/dports/math/R/R-4.1.2/src/library/stats/R/ |
H A D | manova.R | 57 resid <- as.matrix(object$residuals) functionVar 59 if (!is.null(wt)) resid <- resid * sqrt(wt) 60 nresp <- NCOL(resid) 81 df <- df[-pm] 91 ss[[nt]] <- crossprod(resid) 104 if(rss.qr$rank < ncol(resid)) 106 rss.qr$rank, ncol(resid)), domain = NA) 113 "Pillai" = Pillai(eigs[i, ], df[i], df[nt]), 114 "Wilks" = Wilks (eigs[i, ], df[i], df[nt]), 115 "Hotelling-Lawley" = HL (eigs[i, ], df[i], df[nt]), [all …]
|
H A D | aov.R | 162 if(!is.null(wt)) resid <- resid * sqrt(wt) 180 df <- df[keep] 209 df <- c(df, rdf) 302 if(!is.null(wt)) resid <- resid * sqrt(wt) 303 nresp <- NCOL(resid) 346 df <- c(df, sum(ai)) 351 df <- c(df, lengths(split[[int]])) 362 df <- c(df, rdf) 367 ms <- ifelse(df > 0L, ss/df, NA) 597 if(!is.null(wt)) resid <- resid * sqrt(wt) [all …]
|
H A D | nls.R | 102 dev <- sum(resid^2) 158 list(resid = function() resid, nameattr in function 247 dev <- sum(resid^2) 324 list(resid = function() resid, nameattr in function 764 df <- x$df functionVar 765 rdf <- df[2L] 900 df <- c(NA, -diff(df.r)) vector 902 ms <- ss/df 905 if(df[i] > 0) { 909 else if(df[i] < 0) { [all …]
|
/dports/math/libRmath/R-4.1.1/src/library/stats/R/ |
H A D | manova.R | 57 resid <- as.matrix(object$residuals) functionVar 59 if (!is.null(wt)) resid <- resid * sqrt(wt) 60 nresp <- NCOL(resid) 81 df <- df[-pm] 91 ss[[nt]] <- crossprod(resid) 104 if(rss.qr$rank < ncol(resid)) 106 rss.qr$rank, ncol(resid)), domain = NA) 113 "Pillai" = Pillai(eigs[i, ], df[i], df[nt]), 114 "Wilks" = Wilks (eigs[i, ], df[i], df[nt]), 115 "Hotelling-Lawley" = HL (eigs[i, ], df[i], df[nt]), [all …]
|
H A D | aov.R | 162 if(!is.null(wt)) resid <- resid * sqrt(wt) 180 df <- df[keep] 209 df <- c(df, rdf) 302 if(!is.null(wt)) resid <- resid * sqrt(wt) 303 nresp <- NCOL(resid) 346 df <- c(df, sum(ai)) 351 df <- c(df, lengths(split[[int]])) 362 df <- c(df, rdf) 367 ms <- ifelse(df > 0L, ss/df, NA) 597 if(!is.null(wt)) resid <- resid * sqrt(wt) [all …]
|
H A D | nls.R | 102 dev <- sum(resid^2) 158 list(resid = function() resid, nameattr in function 247 dev <- sum(resid^2) 324 list(resid = function() resid, nameattr in function 764 df <- x$df functionVar 765 rdf <- df[2L] 900 df <- c(NA, -diff(df.r)) vector 902 ms <- ss/df 905 if(df[i] > 0) { 909 else if(df[i] < 0) { [all …]
|
/dports/math/py-statsmodels/statsmodels-0.13.1/statsmodels/tsa/statespace/tests/ |
H A D | test_cfa_tvpvar.py | 150 resid = mod.endog - fitted 151 df = v10 + mod.nobs 152 scale = S10 + np.dot(resid.T, resid) 153 assert_allclose(df, results['v10'].iloc[:2]) 157 resid = sim.simulated_state.T[1:] - sim.simulated_state.T[:-1] 158 sse = np.sum(resid**2, axis=0) 192 resid = mod.endog - fitted 193 df = v10 + mod.nobs 194 scale = S10 + np.dot(resid.T, resid) 195 assert_allclose(df, results['v10'].iloc[2:]) [all …]
|
/dports/devel/R-cran-gbm/gbm/demo/ |
H A D | robustReg.R | 18 tmod6 <- gbm( y ~ ., data=d, distribution=list( name="tdist", df=6 ), nameattr 21 tmod100 <- gbm( y ~ ., data=d, distribution=list( name="tdist", df=100 ), nameattr 35 rg <- qscale( resid( gmod , n.trees=gbest) ) 36 rt4 <- qscale( resid( tmod4 , n.trees=t4best) ) 37 rt6 <- qscale( resid( tmod6 , n.trees=t6best) ) 38 rt100 <- qscale( resid( tmod100 , n.trees=t100best ) )
|
/dports/math/R-cran-robustbase/robustbase/R/ |
H A D | ltsReg.R | 239 resid <- y - center functionVar 277 ans$resid <- resid/ans$scale 343 ans$resid <- resid/ans$scale 349 s1 <- sum(resid^2) 412 resid <- z1$residuals 428 ans$resid <- resid/ans$scale 534 df = c(p, rdf, NCOL(Qr$qr)))) nameattr in c 579 df <- x$df functionVar 580 rdf <- df[2] 595 cat("ALL", df[1], "residuals are 0: no residual degrees of freedom!\n") [all …]
|
H A D | lmrob.R | 373 resid <- x$residuals functionVar 374 df <- x$df functionVar 375 rdf <- df[2L] 381 if (NCOL(resid) > 1) 384 else setNames(quantile(resid), nam) 404 if (nsingular <- df[3L] - df[1L]) 532 n <- p + df 543 ans$df <- c(p, df, NCOL(object$qr$qr)) 553 resid <- object$residuals functionVar 581 rMr <- sum(wgt * resid^2) [all …]
|
H A D | nlrob.R | 161 resid <- y - fit functionVar 185 w <- psi(resid/Scale) 207 resid <- residuals(out) 230 rw <- psi(res.sc <- resid/Scale) 389 ans$df <- c(p, rdf) 426 resid <- x$residuals functionVar 427 df <- x$df functionVar 428 rdf <- df[2L] 434 if (NCOL(resid) > 1) 435 structure(apply(t(resid), 1, quantile), [all …]
|
/dports/math/R-cran-spdep/spdep/R/ |
H A D | s2sls.R | 154 resid <- residuals(x) functionVar 156 rq <- if (length(dim(resid)) == 2L) 157 structure(apply(t(resid), 1, quantile), dimnames = list(nam, 158 dimnames(resid)[[2]])) 159 else structure(quantile(resid), names = nam) 355 df <- nrow(Z) functionVar 361 var=vi,sse=sse,residuals=c(e),df=df) nameattr 394 df <- nrow(Z) - ncol(Z) functionVar 429 df=df) globalVar 434 s2 <- sse / df [all …]
|
/dports/finance/R-cran-vars/vars/R/ |
H A D | internal.R | 8 n.par<-sapply(x$varresult, function(x) summary(x)$df[2]) 9 sigma.u <- crossprod(resid(x))/n.par 480 PVAL <- 1 - pchisq(STATISTIC, df = PARAMETER) 512 PVAL <- 1 - pchisq(STATISTIC, df = PARAMETER) 534 PVAL <- 1 - pchisq(STATISTIC, df = 2) 555 PVAL <- 1 - pchisq(STATISTIC, df = PARAMETER) 563 PVAL <- 1 - pchisq(STATISTIC, df = PARAMETER) 571 PVAL <- 1 - pchisq(STATISTIC, df = PARAMETER) 617 PVAL <- 1 - pchisq(STATISTIC, df = PARAMETER) 629 PVAL <- 1 - pchisq(STATISTIC, df = PARAMETER) [all …]
|
H A D | BQ.R | 17 df <- summary(x$varresult[[1]])$df[2] functionVar 18 SigmaU <- crossprod(resid(x)) / df
|
H A D | logLik.varest.R | 3 df <- min(unlist(lapply(object$varresult, function(x) summary(x)$df[2]))) functionVar 5 resids <- resid(object)
|
/dports/math/R-cran-psych/psych/R/ |
H A D | set.cor.R | 49 resid <- y.matrix - yhat functionVar 75 df <- n.obs-k-1 functionVar 76 se.beta[[i]] <- (sqrt((1-R2[i])/(df))*sqrt(1/uniq))} 83 prob <- 2*(1- pt(abs(tvalue),df)) 84 SE2 <- 4*R2*(1-R2)^2*(df^2)/((n.obs^2-1)*(n.obs+3)) 86 F <- R2*df/(k*(1-R2)) 87 pF <- 1 - pf(F,k,df) 88 shrunkenR2 <- 1-(1-R2)*(n.obs-1)/df 116 …a,R=sqrt(R2),R2=R2,Rset=Rset,T=T,cancor = cc, cancor2=cc2,raw=raw,residual=resid,Call = cl)} else { 117 …F=pF,df=c(k,df),Rset=Rset,Rset.shrunk=R2set.shrunk,Rset.F=Rset.F,Rsetu=u,Rsetv=df.v,T=T,cancor=cc,… vector
|
/dports/math/py-statsmodels/statsmodels-0.13.1/statsmodels/stats/tests/ |
H A D | test_diagnostic.py | 308 resid = self.res.resid 573 df=(4, 3, 1), 582 df=(199, 200, 1), 1168 dict(fvalue=1.589672703015157, pvalue=0.178717196987075, df=(198, 193)) 1217 df = infl.summary_frame() 1218 assert_(isinstance(df, DataFrame)) 1668 resid = res.resid 1679 resid = res.resid 1721 df = smsdia.compare_encompassing(res1, res2, cov_type=cov_type) 1733 assert_allclose(np.asarray(df.loc["x"]), expected, atol=1e-8) [all …]
|
/dports/math/R-cran-VGAM/VGAM/R/ |
H A D | aamethods.q | 191 "df.residual" = "numeric", 240 df = "numeric", repr in summary.vgam 241 pearson.resid = "matrix", 254 df = "numeric", repr in summary.vglm 255 pearson.resid = "matrix", 267 df = "numeric", repr in summary.vlm 268 pearson.resid = "matrix", 357 "df.residual"=from@df.residual, 358 "df.total"=from@df.total, 521 if (!isGeneric("resid")) [all …]
|
/dports/math/R-cran-survey/survey/R/ |
H A D | anova.svyglm.R | 14 seqtests[[i]]<-regTermTest(thismodel,tlbls[i],method=method,df=ddf) 35 df<-sapply(x,"[[","df") functionVar 38 rval<-cbind(stats,df,p) 41 rval<-cbind(stats,df,ddf,p) 81 XX[,1]<-resid(xform) 83 XX[,i]<-resid(xform<-lm(Z[,i]~X+Z[,1:(i-1)]+0)) 125 df<-min(object$df.residual, object2$df.residual) functionVar 137 ddf = df, method = "sad", lower.tail = FALSE) 140 df = length(index), p = p, nameattr 151 p<-pchisq(chisq,df=length(index),lower.tail=FALSE) [all …]
|
/dports/math/py-statsmodels/statsmodels-0.13.1/statsmodels/genmod/ |
H A D | qif.py | 223 resid = endog[ix] - mean[ix] 224 sresid = resid / sd 245 m3 = np.dot(deriv.T, np.dot(c, vx * resid) / sd) 296 resid = self.endog - mean 297 scale = np.sum(resid**2) / (self.nobs - ddof_scale) 421 df = self.model.exog.shape[1] 422 return self.qif + 2*df 432 df = self.model.exog.shape[1] 433 return self.qif + np.log(self.model.nobs)*df
|
/dports/math/R-cran-survey/survey/man/ |
H A D | svyglm.Rd | 26 \method{summary}{svyglm}(object, correlation = FALSE, df.resid=NULL, 64 \item{df.resid}{Optional denominator degrees of freedom for Wald 80 If \code{df.resid} is not specified the df for the null model is 81 computed by \code{\link{degf}} and the residual df computed by 85 use \code{df.resid=Inf}, and to use number of PSUs-number of strata, 86 specify \code{df.resid=degf(design)}.
|
/dports/finance/R-cran-urca/urca/ |
H A D | NAMESPACE | 11 ur.ers, ur.kpss, ur.pp, ur.df, ur.sp, ur.za) 14 exportClasses("urca", "ca.jo", "cajo.test", "ur.kpss", "ca.po", "ur.ers", "ur.pp", "ur.sp", "ur.df"… 23 "lm", "na.omit", "pacf", "pchisq", "plot.ts", "resid", "residuals")
|
/dports/math/py-statsmodels/statsmodels-0.13.1/statsmodels/regression/ |
H A D | process_regression.py | 474 resid = self.endog - np.dot(self.exog, mnpar) 497 re = resid[ix] 529 resid = self.endog - np.dot(self.exog, mnpar) 547 resid_i = resid[ix] 861 df = pd.DataFrame() 867 df["Type"] = typ 877 df["tvalues"] = df.coef / df["std err"] 878 df["P>|t|"] = 2 * norm.sf(np.abs(df.tvalues)) 881 df["[%.3f" % (alpha / 2)] = df.coef - f * df["std err"] 882 df["%.3f]" % (1 - alpha / 2)] = df.coef + f * df["std err"] [all …]
|
/dports/math/py-statsmodels/statsmodels-0.13.1/statsmodels/stats/ |
H A D | _diagnostic_other.py | 295 res_ols3 = OLS(np.ones(nobs), pp.resid * resid_p[:,None]).fit() 307 def cm_test_robust(resid, resid_deriv, instruments, weights=1): argument 359 nobs = resid.shape[0] 367 mom_resid = pp.resid 369 moms_test = mom_resid * resid[:, None] * w_sqrt 1102 df = self.rank_cov_mom_constraints 1103 pval = stats.chi2.sf(stat, df) # Theorem 1 1104 return stat, pval, df 1194 df = self.rank_cov_mom_constraints 1195 pval = stats.chi2.sf(stat, df) [all …]
|
/dports/math/py-statsmodels/statsmodels-0.13.1/statsmodels/miscmodels/ |
H A D | tmodel.py | 100 kurt = stats.kurtosis(res_ols.resid) 101 df = 6./kurt + 4 103 df = 5 105 start_params[-2] = df 151 df = params[-2] 157 lPx = sps_gamln((df+1)/2) - sps_gamln(df/2.) 158 lPx -= 0.5*np_log(df*np_pi) + (df+1)/2.*np_log(1+(x**2)/df) 205 df = params[-2] 207 llike = - stats.t._logpdf(errorsest/scale, df) + np_log(scale)
|