Statistics — Page 13
Explore statistical methods, their assumptions, interpretation and limitations.
Research field
Method family
Cultural Consensus Model
The cultural consensus model is a latent-structure measurement framework that estimates the culturally shared answers to a set of questions and, simultaneously, how much each informant knows, without the researcher knowing the correct answe...
DCC-GARCH
DCC-GARCH is Engle's (2002) multivariate volatility model that lets the correlations between several assets change over time. A separate univariate GARCH model is fitted to each series, and then the dynamic correlation matrix is estimated i...
DCC-GARCH model
The DCC-GARCH model, introduced by Engle (2002), extends univariate GARCH to capture time-varying correlations between multiple financial time series. It decomposes the multivariate conditional covariance matrix into individual volatility p...
DCC-MIDAS
DCC-MIDAS combines dynamic conditional correlation (DCC) GARCH with mixed-frequency data sampling (MIDAS), enabling estimation of time-varying correlations between variables when observations arrive at different frequencies. Introduced by E...
DF-GLS Test
The DF-GLS test, introduced by Elliott, Rothenberg, and Stock (1996), is a modified augmented Dickey-Fuller procedure that applies generalized least squares (GLS) detrending before the standard unit-root regression. By removing deterministi...
DIF Analysis
Differential Item Functioning analysis examines whether examinees from different groups — such as gender, ethnicity, or language background — who have the same underlying ability respond differently to a test item. First formalised by Holla...
DSGE Model
A DSGE model is a micro-founded macroeconomic general equilibrium model that combines the optimising decisions of households, firms, and government under rational expectations. Popularised for empirical policy work by Smets and Wouters (200...
Debit Valuation Adjustment
Debit Valuation Adjustment (DVA) represents the value of your own credit risk to counterparties. DVA measures the gain in derivative value if you default on your obligations—a benefit for your shareholders because creditors receive less tha...
DeepHit
DeepHit is a deep neural network framework for survival analysis with competing risks. Introduced by Lee et al. in 2018, it extends DeepSurv to handle settings where multiple, mutually exclusive events can occur, such as disease-specific mo...
DeepSurv
DeepSurv is a deep neural network approach to survival analysis that learns personalized survival distributions directly from data. Introduced by Katzman et al. in 2018, it extends the Cox proportional hazards model using deep learning to c...
Demand System Estimation
Demand system estimation jointly models how a consumer or population allocates a budget across a complete set of goods, estimating a system of equations — one per good — that relate each good's expenditure share or quantity to all prices an...
Descriptive Statistics
Descriptive statistics is a set of procedures that numerically and visually summarises the essential characteristics of a dataset: central tendency (mean, median, mode), spread (standard deviation, interquartile range), shape (skewness, kur...
Desistance Analysis
Desistance analysis models the process by which offenders cease offending — estimating the timing of the last offense, the hazard of termination, and the decline of offending toward zero. Sharpened by Laub and Sampson and by Bushway and col...
Diamond-Mortensen-Pissarides Search-Matching
The Diamond-Mortensen-Pissarides (DMP) model, developed by Peter Diamond, Dale Mortensen, and Christopher Pissarides in the early 1980s, is a fundamental framework for understanding labor market dynamics through the lens of search and match...
Diebold-Mariano Test
The Diebold-Mariano (DM) test, introduced by Diebold and Mariano in 1995, is a widely used non-parametric procedure for formally comparing the predictive accuracy of two competing forecasting models. It evaluates whether the difference in f...
Difference GMM
Difference GMM, introduced by Arellano and Bond (1991), estimates dynamic panel data models by first-differencing the equation to remove fixed effects, then using lagged levels of the endogenous variables as GMM instruments. It is the stand...
Difference-in-Differences
Difference-in-Differences is a causal-inference method that estimates the effect of an intervention by comparing how a treatment group and a control group change over time. Made famous by Card and Krueger's 1994 minimum-wage study and devel...
Dirichlet Process Mixture Model
The Dirichlet Process Mixture Model (DPMM) is a nonparametric Bayesian clustering method introduced through Ferguson's (1973) Dirichlet process prior that places a probability distribution over distributions. Unlike finite mixture models, t...
Discrete Choice Demand Model
Discrete-choice demand models estimate the demand for differentiated products — cars, cereals, computers — by modeling consumers as choosing the single product that maximizes their random utility, where utility depends on the product's obse...
Discrete-Time Hazard of Migration
The discrete-time hazard model analyzes the timing of migration when the data arrive in chunks of time — usually person-years — rather than as exact dates. Paul Allison's 1982 formulation showed that an event history measured in discrete pe...
Discriminant Analysis
Discriminant analysis finds linear combinations of predictor variables that best separate two or more known groups. It is used both to understand which predictors distinguish the groups and to classify new observations into those groups wit...
Distributive Politics Analysis
Distributive politics analysis studies how governments allocate divisible public spending — grants, transfers, projects, and pork — across districts and groups to maximize electoral support. Two competing theories anchor the field. The swin...
Dolado-Lütkepohl Causality
The Dolado-Lütkepohl (DL) test, introduced by Dolado and Lütkepohl (1996), is a modified Wald procedure for testing Granger causality in vector autoregressive (VAR) systems whose variables may be integrated or cointegrated. By fitting a VAR...
Double Bootstrap
The double bootstrap is a resampling method that calibrates a bootstrap confidence interval with a second, nested layer of bootstrap to bring its actual coverage closer to the nominal level. Introduced by Hall (1986) and Beran (1987), it is...