Complete-case regression under conditional missing at random Created 2026-10-07 Updated 2026-11-05
Let indicate observation of a regression response , with fully observed predictors . If and on the target support, the observed conditional density equals the full conditional density. Thus a correctly specified regression model can be fitted to observed responses under conditional missing at random. This does not justify the unadjusted complete-case mean when observation rates and outcome means both vary with , nor does it imply missing completely at random.
Fitted values Created 2026-09-24 Updated 2026-10-14
Fitted values are the predictions at the predictor values used to fit a regression model. In linear regression with an explicit regression intercept,Here is the slope design matrix, and is the regression residual vector. The fitted values estimate the regression function at the observed predictors; they need not equal the observed responses, which may also contain random errors. Prediction at a new predictor vector uses with the same centering and scaling used in fitting. A prediction interval addresses uncertainty in a new response rather than just displaying this point prediction.
For the five constructed observations in linear regression, ordinary least squares gives fitted values . The ridge regression fit at instead gives . Both fitted vectors have sample mean because the regression intercept is unpenalized; their regression residuals differ and their residual sums of squares are and , respectively.
For ordinary least squares, the fitted values are the orthogonal projection of onto the column space of the complete design matrix, including its regression intercept column. They remain unique even in rank-deficient ordinary least squares, although the regression coefficients can be nonunique. The regression residuals are then orthogonal to every column.[ref]
Regression 1: Different perspectives. slides 6–10: fitted values, hat matrix, projection and orthogonal residuals
With centered slopes, ridge regression instead satisfies , so the regression residuals need not be orthogonal to the slope columns. Their sum is still zero because the regression intercept remains free.For fixed predictors and scales and a fixed positive penalty, ridge regression gives a linear smoother,For with at least one nonzero slope direction, this matrix is not an orthogonal projection matrix: applying it twice shrinks that direction again. Its effective degrees of freedom are , where are the positive singular values of ; the extra counts the free regression intercept. If the penalty is selected using , the resulting fitting rule need not be a linear smoother, since its chosen also depends on .
Homoscedasticity and heteroscedasticity 2026-10-14
These describe constancy or variation of conditional error variance across observations. A homoscedastic regression model has ; a heteroscedastic model allows this variance to depend on the observation or its covariates.
John Carlin 2026-11-05
John Carlin develops biostatistics for health and medical research, including methods for missing data and causal inference. His institutional profiles describe work on multiple imputation and the need to specify the scientific purpose of an analysis before choosing a regression model.[ref]
https://www.vicbiostat.org.au/people/john-carlin. Research interests, imputation and scientific practice
[ref]https://www.mcri.edu.au/researcher-details/john-carlin. Methodological research and applications
With multiple imputation, several plausible completed datasets represent uncertainty about unobserved values. Their analyses must account both for uncertainty within a completed dataset and for variation between completed datasets. This makes the assumptions about the missing values visible in the analysis. Carlin is a coauthor of Bayesian Data Analysis by Andrew Gelman and others.[ref]
Bayesian Data Analysis by Andrew Gelman and others. Third-edition author list and missing-data methods
John Carlin
. Portrait identified on the linked official researcher profile; photographer and licence are not asserted. Source. Past exam of the mathematics course of the University of Cambridge 2009 iii Paper 41 1 a Solution Created 2026-10-03 Updated 2026-10-14
Use separate randomization lists for women with and without a self-reported history of depression. Within each stratum, the central service could assign intervention and control in a ratio using randomly permuted blocks, preferably with concealed and varying block sizes. This is stratified randomization; the internet service can retain allocation concealment because the recruiting staff do not know the next assignment.
History is plausibly prognostic for the outcome. Keeping its distribution similar between arms reduces the risk of a chance imbalance in that important baseline factor and can improve precision. It also allows a comparison within each history stratum. Stratification does not guarantee balance of every other covariate, and staff must not be allowed to choose assignments. The regression model can retain history as a baseline covariate, respecting the design.
Regression analysis Created 2026-10-14 Updated 2026-10-20
Regression analysis studies how a response variable depends on explanatory variables through a regression model. It estimates that dependence and assesses uncertainty in fitted regression coefficients, predictions and model comparisons. Linear regression is one important case.
RNA integrity number 2026-11-05
The RNA integrity number is an algorithmic score of RNA integrity inferred from an electropherogram. Its original scale runs from 1 for strongly degraded preparations to 10 for high integrity. The method developed by Andreas Schroeder and colleagues combines several trace features using a trained neural network regression model, rather than using a single ribosomal-peak ratio.[ref]
The RIN: an RNA integrity number for assigning integrity values to RNA measurements by Andreas Schroeder and others. Abstract, Feature selection and Model training
The original apparatus separates RNA in microfluidic channels and detects it through fluorescence. The resulting electropherogram reports signal against migration time. Peak and region features summarize the size distribution; the trained model maps that feature vector to an integrity score.[ref]
The RIN: an RNA integrity number for assigning integrity values to RNA measurements by Andreas Schroeder and others. Techniques for measuring RNA integrity and Figure1
An original area calculation illustrates why a shape feature differs from total signal. If a selected region has integrated signal and the whole trace has in consistent units, its area fraction is . Multiplying every signal value by two gives . Adding signal in a different fragment-size region can instead change the fraction. This simple ratio is not the RNA integrity number algorithm; it illustrates how a trace can contain information distinct from total material.
Training a score also requires checking predictions on measurements not used for fitting. Table1 of the original study partitions 1339 electropherograms into 937 training and 402 test records.[ref]
The RIN: an RNA integrity number for assigning integrity values to RNA measurements by Andreas Schroeder and others. Table1: electropherogram counts
For a constructed error example, predicted scores and against labels and have mean squared error . That evaluates agreement with labels; it does not count intact molecules.An RNA integrity number of 8 therefore cannot be converted into an intact fraction or a universal assay-success probability. Its interpretation also requires the specimen type and intended analysis: bulk ribosomal RNA features do not directly certify every individual messenger RNA.
Rotatable design Created 2026-10-14 Updated 2026-11-05
A rotatable design for a specified regression model has variance of a fitted regression mean depending on only through its Euclidean distance from the design center. It concerns prediction precision, not rotational symmetry of the mean response itself.
For a full quadratic regression model in variables, consider all factorial corners, the axial points , and center runs giving a nonsingular information matrix of an experimental design. Sign symmetry cancels odd moments and permutation symmetry makes the second coordinate moments equal. Fourth-order rotational balance requires, for distinct ,The factorial corners contribute to both sums, axial runs contribute only to the first, and center runs contribute zero. Thus , givingFor , ; for , . Center replication can estimate pure error but does not change this fourth-moment equation. If a fractional factorial portion is used, its own moments and estimability must be checked; simply substituting the original factor count into the full-factorial formula is not justified. In one dimension rotational invariance only means reflection symmetry, so the distinct-coordinate fourth-moment equation does not impose the displayed choice.
Statistical model Created 2026-09-24 Updated 2026-11-05
A statistical model is a specified family of probability distributions for the observations. A statistical parameter often indexes it as , where is the parameter space. The choice states which patterns of variation are considered possible and supplies a basis for statistical inference; it does not guarantee that any member exactly describes the data-generating mechanism.
For example, suppose binary observations are independent and identically distributed with a common unknown success probability . The Bernoulli distribution model has and likelihood functionWith and seven successes, this becomes and is maximized at . The binary observation type alone does not supply independence or a common : those are additional model assumptions. A regression model can instead let the response law depend on observed covariates, while a mixed model represents a specified grouping structure through random effects.
