MIT's guide uses an illuminated vacuum photodiode, with collecting anode positive relative to the emitting cathode. A transimpedance amplifier gives ; a multimeter reads its mean. The fluctuation path rejects below , adds roughly tenfold voltage gain, then nominal hundredfold preamplification and a – band-pass filter; the readout measures root mean square voltage. With diode bias off, a sinusoid at the test port calibrates . Restore bias, retain gain settings, vary lamp brightness, and repeat both readings. The guide warns about overload; it supplies a procedure, not measured results.[ref]
Figure 1.
Functional photocurrent measurement: separate mean-current, fluctuation and calibration paths
. Original functional diagram organizing the laboratory's measurement roles; it is not a component-level circuit reproduction. includes current-to-voltage conversion and the complete fluctuation path. The dark comparison below is an additional control. Details.
The inference can be expressed without relying on nominal passband edges. Let denote the calibrated voltage transfer after the conversion, so and define . Under independent arrivals and an unchanged additive background,
The slope of voltage variance against mean electric current can therefore estimate . A free intercept accounts for a constant background; forcing the line through zero generally biases the slope. The root mean square readings must have their mean removed and then be squared. Subtracting two root mean square amplitudes does not subtract independent variances. Estimate the variance from successive records; averaging the waveforms first would suppress the fluctuation being measured.
Additional controls sharpen this interpretation. Block the light with detector bias, temperature, and gain unchanged; this preserves dark current and electronics while removing photocurrent. Repeat this dark comparison between illumination settings to check drift. If independent dark arrivals have mean magnitude and illuminated arrivals add , their spectra add: . Subtracting the unchanged dark variance isolates . This subtraction model assumes unchanged transfers and independence; switching off bias for gain calibration is a different control and need not preserve the dark background.
Vary measured rather than assuming lamp knob position is proportional to photocurrent. Check collection versus bias to identify a range where incomplete collection is negligible; a space charge limited tube can correlate transfers. Verify that the transimpedance amplifier remains linear and that its frequency response is unchanged over the illumination range. Changing signal bandwidth should change the excess variance through ; compare inferred input spectra in several bands. Correlated fluctuations of the light source can add a contribution scaling approximately as , while an electronics floor can hide the linear term at small electric currents. A fitted line over a short range alone does not establish independent transfers.
The gain calibration must include the same detector-to-readout path used for noise, or explicitly supply any omitted transfer. Detector capacitance, finite collection time, amplifier voltage and current noise, thermal electrical noise, pickup, clipping, and finite recording precision limit the inference. Current-dependent electrical impedance or heating can make a background current-dependent too. Since contains squared gain, a small fractional error in gain produces approximately twice that fractional error in the predicted variance scale. Knowing a nominal gain and two cutoff settings is insufficient.
Shot noise worked example Created 2026-10-18 Updated 2026-10-20
For an original model, set , , , , and the exponential low-pass filter's . Assume an ideal detector without charge multiplication and omit all additive noise for this calculation. Then
Doubling doubles the voltage variance and multiplies its standard deviation by . Halving also doubles the variance, provided the detector remains approximately white throughout the enlarged passband. Using in place of underestimates the variance by the factor . These are calculated predictions, not measured values or settings claimed for the laboratory below.
Figure 1. . Original exact model calculations, with no experimental trace. Left: Poisson distribution for mean count . Middle: normalized one-sided power spectral densities after an exponential low-pass filter. Right: count variance and normalized filtered-current variance versus their common normalized mean. Details.
To read the dimensionless figure, set and , with frequency in cycles per unit . A gate of duration has count mean and variance . The continuously filtered instead has
The count and the filtered electric current are different observables. The factor comes from the exponential weighting, not from non-Poisson arrivals. The dimensionless count illustration is a separate choice of rate; it does not assert that the example has only four electrons per .
Signal power Created 2026-10-24 Updated 2026-11-05
For a periodic signal, the mean squared magnitude over a period. Its units are the square of the signal's units: a voltage signal has mean-square power in . Physical electrical power in a resistive load additionally divides this quantity by electrical resistance. Subtracting the squared mean gives the variance of the signal over a uniformly sampled phase; the two quantities coincide for a zero-mean signal.
Sill of a semivariogram 2026-10-05
The sill is the large-distance level of a semivariogram when that limit exists. For covariance tending to zero, the sill is the total marginal variance; a nugget plus a structured component has total sill . A nonzero constant covariance component is invisible to the semivariogram.
Simple kriging Created 2026-10-05 Updated 2026-10-18
Simple kriging assumes a known mean function. If and are known, center the observations, predict the residual, and add back the target mean:
For known zero mean, these reduce to and . Completing the covariance quadratic form gives
which proves minimum error variance among predictors of the form . No sum-to-one constraint is needed: the known mean already supplies the offset. In the exponential example from ordinary kriging, imposing known zero mean gives weights , prediction , and error variance . The smaller error variance uses additional knowledge of the mean; it is not a free improvement when the mean is unknown.
If has a joint multivariate normal distribution, the displayed prediction is exactly , and is its conditional variance. A conditional expectation minimizes mean squared error among all square-integrable functions of the observations. Without a joint multivariate normal distribution, simple kriging remains the best predictor in the specified affine class, but the conditional expectation may be nonlinear and its conditional variance may depend on . Thus Gaussian process regression and the second-moment kriging construction agree under these assumptions, while having different starting points.[ref]
Simple linear regression Created 2026-09-24 Updated 2026-10-14
Simple linear regression uses one predictor and an intercept, , with . The regression coefficients describe a straight conditional-mean line: is its value at zero and its rate of change per unit of the predictor. When zero is outside the observed range, predictor centering can make the intercept refer to a more representative predictor value.
For fixed predictors and uncorrelated mean-zero errors of common variance , with ,
A larger predictor spread improves slope precision under this model. In the worked example and ; the estimated error variance is . A normal linear model gives the slope pivot a Student t-distribution with degrees of freedom. The distinction between a fitted line and a reliable uncertainty statement is precisely the role of the error assumptions.
Simple random sampling Created 2026-10-07 Updated 2026-10-14
Here simple random sampling means a random unordered subset of exactly distinct labels from , with every size- subset equally likely. The sample size is fixed in advance, , and sampling without replacement prevents duplicate units. This is SRSWOR; some texts also use "simple random sampling" for independent uniform draws with replacement, which is a different design.[ref]
Every label has inclusion probability , but equal inclusion probabilities alone are insufficient. For example, from six labels choose either or with probability . Each label is included with probability , yet eighteen of the twenty size-three subsets are impossible: this is a two-group cluster sampling design. Unequal probability sampling deliberately changes inclusion probabilities, often to improve precision for a particular estimand, and generally requires an appropriately weighted estimator rather than the plain sample mean.
Consider the original mathematical population with labelled values , and let . The fifteen equiprobable subsets, followed by their sample means, are
Their sample means sum to , giving expected value . Their squared deviations from sum to , giving variance . This is an enumeration over hypothetical selections from six stipulated numbers, not measured survey data.
Figure 1.
All fifteen size-two subsets and all thirty-six ordered replacement outcomes from six labelled values
. Details.
With independent uniform sampling with replacement, the ordered outcomes each have probability . The two orders and are distinct outcomes, and is now possible. Forgetting order does not make the resulting unordered multisets equiprobable: has probability but has probability . The thirty-six sample means still have expected value , but their squared deviations sum to , giving variance . Avoiding duplicate labels improves precision for this fixed population.
Simple random walk Created 2026-09-24 Updated 2026-10-14
A simple random walk on a locally finite graph chooses each vertex in the current vertex's graph neighbourhood with equal probability, assuming there is at least one available neighbour. On the integer line there are two choices, one unit left or right, so each has probability . This is the one-dimensional simple symmetric random walk. Terminology varies: a simple random walk on the integer line is also often allowed unequal step probabilities, with “symmetric” specifying the fair case.
For a simple symmetric random walk starting at , each increment has the Rademacher distribution, with expected value zero and variance one. Thus linearity of expectation and the variance of a sum of independent random variables give
For example, after steps the expected value is zero, the variance is , and the standard deviation is . Doubling the typical distance scale takes four times as many steps. This square-root growth explains why a random walk can wander far even when there is no preferred direction.
Figure 1.
Four fair and two biased unit-step random-walk paths, with their expected values and bands one standard deviation wide on either side.
Details.
The colored curves are illustrative sample paths, not averages over all possible walks. The dashed curves show the expected values; the shaded bands show the expected value plus or minus one standard deviation at each time. These bands are a scale of spread, not confidence intervals, and give no guarantee that an entire sample path stays inside them.
Zero expected value does not make this a stationary process: its one-time probability distribution changes with , as the increasing variance already proves. It does have stationary increments and independent increments, because blocks of fresh steps have the same probability distribution at any starting time and disjoint blocks use independent random variables. This separation of position from increment is one reason the random walk is such a useful first example of a stochastic process.
Simple random walk on the integer line Created 2026-09-24 Updated 2026-10-14
A simple random walk on the integer line starts at and takes independent and identically distributed random variables as unit increments, with
The simple symmetric random walk has ; a biased random walk has . At or every step is deterministic, giving or respectively.
Count the rightward steps using indicator functions:
Thus the endpoint is a shifted and rescaled random variable with a binomial distribution. For a worked example, at the endpoint means exactly three rightward steps and one leftward step. There are possible orders, so its probability is , equal to in the fair case. More generally the binomial coefficient counts the orders, giving the exact probability mass function
In particular, the endpoint must have the same integer parity as : . For the support of a probability distribution is exactly . At only even integers in are reachable; at only odd integers are reachable. This restriction is easy to lose if one draws a smooth curve instead of discrete probability masses. The fair-walk counting argument is also presented in Grinstead and Snell, Introduction to Probability, section 12.1.
Figure 1.
Exact binomial endpoint probabilities for fair walks of 20 and 80 steps and a biased walk of 80 steps; only even endpoints are possible.
Details.
The endpoint identity and the binomial distribution give the expected value, variance, and standard deviation
A short direct check gives and , hence . Then apply linearity of expectation and the variance of a sum of independent random variables.
The absolute width and the width relative to the number of steps answer different questions. In the fair case the standard deviation grows from to , while shrinks from to . At , the standard deviation is , or times the fair width, and . Centering and dividing by each walk's own standard deviation gives, for ,
This rescaling equalizes the variances, not the entire probability distributions. The spacing between reachable endpoints is two, so its rescaled spacing is : approximately for the fair -step walk, for the fair -step walk, and for the biased -step walk.
The positions themselves are dependent. For , , where the second term is independent of . Their covariance is therefore
For example, in the fair case allows or , whereas allows or . Nevertheless the position process is a Markov chain: given its current position, the next fresh increment has no dependence on its past. Its transition probabilities are
These transition probabilities are the same at every time and every integer position: shifting both and by the same integer leaves unchanged. Thus the Markov property and independent increments coexist with dependent positions.
Simultaneous wavelet coefficient noise bound Created 2026-10-14 Updated 2026-11-05
For coefficient weights and independent mean-zero sub-Gaussian random variables of parameter , put . Multiplying moment-generating-function bounds shows that the weighted noise has parameter . The exponential Markov inequality, optimized in its parameter, gives tail bound . At the displayed thresholds, a union bound over coefficients gives simultaneous control with probability at least . No coefficient independence is required. Integrated wavelet weights satisfy . Finite variance alone only supports the weaker Chebyshev choice .
Single-observation location minimax bound Created 2026-10-06 Updated 2026-11-05
For a known mean-zero noise law with finite variance , observing only with unrestricted has minimax risk under squared-error loss. The observation itself attains this risk. For the lower bound, use a flat prior distribution on and condition an easier experiment on . Away from the prior endpoints, the Bayesian posterior noise has its original truncated law. Let and then in the resulting Bayes risk lower bound. No normal distribution or density for the noise is required.
Skellam distribution Created 2026-10-14 Updated 2026-11-05
The distribution of for independent Poisson random variables with means is the Skellam distribution. Its characteristic function is , its mean is and its variance is . For equal means ,
This is the fixed-time law of a symmetric Poisson difference process.
// Target: markov-process.bigb
Skewness Created 2026-10-05 Updated 2026-11-05
For a real random variable with finite third absolute moment and positive variance , its skewness is . It is dimensionless and unchanged by positive rescaling or translation; a reflection reverses its sign. A symmetric distribution has zero skewness, but the converse fails: values with probabilities have mean zero and third moment zero without symmetry. Constant variables have no defined standardized skewness because . The cosmological reduced skewness uses a different normalization.
Skorokhod embedding theorem Created 2026-09-24 Updated 2026-10-03
The Skorokhod embedding theorem represents a centered probability distribution on the real numbers with finite variance as for a stopping time of Brownian motion. One may choose so that the stopped process is uniformly integrable and .
Slepian's lemma Created 2026-10-06 Updated 2026-11-05
For centered multivariate normal distributions represented by vectors with equal corresponding variances and for all distinct indices, for every threshold vector. In particular the supremum of is stochastically smaller than the supremum of . Equal corresponding variances are essential to this formulation. The related Sudakov-Fernique inequality compares expected values of maxima using variances of increments and does not require equal pointwise variances.
Slutsky theorem Created 2026-09-24 Updated 2026-11-05
If and for a deterministic constant , then . The continuous mapping theorem therefore gives
and when . No independence between the two sequences is required. The deterministic limit matters: convergence of two separate nondegenerate marginal distributions does not determine their joint limit.
For example, if with and , then wherever the denominator is defined. This justifies substituting a consistent estimator of asymptotic variance when constructing a Wald confidence interval.
Small-angle width of nematic orientation Created 2026-10-20 Updated 2026-11-05
For a narrow nematic liquid crystal orientation distribution about its unoriented nematic director, expand . This proves the displayed root-mean-square width. It does not determine the full distribution or a full width at half maximum. If the two small transverse tilt components are independent equal-variance Gaussians with variance , then , so .
Smoothed matter density variance Created 2026-10-06 Updated 2026-11-05
Let be the linear density contrast and its convolution with a normalized smoothing window function. For a statistically homogeneous and isotropic field with matter power spectrum ,
The variance is ; the root-mean-square fluctuation is its square root . The formula needs a convergent integral and does not require the field to be Gaussian.
For a spherical top-hat window function of comoving radius , the Lagrangian mass label is , where is the present mean matter mass density and . One therefore writes the same quantity as . This is the initially assigned mass scale, rather than the final physical radius of a collapsed halo. For scale-independent linear growth factor , scales as at fixed .
A collapse calculation must use a compatible smoothing window, epoch and barrier convention. Large extrapolated linear variance indicates that nonlinear evolution matters; it does not turn the linear spectrum into the true nonlinear density distribution. The eight-megaparsec density fluctuation amplitude is one particular present-day top-hat rms value.
Smoothing bandwidth Created 2026-10-05 Updated 2026-10-14
A smoothing bandwidth determines the scale over which a regression kernel averages data, or a kernel for density estimation spreads each observation. It has the same units as the observations. In kernel density estimation, changing changes the visible detail while preserving the total integral one. For a Gaussian density kernel, each bump has standard deviation and its individual contribution has peak height .
If the smoothing bandwidth is too small relative to the spacings in a statistical sample, the kernel density estimator shows narrow spikes tied to individual observations: apparent peaks may be sampling accidents. If it is too large relative to features of the unknown probability density function, it blurs distinct groups together and spreads fitted probability far from the observations. An intermediate smoothing bandwidth can reveal broad structure, but visual smoothness alone cannot establish accuracy.
Figure 1.
The same sample at three Gaussian bandwidths, and leakage below zero for a separate positive sample
. Details.
The first three panels use exactly with smoothing bandwidths , and , respectively. Every curve has area one; the two groups in the observed statistical sample become less distinct as increases. No true probability density function is specified in this illustration, so the middle panel is illustrative, not a certified optimal fit. The fourth panel uses and to illustrate boundary bias of a kernel density estimator.
For a fixed nonnegative kernel for density estimation with finite squared integral, a probability density function that is bounded and continuous at an interior point with , and a deterministic sequence , the pointwise sampling variance obeys
Thus decreasing the smoothing bandwidth increases the leading sampling variance while reducing interior smoothing bias of an estimator: this is a bias-variance tradeoff. The conditions and express two goals, increasingly fine resolution and enough observations contributing locally. Practical methods such as plug-in bandwidth selection use the data to choose ; pointwise optimal kernel bandwidth depends on local features of the unknown probability density function. The smoothing bandwidth remains a tuning choice in nonparametric statistics, and knowing the support of a probability distribution can require more than a width adjustment near a boundary.
The spectral-diffusion frequency-increment variance quantifies how much a transition frequency changes between two observation times. For a real stationary process with mean and autocovariance function ,
The mean increment is zero under these assumptions, so its second moment is also its variance. Expanding the square proves the identity: the two squared-frequency deviations each contribute and their cross term contributes .
If , then
For an original example with and , and the root-mean-square increment is about . The single-time frequency spread remains ; temporal decorrelation does not require the stationary distribution to broaden.
The long-time value assumes that the autocovariance function tends to zero. It is not a universal upper bound. For a random-phase sinusoid with phase uniform over a full cycle,
At half a cycle, the frequencies are anticorrelated and ; at a complete cycle the increment vanishes. Thus a nonmonotone increment statistic can reflect recurring frequency memory.
For nonstationary observations , the general identity instead is
Drift of the mean must not be silently assigned to stationary spectral diffusion. Likewise, under an explicit model of independent zero-mean endpoint measurement errors with variance , the observed second moment gains . This spectral frequency-increment measurement noise term changes when the endpoint errors are correlated.
Primary two-dimensional infrared spectroscopy work uses controlled frequency labeling and later readout to constrain frequency memory.[ref] The identity above is a model relation; a measured 2D IR center-line slope needs the stated response assumptions before it supplies .