Navigation

Axis-2 · Cascade-Free Harvest — Iteration 3 18 NEW

Family swept: jump / tail / fragility ignition detectors · campaign regime-invariant-orthogonality · append-only

18new candidates
0dupes
66running total (spot)
0out-of-scope this iter

The ignition axis. The prior iterations mapped who is exposed to a cascade (fragility, connectedness, crowding); this one harvests the detectors that fire when a cascade starts: discontinuous price jumps (BNS bipower, Huang–Tauchen, Lee–Mykland, Aït-Sahalia–Jacod, Jiang–Oomen), jump-robust vol baselines (Mancini threshold, MedRV/MinRV, preaveraging), signed jump variation and realized higher moments (downside/"bad" vol, negative realized skew = crash-risk), self-exciting criticality (Hawkes branching-ratio n→1, Filimonov–Sornette reflexivity/endogeneity index), fat-tail EVT (Hill, Pickands, Dekkers–Einmahl–de Haan, POT-GPD), and the bubble/crash singularity (LPPLS).

All 18 are spot-legal — none need quotes/L2 or derivatives. Two spot sub-axes: [P] from HF prices/returns (ODB bar OHLC or aggTrade mid), [T] from trade/event timestamps. Generic Hawkes intensity was already seeded (S16); the genuinely new addition here is the branching-ratio / reflexivity criticality (n→1) reading — H46/H47 cite S16 as parent.

New candidates (iter 3)

#NameFamilyMeasuresCascade / ignition mappingSpot?ParamStable-IDFOSS
H35BNS bipower-variation jump testrealized-jump-testRV−BV gap ⇒ presence & share of jump variationjump ignition (discontinuous moves)[P]PPBarndorff-Nielsen & Shephard 2004/2006 — DOI 10.1093/jjfinec/nbh001; 10.1093/jjfinec/nbi022VER highfrequency::BNSjumpTest (R, GPL≥2)
H36Huang–Tauchen relative-jump / z-statrealized-jump-testRJ=(RV−BV)/RV; ratio/log/max z-statisticjump ignition; variance fraction from jumps[P]DIMHuang & Tauchen 2005, JFEc — DOI 10.1093/jjfinec/nbi025 · parent H35VER highfrequency (R)
H37Lee–Mykland jump testrealized-jump-testreturn / local bipower spot-vol ⇒ intraday jump times & sizesjump ignition, per-event timing[P]PPLee & Mykland 2008, RFS — DOI 10.1093/rfs/hhm056VER YalDan/hf.econometrics + QuantLet/JumpDetectR (R/Py, crypto-native)
H38Aït-Sahalia–Jacod jump testrealized-jump-testpower-variation ratio at two scales → 1 (jumps); jump-activity indexjump ignition; infinite- vs finite-activity fragility[P]PPAït-Sahalia & Jacod 2009, Ann.Stat — DOI 10.1214/07-AOS568; arXiv:0903.0226VER highfrequency::AJjumpTest (R); hf.econometrics (Py)
H39Mancini threshold / truncated RVjump-robust-volcontinuous-part IV by truncating returns above θ(Δ)separates diffusion from jump; jump-size ID[P]PPMancini 2009, Scand.J.Stat — DOI 10.1111/j.1467-9469.2008.00622.xVER highfrequency (R) threshold measures
H40MedRV / MinRVjump-robust-volnearest-neighbour-truncation jump-robust integrated variancejump-robust IV baseline for the RV−IV jump gap[P]PFAndersen, Dobrev, Schaumburg 2012, J.Econometrics — DOI 10.1016/j.jeconom.2012.01.011VER highfrequency::medRV / minRV (R, GPL≥2)
H41Jiang–Oomen swap-variance jump testrealized-jump-testvariance-swap replication-error statistic (3rd+ return moments)jump ignition; more powerful than BV in tails[P]PPJiang & Oomen 2008, J.Econometrics — DOI 10.1016/j.jeconom.2008.03.011VER highfrequency::JOjumpTest (R)
H42Preaveraging noise-robust (JLMPV)jump-robust-volpre-average returns to kill microstructure noise → consistent IV / jump testsjump ID robust to noise (dense aggTrades)[P]PPJacod, Li, Mykland, Podolskij, Vetter 2009, SPA — DOI 10.1016/j.spa.2008.11.004VER highfrequency (R) preaveraged cov
H43Bollerslev–Law–Tauchen co-jump testco-jumpcross-sectional common-jump detector across a panelsystemic co-jump ignition / contagion across symbols[P] multi-symbolPPBollerslev, Law, Tauchen 2008, J.Econometrics — DOI 10.1016/j.jeconom.2008.01.006UNV highfrequency::rBPCov blocks; dedicated BLT UNVERIFIED
H44Realized semivariance / signed jump variationsigned-jump-semivarianceRS⁺, RS⁻; SJV = RS⁺−RS⁻ ("good"/"bad" vol)crash precursor: bad vol & negative SJV predict higher future vol[P]PFBarndorff-Nielsen, Kinnebrock, Shephard 2010; Patton & Sheppard 2015, REStat — DOI 10.1162/REST_a_00503VER highfrequency::rSV / rSemiCov (R, GPL≥2)
H45Realized skewness / kurtosisrealized-higher-momentintraday-return realized skewness & kurtosis over a windowfat-tail fragility; negative realized skew = crash-risk loading[P]DIMAmaya, Christoffersen, Jacobs, Vasquez 2015, JFE — DOI 10.1016/j.jfineco.2015.02.009VER highfrequency::rSkew / rKurt (R, GPL≥2)
H46Hawkes branching-ratio criticality (n→1)self-exciting-criticalitybranching ratio n = kernel L¹-norm; n→1 ⇒ near-critical self-excitationreflexive feedback; one event triggers a near-diverging cascade[T]DIMHardiman, Bercot, Bouchaud 2013, EPJ B — DOI 10.1140/epjb/e2013-40107-3; arXiv:1302.1405 · parent S16VER X-DataInitiative/tick (Py, BSD-3); hawkesbook; hawkeslib
H47Filimonov–Sornette reflexivity indexself-exciting-criticalityendogeneity fraction = n (self-generated vs exogenous-news activity)flash-crash precursor; rising endogeneity ⇒ approaching criticality[T]DIMFilimonov & Sornette 2012, PRE 85:056108 — DOI 10.1103/PhysRevE.85.056108; arXiv:1201.3572 · parent H46UNV tick / hawkesbook (calibrate → n); dedicated FS pkg UNVERIFIED
H48Hill tail-index estimatortail-index-EVTML tail exponent α from k upper order statistics (power-law tail)fat-tail fragility; small α ⇒ heavy crash tail[P]PPHill 1975, Ann.Stat — DOI 10.1214/aos/1176343247VER evir::hill (R, GPL≥2); POT; extRemes
H49Pickands tail-index estimatortail-index-EVTorder-statistic estimator of EVT shape ξ (all domains of attraction)fat-tail fragility; ξ>0 ⇒ heavy tail[P]PPPickands 1975, Ann.Stat — DOI 10.1214/aos/1176343003VER evir::pickands (R); POT
H50Dekkers–Einmahl–de Haan moment estimatortail-index-EVTmoment-ratio estimator of EVT index γ (Hill generalized to real γ)fat-tail fragility (bounded & heavy tails)[P]PPDekkers, Einmahl, de Haan 1989, Ann.Stat — DOI 10.1214/aos/1176347397UNV evir / extRemes (R); exact fn UNVERIFIED
H51Peaks-Over-Threshold GPD fittail-index-EVTexceedances over threshold u ~ Generalized Pareto (Balkema–de Haan–Pickands)fat-tail fragility; tail-VaR / ES; ξ = crash-tail heaviness[P]PPBalkema & de Haan 1974, Ann.Prob — DOI 10.1214/aop/1176996548; Pickands 1975VER POT (R, GPL≥2); extRemes; scipy.stats.genpareto (Py, BSD-3)
H52LPPLS log-periodic power-law singularitybubble-crash-singularityfits faster-than-exp growth + log-periodic oscillations → finite-time critical t_cbubble/crash precursor; endogenous critical point t_c[P]PP (7 params, ill-cond.)Johansen, Ledoit, Sornette 2000, IJTAF — DOI 10.1142/S0219024900000115; calib. Filimonov & Sornette 2013 — DOI 10.1016/j.physa.2013.04.012VER Boulder-Investment-Technologies/lppls (Py, MIT)

FOSS anchors verified this iteration

Scope & provenance notes
Next angle → illiquidity & price-impact + market-impact laws + capacity/turnover (Amihud–Mendelson, Hasbrouck VAR info-share, Pástor–Stambaugh, square-root impact law / Almgren–Chriss, Hasbrouck Gibbs-sampler spread, participation/turnover). · Data SSoT: axis-2-cascade-free/CANDIDATE-CATALOG.md · back to loop hub