshev's inequality proves existence and relative concentration when . This remains valid for varying probabilities eventually at most one half.
Consider the explicitly specified objective
and estimate its derivative by a symmetric finite difference with step . The choice of shared or independent noise changes the estimator's variance even though both use correct normal distributions at the two parameter values.
With common random numbers, the same appears on both sides:
Thus and , independent of . Cancellation removes the noisy square term. For this quadratic, the symmetric difference has no truncation bias in exact arithmetic.
For independent standard normals , instead use
If , expand . The standard-normal moments , and give
Adding the two independent square variances and dividing by yields
Both estimators have the correct expected value , but the independent-noise variance diverges as tends to zero. At and , the variances are and . An average of independent replicate estimators divides each variance by .
This is a complete calculation for the stated quadratic, not a universal dominance theorem. At , and , the independent variance is , below the shared value . The covariance principle in common random numbers explains why coupling needs a specified objective and comparison. Very small steps in floating-point evaluation also introduce cancellation concerns that this exact-arithmetic model does not include.
Variance of hypothetical means Created 2026-10-06 Updated 2026-11-05
The variance of hypothetical means in the Bühlmann model is the between-risk variance of the conditional claim expected value. It creates the shared covariance between different years of the same risk and determines how much individual experience should influence the premium.
For pots per treatment and leaves per pot, the group sample mean decomposes into two averages:
The variance of a sum adds the variances of the independent terms. Every pot random effect has weight , whereas each remaining error has weight , giving the short proof
This is also the variance of the arithmetic mean of the pot sample means, each with variance . Equal numbers of leaves per pot make the two averaging procedures identical.
If all leaf measurements were falsely treated as independent, the predicted variance would instead be . The ratio of correct to false variance is
Thus pseudoreplication can underestimate a standard error by the square root of this ratio. Equality holds when or ; sharing a pot creates an error here precisely when the shared influence has positive variance.
Choose , , and as constructed model parameters in squared length units. These are assumptions rather than fitted experimental values. For each group,
The treatment contrast has expected value . Since the group errors are independent conditional on the allocation, its variance is twice the group variance, namely , whereas the false calculation gives . Its correct standard error is length units; the false value is . The variance ratio is .
Figure 1.
Constructed variance predictions: adding pots reduces uncertainty faster than adding leaf measurements within four pots
. Each curve uses and ; the horizontal axis counts measurements per treatment. The solid designs agree at four pots with three leaves each. The dashed curve assumes all measurements are independent and therefore illustrates pseudoreplication; none of the curves are observed experimental data. Details.
With four pots fixed, increasing drives the error contribution towards zero, but the limit of the group variance remains . Measuring twelve leaves on each of four pots gives . Using the same forty-eight measurements on sixteen pots, with three leaves per pot, gives . More independent experimental units reduce both contributions. Extra nested measurements are useful for characterizing each experimental unit, but cannot average away its shared random effect. This is why sample collection effort and the number of independent treatment replicates answer different questions.[ref]
Variance of the Watterson estimator Created 2026-10-14 Updated 2026-11-05
The moments of the mutation count on a neutral coalescent tree give this variance for . Since and the sum of inverse squares is bounded, it tends to zero. Together with unbiasedness, this gives mean-square convergence to the mutation parameter, so it is a consistent estimator.
Variance-stabilizing transformation Created 2026-10-14 Updated 2026-10-25
If a response has mean and variance , the delta method gives . Choosing proportional to makes this first-order variance independent of . For on positive means, the resulting transformation is the natural logarithm. This is a local approximation and requires the transformation to be defined on the observations; it does not make arbitrary normal responses positive or preserve an exact normal distribution.
Vector noise normalization in inertial Langevin dynamics Created 2026-10-14 Updated 2026-11-05
Let the physical viscous drag coefficient be in
For isotropic three-dimensional equilibrium Gaussian white noise, each force component has covariance . The random acceleration therefore satisfies
The factor six is twice the three Cartesian components. It agrees with the equipartition theorem, , and with damping rate . A one-component variance has factor two; a vector dot-covariance is the trace and has factor six. Stating whether a coefficient is a drag or a damping rate avoids a further factor-of-mass error.
The unnormalized autocorrelation function of a stationary velocity. For zero mean, is the velocity variance. It is different from the normalized autocorrelation function often used in time series.
If , integrating the two-time covariance over the square gives
This identity connects a mean squared displacement to the Green-Kubo formula for diffusion.
Velocity moments of an isotropic Mestel disk Created 2026-10-06 Updated 2026-10-14
The planar Mestel disk has , giving independent centered Gaussian distributions for with velocity dispersions . Its streaming velocity is zero. A maximally prograde stellar distribution instead has mean and azimuthal variance , while all second raw moments remain unchanged.
A vibrational frequency-frequency correlation function describes how deviations of a vibrational transition frequency at two times vary together. For a real stationary process with mean , define
This is an autocovariance function. It has squared-frequency units, and is the variance of the frequency fluctuations. If , the normalized quantity starts at one. Normalizing removes the fluctuation amplitude, so two systems can have the same but different .
Vibrational spectral diffusion is the associated evolution of transition frequencies in their changing molecular surroundings. Decay of their correlation need not mean loss of vibrational population.
An original exponential example is
With and , and , while . The mean transition frequency has not been specified by these fluctuation parameters.
The function also connects a frequency model with coherence decay. For a zero-mean classical Gaussian process, neglect population loss and other broadening, and let accumulated phase be . Its Gaussian average gives
For the exponential model,
Thus the chosen example has and coherence factor about . These are stipulated model values, not an experimental fit.
The 2007 primary analysis relates vibrational spectral diffusion to changing 2D IR line-shape correlation. Three controlled infrared pulses label an initial frequency and later read out the response, with the intervening 2D IR waiting time varied.[ref] A measured 2D IR center-line slope can constrain such dynamics under appropriate response approximations; it is not a direct time trace of each molecule's frequency. Vibrational relaxation and instrumental effects need separate consideration.
A vibrational frequency-state residence time is the duration a probe remains in a defined frequency environment before leaving it. It differs from the time over which the probe's frequency retains statistical memory, and from a vibrational relaxation lifetime describing excitation loss.
For a state with constant exit rate , let be the probability of no exit by time . The small-interval exit model gives
The residence-time density is , with mean and variance . The exponential distribution is memoryless: . These conclusions require a constant-rate model, rather than following from the name of a spectral state alone.
For a two-state continuous-time Markov chain with A-to-B rate and B-to-A rate , the mean residence times are and . The normalized two-state vibrational frequency memory instead decays as . Returning after an exit contributes to occupancy and correlation but not to survival without an exit.
An original symmetric example uses . Mean residence time is , while frequency-memory time is . Starting in A, the probability of being in A after is
whereas no-exit probability is . At these are about and .
This produces vibrational residence-time sampling bias if a same-state observation is treated as proof that no exit occurred. Using as an exit-rate estimate gives about , below the stipulated . Faster time sampling can resolve more excursions, but the estimator must still account for missed transitions and state-assignment uncertainty.
In two-dimensional infrared spectroscopy, the 2D IR waiting time separates initial frequency labeling from later response readout. Primary response theory relates such measurements to frequency memory under explicit approximations.[ref] A fitted memory decay is therefore not automatically a directly measured single-state residence time. Nonexponential survival can require additional states, time-dependent rates or a different physical model.
For data , known complex source template , real amplitude , and known noise covariance , generalized least squares gives the displayed amplitude. This convention takes in the quadratic objective ; factors of two in the amplitude variance depend on whether complex-component or real-component covariance is used. Source position, shape and contaminants must be fitted or marginalized when uncertain. An extended-source complex visibility template accounts for resolved-out flux rather than assuming the source is unresolved.
For fixed particle number and temperature, a bubble with surface tension and area has effective availability . Its stationary condition is . Its curvature is . Positive curvature is required for stable Gaussian fluctuation approximation. The variance follows from availability curvature and equilibrium fluctuations. For an ideal gas, the restoring denominator becomes for positive . Treating the internal pressure as externally fixed instead of fixing the gas particle number changes the stability problem.
Waiting time to observe both Bernoulli outcomes Created 2026-10-14 Updated 2026-11-05
In independent trials with two outcomes of probabilities and , let include the first trial and the trial that first completes the pair. Conditional on the first outcome, has a geometric distribution of parameter or , with mixture weights . The law of total expectation and law of total variance give
The final term in the unsimplified variance is the variance of the two conditional means; omitting it is incorrect unless . Both outcomes must have positive probability for these finite formulas.
Wald statistics with a shared control Created 2026-10-06 Updated 2026-11-05
Independent normal arm means with variances give treatment-contrast Wald test statistics whose correlation coefficient is . The common control mean creates positive dependence between comparisons.
Wall-clock slack in saturation-limited Raman frame allocation is time that remains unused when a fixed number of detector frames has already reached its permitted exposure caps. With pump-on/off pairs, per-frame cap and readout time per frame,
assuming . The integer frame-count choice under a Raman saturation limit compares these possibilities over different pair counts. Slack at fixed does not imply that the continuous exposure allocation was optimized incorrectly.
If , both states can use their full live totals , and the shot-noise relative variance is . Increasing only the wall-clock allowance cannot improve it: the marginal value of unused time below a Raman frame cap is zero in this capped regime. Another frame pair changes both the overhead and the allowable division of live time.
For an original example, set , , and . The live time is , readout uses , and slack is . With and , equal capped totals give .
Three pairs increase readout time to , leaving only live time. Yet the larger per-state cap permits the preferred ratio two to one: and . Their variance is , lower despite less total live time. Relieving the weak state's cap outweighs the extra readout cost in this chosen model.
The primary Raman apparatus limited exposures to avoid detector saturation and alternated pump state during shuttered readout.[ref] The timings above are separate illustrative choices. Read noise, sample drift and switching constraints can change the comparison; unused time and useful precision are different optimization quantities.
Wavelet regression estimator Created 2026-10-14 Updated 2026-11-05
At design sites , let be the step function taking response on . Project it onto an interval-adapted wavelet basis through resolution . Each coefficient is . Its expectation is the corresponding coefficient of the step function of sampled regression means. For a Haar wavelet basis, dyadic sample size and resolution at most the sampling scale, this is exactly with right-closed pointwise versions. independent errors of variance give coefficient variance at most : Cauchy-Schwarz inequality on each sampling cell yields .
Weak law of large numbers Created 2026-09-24 Updated 2026-10-14
Let be real independent and identically distributed random variables with and expected value . The weak law of large numbers states that their sample mean has convergence in probability to : for every fixed ,
Thus a large sample is unlikely to give an average with a specified fixed-size error. The strong law of large numbers makes the stronger statement of almost sure convergence along an entire sequence. Under the displayed assumptions both laws apply; their names distinguish the conclusions, not two competing predictions.
When the variance is finite, variance additivity for independent random variables gives . The Chebyshev inequality immediately supplies a useful quantitative form and a brief proof:
For independent trials with a Bernoulli distribution of parameter , the expected value is and the variance is . At , the chance of an error of at least is therefore at most . The exact binomial distribution gives a much smaller probability, as the figure under the strong law of large numbers shows. The bound is conservative, but it is valid for every sample size under these assumptions and does not require a normal approximation.
The weak law of large numbers addresses a fixed tolerance . The central limit theorem instead resolves errors on the shrinking scale and gives their approximate normal distribution. In particular, the weak law of large numbers alone supplies neither a bell-shaped error law nor a universal rate of approach. For example, a Pareto distribution with minimum one and shape has expected value three but infinite variance: both the weak law of large numbers and strong law of large numbers apply, while the finite-variance statement of the central limit theorem does not.
Weakly stationary process Created 2026-09-28 Updated 2026-10-14
A real stochastic process is a weakly stationary process if it has finite second moments, a constant expected value , and an autocovariance depending only on the lag of a time series:
In particular its variance is the same at every time, . This is often called second-order stationarity. It makes observations from different parts of a record comparable through the same autocorrelation function. Bartlett uses this second-order meaning of stationarity in Introduction to Time Series Analysis, lecture 2: mean, covariance, and stationarity.
For a worked contrast, let be centered white noise of variance . The process has mean , variance , and zero autocovariance at nonzero lags, so it is weakly stationary. The process has exactly the same covariance structure, but its mean is , so it is not weakly stationary. Constant variance alone is insufficient.
Weak stationarity need not imply strict stationarity. For example, choose independent random variables at all integer times, using a standard normal distribution at even times and a Rademacher distribution at odd times. Every coordinate has zero mean and unit variance, and distinct coordinates have zero covariance. Nevertheless a shift by one changes the marginal probability distribution from continuous to two-point. This also illustrates why weak white noise need not be identically distributed.
Weibull distribution Created 2026-09-24 Updated 2026-11-05
The two-parameter Weibull distribution is a positive lifetime model with shape and scale . Its Probability density function and Survival function are
Its Cumulative distribution function is . The Hazard function is : it decreases for , is constant for , and increases for . This permits decreasing or increasing failure rates within one family.[ref]
The mean is and the variance is . The substitution reduces the power-moment integrals to gamma integrals. At the law is exponential with rate ; at its survival is .
Inverse transform sampling is explicit: for uniform on , take . Conditional survival after an already attained age is , which depends on unless . This is why an Unknown entry age in a Weibull survival segment affects the likelihood. The scale parameter here is ; inverse-scale parameterizations instead use its reciprocal.