2D IR slope-axis convention 2026-11-05
A 2D IR slope-axis convention specifies which frequency coordinate is held fixed when taking spectral slices, which coordinate supplies each slice maximum, and which coordinate is plotted vertically. It also specifies whether the reported 2D IR center-line slope is that geometric slope or its inverse. These choices are needed before comparing slopes from two-dimensional infrared spectroscopy experiments or software.
Let be an excitation-frequency offset and a detection-frequency offset. An original positive bivariate normal distribution envelope with widths and correlation coefficient has conditional maximaThe first relation maximizes over at fixed ; the second maximizes over at fixed . They trace different lines unless the distribution is degenerate. Changing the slicing direction is not the same operation as taking the reciprocal of an already fitted line's slope.
For , and in matching frequency units, the first slope is 1.2. The second conditional slope is 0.3. Plotting that second set of maxima with vertical gives geometric slope ; its inverse is 0.3, not 1.2. Both sets came from the same stipulated band.
The 2007 primary method takes cuts parallel to the initial-frequency axis and defines its reported quantity through an inverse-slope convention. Its relationship with a vibrational frequency-frequency correlation function is established within the paper's response approximations.[ref]
Frequency-frequency correlation functions and apodization in two-dimensional infrared vibrational echo spectroscopy: A new approach by Kyungwon Kwak and others. Abstract and §II.B, center-line construction and inverse slope
A generic graphing routine's slope label does not identify that observable.Units can change a geometric slope without changing the underlying correlation coefficient. Under coordinate scalings and , a fitted slope becomes . Expressing only the vertical axis in GHz instead of THz multiplies its numerical slope by 1000. Using the same conversion on both axes leaves the slope unchanged. Reciprocal wavelength coordinates require their own transformation rather than a constant rescaling over an arbitrary bandwidth.
Report axis labels, units, slice direction, fit range and inversion convention with the result. At in the ideal envelope, the maxima at fixed lie on : that line is vertical even though its inverse slope tends to zero. A failed finite geometric fit near this limit need not mean molecular frequency memory increased. Noise, overlapping signed bands and finite fitting ranges require separate checks.
Bivariate normal distribution Created 2026-09-24 Updated 2026-11-05
A bivariate normal distribution is a multivariate normal distribution with two coordinates. It is determined by means , positive standard deviations , and correlation coefficient . For it has joint probability densityOne construction uses independent standard normal variables : set and . This verifies the means, variances and covariance , and also explains the limiting cases. At the law is supported on a line and has no two-dimensional Lebesgue density. At the density factors into its marginal normal densities and the coordinates are independent.
Each conditional law is normal: has mean and variance . For example, equally scaled standardized variables with correlation have conditional variance , quantifying the uncertainty left after observing the first coordinate.
Bivariate probit model for endogenous treatment Created 2026-09-28 Updated 2026-11-05
A bivariate probit model for a binary treatment and outcome uses latent equationswhere has a bivariate normal distribution. Its correlation parameter represents dependence between the two latent disturbances; when nonzero, treatment is endogenous in the outcome equation.
Bivariate standard normal distribution Created 2026-09-24 Updated 2026-11-05
A Bivariate standard normal distribution is a bivariate normal distribution whose two marginal means are zero and marginal variances are one; its remaining parameter is their correlation.
Gaussian Gibbs sweep autocorrelation 2026-10-14
In a systematic Gibbs sampler for a standardized bivariate normal distribution with correlation , update conditionally on the old , then update using the new . Substitution gives the displayed autoregressive process of order one, with independent noises with the standard normal distribution . The sweep-to-sweep autocorrelation of at lag is , so the chain mixes slowly as approaches one.
Kyungwon Kwak 2026-11-05
Kyungwon Kwak is a chemist working on ultrafast time-resolved spectroscopy of molecular systems. The Institute for Basic Science directory identifies his Korea University chemistry affiliation, Stanford doctorate and research in molecular dynamics. The primary 2007 paper gives the same full byline.[ref]
Kyungwon Kwak profile at the Institute for Basic Science. People search, Kwak, Kyungwon, Information and Research interests
Kyungwon Kwak, Sungnam Park, Ilya J. Finkelstein and Michael D. Fayer coauthored the 2D IR center-line slope method. Their paper defines its slope convention through maxima of frequency-axis slices; that convention matters when converting a plotted geometric slope into a dynamical observable.[ref]
An original bivariate normal distribution gives a transparent geometric example. Let be a centered, scaled horizontal frequency and a centered, scaled vertical frequency. For , take a positive model bandAt each fixed , maximize over . Differentiating the exponent gives . If , the line of maxima has geometric slope , while its inverse is . If , the maxima lie on the vertical line : the geometric slope is unbounded, while the inverse tends to zero. Exchanging axes changes which quantity is called the slope.
This model explains an axis convention; it is not a derivation of the full nonlinear optical response. A measured spectrum can contain homogeneous broadening, overlapping bands, finite-pulse effects and noise. Its fitted line need not be the correlation coefficient of a Gaussian probability distribution. The vibrational frequency-frequency correlation function requires the spectroscopic model that connects molecular fluctuations with the measured band.
The contribution also addresses interferogram apodization: multiplying time-domain data by a window function before the Fourier transform. The paper's stated symmetry and axis restrictions are essential, rather than a guarantee that arbitrary filtering preserves molecular information.[ref]
Frequency-frequency correlation functions and apodization in two-dimensional infrared vibrational echo spectroscopy: A new approach by Kyungwon Kwak and others. Abstract and Introduction, symmetric apodization along the selected axis
Useful processing must retain the observable being interpreted, not merely make the image look smoother.Kyungwon Kwak, portrait explicitly named on the Institute for Basic Science center's Steering Committee page
. For a Poisson process, the count and Poisson arrival time have the displayed inequality at every deterministic . A large count and a late arrival reflect opposite directions of the same fluctuation.
Here is a proof from independent increments. If , write with independent of . Conditional on , the event has probability , a nondecreasing function of . The event has a nonincreasing indicator function . For any random variable and an independent copy , oppositely monotone bounded functions satisfyTaking proves the claim. If , condition instead on ; then is nonincreasing in and is nondecreasing, giving the same inequality.
The inequality is preserved under joint convergence in distribution when the marginal distributions of the limit are continuous. Consequently, a limiting bivariate normal distribution with standard normal marginal distributions cannot have positive correlation coefficient. For , conditioning on makes , so , contradicting the inequality. For , that quadrant has probability , which also contradicts it.
Past exam of the mathematics course of the University of Cambridge 2003 iii Paper 42 1 iii Solution Created 2026-10-03 Updated 2026-10-14
Under the unrestricted model, insert the maximum-likelihood estimates . Under the diagonal-covariance restriction, the quadratic form is minimized over the mean at , and the remaining objective separates over the diagonal entries:Differentiating in gives ; the derivative changes from negative to positive there. Put . The fitted trace term is under either model, since . Consequently the likelihood-ratio test statistic is determined byThis is the Gaussian diagonal-covariance likelihood-ratio test. Reject for sufficiently small , equivalently for large . Under the regular large-sample calibration, Wilks theorem gives , since diagonality removes that many free covariance parameters. The exact critical constant can instead be obtained from the null distribution at the actual sample size.
For , write the sample correlation coefficient as . Then , so the likelihood-ratio test rejects for large , not merely for large positive . Under the null, the two variables have a bivariate normal distribution and are independent, and the exact test isIndeed, condition on the centered first-variable observation vector. Decompose the second centered Gaussian vector into its component along that direction and the -dimensional orthogonal complement. Their squared lengths give independent and variables. Their ratio shows that has Student's t-distribution with statistical degrees of freedom.
Past exam of the mathematics course of the University of Cambridge 2009 ia Paper 2 3F a Solution Created 2026-09-24 Updated 2026-10-14
With and , the bivariate normal distribution has probability density functionThe strict correlation bound makes its covariance matrix positive definite, so this is an ordinary two-dimensional density rather than a distribution supported on a line.
Past exam of the mathematics course of the University of Cambridge 2009 iii Paper 40 5 b Solution 2026-10-14
At , complete the square:For fixed , all factors not involving enter its conditional normalizing constant. Interchanging the roles of the coordinates givesThese are the full conditional distributions of the standard bivariate normal distribution with correlation .
A systematic Gibbs sampler starts at a chosen and, at each sweep, draws independent standard normals and setsThe second update uses the newly drawn . Both coordinate updates preserve the target by part (a), hence so does the sweep. The Gaussian two-coordinate Gibbs recursion is explicitlyan AR(1) recursion with innovation variance . Its stationary variance is one, and its correlation at sweep lag is , displaying the dependence of the sample.
The printed general- expression has a separate normalization defect: for its integral is , not one, since the exponent has covariance , whose normalizing denominator is . Retaining that exponent requires in the prefactor. The requested target is already normalized, so this defect does not alter the conditional distributions above.
Past exam of the mathematics course of the University of Cambridge 2010 ia Paper 2 12F a Solution Created 2026-09-24 Updated 2026-10-14
The nonsingular bivariate normal distribution has and . Put and . Completing the square givesConsequently the joint probability density function factors asFor fixed , the second factor is a normalized normal distribution density in , with mean and standard deviation . Its integral is one; explicitly substitute in the Gaussian integral. Thus the marginal density is
Past exam of the mathematics course of the University of Cambridge 2010 iii Paper 33 6 Solution Created 2026-10-03 Updated 2026-10-14
For the expectation-maximization algorithm, let . At iteration , the E-step forms the conditional distribution of the missing data at the current parameter and the functionThe M-step isIn this maximization the conditional distribution defining the expectation is held at the old parameter; it is not recomputed as varies. The Jensen inequality givesby writing the likelihood function ratio as a conditional expectation of . Hence an exact M-step does not decrease the observed-data likelihood function. The algorithm does not in general guarantee convergence to its global maximum; initialization and the likelihood function's geometry matter.
For the specified diagonal bivariate normal distribution, use . The two coordinates are independent, as are the four observations. Therefore the known second coordinate of the fourth observation gives no information about its first coordinate conditional on the parameters. The E-step isThese two moments suffice for the complete Gaussian log-likelihood. Discarding terms independent of the proposed parameters, its conditional expectation isDifferentiating with respect to each mean gives four times that mean minus the corresponding expected sum of observations. Thus the updates in EM for an independent missing normal coordinate areFor either variance the remaining criterion is ; its derivative vanishes at , which is its maximum when . Evaluate the expected residual sum at the new means to obtainThe missing contribution isIts first term is essential. Substituting only the imputed mean for would omit its uncertainty and would not maximize the required expected complete log-likelihood.
As a check, the observed-data likelihood function integrates out the missing first coordinate, leaving three first-coordinate and four second-coordinate normal densities. Put and . The first-coordinate recurrence impliesThus the iterates converge to the three-observation mean and maximum-likelihood variance, while the second-coordinate estimates are reached after one update. If the observed values in a coordinate are all equal, its likelihood function instead has a zero-variance boundary degeneracy, and there is no positive-variance maximizer; the variance formulas then describe that boundary limit. For nonzero empirical spreads the displayed updates give the ordinary nonsingular EM iteration.
Past exam of the mathematics course of the University of Cambridge 2014 iii Paper 32 1 c Solution Created 2026-10-03 Updated 2026-10-06
Write , , and let be independent standard normal random variables obtained by centering and scaling the separate stage means. ThenThe second statistic uses all patients, so the statistics are correlated even though the stages' new observations are independent. Their covariance is and each variance is one. This gives the exact bivariate normal distributionUnder the null hypothesis both means are zero. At replace by ; the mean vector is . In this group sequential design the full-sample statistic may be viewed as a potential statistic from the underlying sequence of outcomes, even on paths where recruitment stops.
Past exam of the mathematics course of the University of Cambridge 2014 iii Paper 32 1 d Solution Created 2026-10-03 Updated 2026-10-25
Set . Under the null hypothesis rejection requires both and . Since has the standard normal distribution,The bivariate normal distribution in the preceding calculation has a nonsingular covariance matrix and strictly positive statistical probability density everywhere. For every finite futility boundary and , the open rectangle has positive probability. ThereforeFor an explicit expression, conditional on the full-sample statistic is under the null hypothesis, yieldingThe type I error is reduced because some otherwise rejecting paths stop for futility. Equality is approached as , but does not hold at a finite futility boundary.
Past exam of the mathematics course of the University of Cambridge 2016 iii Paper 207 1 c Solution Created 2026-10-03 Updated 2026-10-25
Let denote the centered unit-variance bivariate normal distribution density,The complement of rejecting either null hypothesis is . Therefore the probability of at least one rejection isWhen both null hypotheses are true, this is the familywise error rate. If one null hypothesis is false, a rejection of that hypothesis is not a type I error, so the displayed probability is then an any-rejection probability rather than the familywise error rate.
Past exam of the mathematics course of the University of Cambridge 2016 iii Paper 207 1 d Solution Created 2026-10-03 Updated 2026-10-25
Couple the Wald test statistics as , where the joint centered bivariate normal distribution of is fixed. Increasing either enlarges, pointwise in this coupling, the event . Its probability is consequently nondecreasing in each treatment effect.
If both null hypotheses hold, then , so this probability is maximal at the joint boundary . To check the familywise error rate across all configurations, suppose only hypothesis is true. A type I error then occurs only if , with probability at most , where is the standard normal distribution function. This is no larger than the any-rejection probability at , since that joint event contains . If neither null hypothesis is true, the familywise error rate is zero. Hence the least-favourable null configuration for type I error iswhere is the centered bivariate normal distribution function with correlation coefficient .
Past exam of the mathematics course of the University of Cambridge 2019 ia Paper 2 11F a i Solution 2026-09-29
For every ,The right-hand side is a normal random variable by the definition of a bivariate normal distribution. Therefore every linear combination of the coordinates of is normal, so .
The correlation measures dependence between two normalized latent disturbances; it is not a scale-free measure of the strength of one physical confounder. Different latent-variable constructions can induce the same while producing different treatment-outcome confounding, and the same omitted cause can produce different after changing thresholds or disturbance scales. Moreover, re-estimating at each value of changes the entire latent model, so the fitted models do not represent one fixed data-generating mechanism with only its confounder strength varied. At the bivariate normal distribution is singular as well. Varying is a model-based sensitivity analysis, but interpreting the interval as an ordered range of strengths of a single unmeasured confounder is therefore logically unjustified.
