/dports/math/R-cran-MSwM/MSwM/man/ |
H A D | AIC.Rd | 1 \name{AIC-methods} 3 \alias{AIC} 4 \alias{AIC-methods} 5 \alias{AIC,MSM.glm-method} 6 \alias{AIC,MSM.lm-method} 7 \alias{AIC.MSM.lm} 8 \alias{AIC.MSM.glm} 16 AIC(object, ..., k = 2) 20 …meric value for the penalty per parameter to be used. The default \code{k=2} is the classical AIC.} 26 Returns a numeric value with the corresponding AIC (or BIC, or ..., depending on k). [all …]
|
/dports/finance/R-cran-strucchange/strucchange/man/ |
H A D | logLik.breakpoints.Rd | 4 \alias{AIC.breakpointsfull} 8 Computation of log likelihood and AIC type information criteria 14 \method{AIC}{breakpointsfull}(object, breaks = NULL, ..., k = 2) 23 is the classical AIC, \code{k = log(n)} gives the BIC, if \code{n} 41 the AIC respectively. 57 plot(0:5, AIC(bp.nile, k = log(bp.nile$nobs)), type = "b") 58 ## AIC 59 plot(0:5, AIC(bp.nile), type = "b") 61 ## BIC, AIC, log likelihood of a single partition 63 AIC(bp.nile1, k = log(bp.nile1$nobs)) [all …]
|
/dports/math/R-cran-forecast/forecast/R/ |
H A D | tbats.R | 232 best.model$AIC <- Inf 249 if (new.model$AIC > best.model$AIC) { 320 aic.vector <- c(up.model$AIC, level.model$AIC, down.model$AIC) 338 if (down.model$AIC > best.model$AIC) { 366 if (up.model$AIC > best.model$AIC) { 381 if (non.seasonal.model$AIC < best.model$AIC) { 423 if (best.seasonal.model$AIC < best.model$AIC) { 435 if (new.model$AIC < best.model$AIC) { 494 if (second.model$AIC < first.model$AIC) { 563 if (second.model$AIC < first.model$AIC) { [all …]
|
H A D | bats.R | 127 … AIC = -Inf, likelihood = -Inf, variance = 0, alpha = 0.9999, method = "BATS", call = match.call() nameattr 211 aics[i] <- models.list[[i]]$AIC 230 if (current.model$AIC < best.aic) { 231 best.aic <- current.model$AIC 256 return(list(AIC = Inf)) nameattr 263 if (first.model$AIC > non.seasonal.model$AIC) { 286 if (second.model$AIC < first.model$AIC) { 306 return(list(AIC = Inf)) nameattr 313 if (first.model$AIC > non.seasonal.model$AIC) { 336 if (second.model$AIC < first.model$AIC) { [all …]
|
/dports/math/R/R-4.1.2/src/library/stats/man/ |
H A D | AIC.Rd | 1 % File src/library/stats/man/AIC.Rd 6 \name{AIC} 8 \alias{AIC} 23 AIC(object, \dots, k = 2) 33 default \code{k = 2} is the classical AIC.} 37 the smaller the AIC or BIC, the better the fit. 74 AIC (or BIC, or \dots, depending on \code{k}). 94 AIC(lm1) 95 stopifnot(all.equal(AIC(lm1), 96 AIC(logLik(lm1)))) [all …]
|
H A D | extractAIC.Rd | 8 \title{Extract AIC from a Fitted Model} 25 part in the AIC formula.} 40 \deqn{AIC = - 2\log L + k \times \mbox{edf},}{AIC = - 2*log L + k * edf,} 48 \code{\link{logLik}} and hence \code{\link{AIC}}. If \eqn{RSS} 53 \code{\link{AIC}} only handles unknown scale and uses the formula 55 where \eqn{w} are the weights. Further \code{AIC} counts the scale 59 compute the AIC: see the note under \code{logLik} about the 62 \code{k = 2} corresponds to the traditional AIC, using \code{k = 66 assumptions from those of methods for \code{\link{AIC}} (usually 72 to compare models of the same class (where only differences in AIC [all …]
|
/dports/math/libRmath/R-4.1.1/src/library/stats/man/ |
H A D | AIC.Rd | 1 % File src/library/stats/man/AIC.Rd 6 \name{AIC} 8 \alias{AIC} 23 AIC(object, \dots, k = 2) 33 default \code{k = 2} is the classical AIC.} 37 the smaller the AIC or BIC, the better the fit. 74 AIC (or BIC, or \dots, depending on \code{k}). 94 AIC(lm1) 95 stopifnot(all.equal(AIC(lm1), 96 AIC(logLik(lm1)))) [all …]
|
H A D | extractAIC.Rd | 8 \title{Extract AIC from a Fitted Model} 25 part in the AIC formula.} 40 \deqn{AIC = - 2\log L + k \times \mbox{edf},}{AIC = - 2*log L + k * edf,} 48 \code{\link{logLik}} and hence \code{\link{AIC}}. If \eqn{RSS} 53 \code{\link{AIC}} only handles unknown scale and uses the formula 55 where \eqn{w} are the weights. Further \code{AIC} counts the scale 59 compute the AIC: see the note under \code{logLik} about the 62 \code{k = 2} corresponds to the traditional AIC, using \code{k = 66 assumptions from those of methods for \code{\link{AIC}} (usually 72 to compare models of the same class (where only differences in AIC [all …]
|
/dports/math/R-cran-memisc/memisc/R/ |
H A D | xx-getSummary.R | 32 AIC <- AIC(obj) functionVar 33 BIC <- AIC(obj,k=log(N)) 44 AIC = AIC, nameattr 106 AIC <- AIC(obj) functionVar 107 BIC <- AIC(obj,k=log(N)) 119 AIC = AIC, nameattr
|
H A D | yy-mtable-ext-JasonWMorgan.R | 90 AIC <- -2*ll + 2*K functionVar 93 sumstat <- c(logLik = ll, AIC = AIC, BIC = BIC, N = N) nameattr 130 AIC <- -2*ll + 2*K functionVar 132 sumstat <- c(logLik = ll, AIC = AIC, BIC = BIC, N = N) nameattr 171 AIC <- -2*ll + 2*K functionVar 173 sumstat <- c(logLik = ll, AIC = AIC, BIC = BIC, N = N) nameattr
|
H A D | yz-getSummary-ordinal.R | 66 AIC <- AIC(obj) functionVar 67 BIC <- AIC(obj,k=log(N)) 78 AIC = AIC, nameattr 183 AIC <- AIC(obj) functionVar 195 AIC = AIC, nameattr
|
H A D | yy-mtable-ext-DaveAtkins.R | 61 AIC <- AIC(obj) functionVar 62 BIC <- AIC(obj,k=log(N)) 74 AIC = AIC, nameattr
|
/dports/math/R-cran-dlmodeler/dlmodeler/man/ |
H A D | AIC.dlmodeler.fit.Rd | 1 \name{AIC.dlmodeler.fit} 4 \alias{AIC.dlmodeler.fit} 6 Log-likelihood and AIC of a model 9 Returns the log-likelihood or the AIC for a fitted DLM object. 16 \method{AIC}{dlmodeler.fit}(object, ..., k = 2) 26 The AIC is computed according to the formula 29 and \eqn{k = 2} for the usual AIC, 34 Returns a numeric value with the corresponding log-likelihiid, AIC,
|
/dports/math/gretl/gretl-2021d/doc/tex/ |
H A D | criteria.tex | 50 {\rm AIC} = -2 \ell(\hat{\theta}) + 2k 58 the researcher seeks the minimum AIC. 65 {\rm AIC} = \ell(\hat{\theta}) - k 69 wants to maximize AIC. 83 {\rm AIC} = n(1 + \log 2\pi - \log n) + n\log {\rm SSR} + 2k 90 {\rm AIC} = n\log \left( \frac{\rm SSR}{n} \right) + 2k + 105 writing AIC$_G$ for the version given by Greene, we have 108 {\rm AIC}_G = \frac{1}{n} {\rm AIC} - (1 + \log 2\pi) 115 {\rm AIC}_R = \left( \frac{\rm SSR}{n} \right) e^{2k/n} 135 An alternative to the AIC which avoids this problem is the [all …]
|
/dports/math/R-cran-VGAM/VGAM/man/ |
H A D | AICvlm.Rd | 44 the default is the classical AIC. 54 in the fitted model, and \eqn{k = 2} for the usual AIC. 93 AIC has not been defined for QRR-VGLMs, yet. 96 Using AIC to compare \code{\link{posbinomial}} models 106 \code{AICc(...)} is the same as \code{AIC(..., corrected = TRUE)}. 128 The general applicability of \code{AIC} for the VGLM/VGAM classes 140 \code{\link[stats]{AIC}}, 161 AIC(fit1) 163 AIC(fit1, corrected = TRUE) # Slow way 167 AIC(fit2) [all …]
|
H A D | BICvlm.Rd | 48 BIC, AIC and other ICs can have have many additive 98 \code{\link[stats]{AIC}}. 125 %c(AIC(fit.l), AIC(fit.g), AIC(fit.v)) 126 %c(AIC(fit.l) - AIC(fit.v), 127 % AIC(fit.g) - AIC(fit.v))
|
/dports/math/R-cran-spdep/spdep/R/ |
H A D | anova.sarlm.R | 47 AIC <- unlist(lapply(aux, AIC)) functionVar 49 AIC = AIC, logLik = logLik, check.names = FALSE) nameattr 76 AIC <- AIC(LL) 77 res <- data.frame("AIC"=AIC, "Log likelihood"=LL, "df"=attr(LL, "df"),
|
/dports/textproc/adabrowse/adabrowse_4.0.3/ |
H A D | ad-driver.adb | 154 package AIC renames AD.Indices.Configuration; packspec 236 (Idx : in AIC.Index_Type; 241 AIC.Enter_Index (Idx); 436 AIC.Set_Structured (AIC.Unit_Index, True); 441 AIC.Set_Structured (AIC.Unit_Index, True); 442 AIC.Set_File_Name 446 AIC.Set_Structured (AIC.Unit_Index, False); 451 AIC.Set_Structured (AIC.Unit_Index, False); 452 AIC.Set_File_Name 460 AIC.Set_File_Name [all …]
|
/dports/math/gretl/gretl-2021d/doc/tex_it/ |
H A D | criteria.tex | 49 {\rm AIC} = -2 \ell(\hat{\theta}) + 2k 55 modello''. In questa formulazione, con AIC correlato negativamente alla 64 {\rm AIC} = \ell(\hat{\theta}) - k 68 si cercher� di massimizzare l'AIC. 82 {\rm AIC} = n(1 + \log 2\pi - \log n) + n\log {\rm SSR} + 2k 89 {\rm AIC} = n\log \left( \frac{\rm SSR}{n} \right) + 2k + 99 {\rm AIC} = \log \left( \frac{\rm SSR}{n} \right) + \frac{2k}{n} 104 AIC$_G$ la versione proposta da Greene, abbiamo 107 {\rm AIC}_G = \frac{1}{n} {\rm AIC} - (1 + \log 2\pi) 114 {\rm AIC}_R = \left( \frac{\rm SSR}{n} \right) e^{2k/n} [all …]
|
/dports/biology/hyphy/hyphy-2.5.33/res/TemplateBatchFiles/ |
H A D | AAModelComparison.bf | 71 AIC = 2(-res[1][0]+params); 90 Format (AIC, 9,3), " | "); 105 resultMatrix[midx][2] = AIC; 109 if (AIC < bestAIC) 111 bestAIC = AIC; 176 capString * "| Log Likelihood | #prms | AIC Score | c-AIC Score | Tree Length |\n"; 222 fprintf (stdout, "\n\nBest AIC model:\n\t", modelMatrixList[bestAICidx][0], " with the score of ", … 226 …fprintf (stdout, "\n\nBest c-AIC model:\n\t", modelMatrixList[bestCAICidx][0], " with the score of… 229 labelMatrix = {{"Log-likelihood","Parameters","AIC","c-AIC","Total tree length",""}};
|
/dports/math/R-cran-maxLik/maxLik/man/ |
H A D | maxLik-methods.Rd | 1 \name{AIC.maxLik} 2 \alias{AIC.maxLik} 14 \method{AIC}{maxLik}(object, \dots, k=2) 23 \sQuote{k = 2} is the classical AIC.} 34 \item{AIC}{calculates Akaike's Information Criterion (and other 60 AIC(ml)
|
/dports/devel/R-cran-classInt/classInt/man/ |
H A D | logLik.classIntervals.Rd | 22 within an interval, and with the AIC, a per-interval penalty can be used to 27 selected for a set of data. The `logLik()` function (and associated `AIC()` 31 As illustrated by the examples below (the AIC comparison does not 39 AIC(x) # By having a logLik method, AIC.default is used. 51 # AIC will make selection of the optimal intervals easier. 56 AIC(x_2, x_3, x_4)
|
/dports/math/octave/octave-6.4.0/liboctave/external/amos/ |
H A D | cuoik.f | 29 REAL AARG, AIC, ALIM, APHI, ASCLE, AX, AY, ELIM, FNN, FNU, GNN, local 34 DATA AIC / 1.265512123484645396E+00 / 82 IF (IFORM.EQ.2) RCZ = RCZ - 0.25E0*ALOG(AARG) - AIC 92 IF (IFORM.EQ.2) RCZ = RCZ - 0.25E0*ALOG(AARG) - AIC 104 CZ = CZ - CMPLX(0.25E0,0.0E0)*CLOG(ARG) - CMPLX(AIC,0.0E0) 136 IF (IFORM.EQ.2) RCZ = RCZ - 0.25E0*ALOG(AARG) - AIC 148 CZ = CZ - CMPLX(0.25E0,0.0E0)*CLOG(ARG) - CMPLX(AIC,0.0E0)
|
/dports/math/slatec/src/ |
H A D | cuoik.f | 39 REAL AARG, AIC, ALIM, APHI, ASCLE, AX, AY, ELIM, FNN, FNU, GNN, 44 DATA AIC / 1.265512123484645396E+00 / 93 IF (IFORM.EQ.2) RCZ = RCZ - 0.25E0*ALOG(AARG) - AIC 103 IF (IFORM.EQ.2) RCZ = RCZ - 0.25E0*ALOG(AARG) - AIC 115 CZ = CZ - CMPLX(0.25E0,0.0E0)*CLOG(ARG) - CMPLX(AIC,0.0E0) 147 IF (IFORM.EQ.2) RCZ = RCZ - 0.25E0*ALOG(AARG) - AIC 159 CZ = CZ - CMPLX(0.25E0,0.0E0)*CLOG(ARG) - CMPLX(AIC,0.0E0)
|
/dports/math/xlife++/xlifepp-sources-v2.0.1-2018-05-09/ext/Amos/ |
H A D | cuoik.f | 29 REAL AARG, AIC, ALIM, APHI, ASCLE, AX, AY, ELIM, FNN, FNU, GNN, 34 DATA AIC / 1.265512123484645396E+00 / 82 IF (IFORM.EQ.2) RCZ = RCZ - 0.25E0*ALOG(AARG) - AIC 92 IF (IFORM.EQ.2) RCZ = RCZ - 0.25E0*ALOG(AARG) - AIC 104 CZ = CZ - CMPLX(0.25E0,0.0E0)*CLOG(ARG) - CMPLX(AIC,0.0E0) 136 IF (IFORM.EQ.2) RCZ = RCZ - 0.25E0*ALOG(AARG) - AIC 148 CZ = CZ - CMPLX(0.25E0,0.0E0)*CLOG(ARG) - CMPLX(AIC,0.0E0)
|