Send output to:
Browser Blue - Charts White
Browser Black/White
CSV
Data X:
1554 53.361 0 0 1994 56.628 0 0 1961 62.073 0 0 1716 62.073 0 0 1425 71.1295 0 0 1664 76.86575 0 0 1524 79.16025 0 0 1342 81.45475 0 0 1449 78.969 0 0 1622 83.755 0 0 1530 82.5585 0 0 1385 76.576 0 0 1117 81.609 0 0 1253 79.136 0 0 1088 86.555 0 1 1167 90.2645 0 1 1344 78.315 0 0 1745 82.23075 0 0 1559 62.652 0 0 1395 69.17825 0 0 1521 72.252 0 0 1890 62.886 0 0 1531 65.562 0 0 1635 58.872 0 0 1269 70.21425 1 0 1612 72.96775 1 1 1343 82.605 1 0 1634 81.22825 1 0 1571 84.5175 1 0 1881 80.22 1 0 1528 75.9225 1 0 1960 64.4625 1 0 1676 69.56 1 0 2166 68.08 1 0 1663 63.64 1 0 2067 74 1 0 1801 80.548 1 1 2347 96.038 1 1 1938 89.842 1 1 1980 103.783 1 1 2097 91.04325 1 1 2579 97.43225 1 1 2191 115.002 1 1 2449 103.82125 1 1 2208 101.30575 1 1 2353 104.62725 1 1 2151 106.288 1 1 2307 116.2525 1 1 1826 130.72 1 1 2414 123.84 1 1 2029 129 1 1 2091 120.4 1 1 1988 139.593 1 1 2484 132.246 1 1 2321 137.75625 1 1 2614 143.2665 1 1
Names of X columns:
a b c d
Sample Range:
(leave blank to include all observations)
From:
To:
Column Number of Endogenous Series
(?)
Fixed Seasonal Effects
Do not include Seasonal Dummies
Do not include Seasonal Dummies
Include Seasonal Dummies
Type of Equation
No Linear Trend
No Linear Trend
Linear Trend
First Differences
Seasonal Differences (s)
First and Seasonal Differences (s)
Degree of Predetermination (lagged endogenous variables)
Degree of Seasonal Predetermination
Seasonality
12
1
2
3
4
5
6
7
8
9
10
11
12
Chart options
R Code
par5 <- '0' par4 <- '1' par3 <- 'No Linear Trend' par2 <- 'Do not include Seasonal Dummies' par1 <- '1' library(lattice) library(lmtest) n25 <- 25 #minimum number of obs. for Goldfeld-Quandt test mywarning <- '' par1 <- as.numeric(par1) if(is.na(par1)) { par1 <- 1 mywarning = 'Warning: you did not specify the column number of the endogenous series! The first column was selected by default.' } if (par4=='') par4 <- 0 par4 <- as.numeric(par4) if (par5=='') par5 <- 0 par5 <- as.numeric(par5) x <- na.omit(t(y)) k <- length(x[1,]) n <- length(x[,1]) x1 <- cbind(x[,par1], x[,1:k!=par1]) mycolnames <- c(colnames(x)[par1], colnames(x)[1:k!=par1]) colnames(x1) <- mycolnames #colnames(x)[par1] x <- x1 if (par3 == 'First Differences'){ (n <- n -1) x2 <- array(0, dim=c(n,k), dimnames=list(1:n, paste('(1-B)',colnames(x),sep=''))) for (i in 1:n) { for (j in 1:k) { x2[i,j] <- x[i+1,j] - x[i,j] } } x <- x2 } if (par3 == 'Seasonal Differences (s=12)'){ (n <- n - 12) x2 <- array(0, dim=c(n,k), dimnames=list(1:n, paste('(1-B12)',colnames(x),sep=''))) for (i in 1:n) { for (j in 1:k) { x2[i,j] <- x[i+12,j] - x[i,j] } } x <- x2 } if (par3 == 'First and Seasonal Differences (s=12)'){ (n <- n -1) x2 <- array(0, dim=c(n,k), dimnames=list(1:n, paste('(1-B)',colnames(x),sep=''))) for (i in 1:n) { for (j in 1:k) { x2[i,j] <- x[i+1,j] - x[i,j] } } x <- x2 (n <- n - 12) x2 <- array(0, dim=c(n,k), dimnames=list(1:n, paste('(1-B12)',colnames(x),sep=''))) for (i in 1:n) { for (j in 1:k) { x2[i,j] <- x[i+12,j] - x[i,j] } } x <- x2 } if(par4 > 0) { x2 <- array(0, dim=c(n-par4,par4), dimnames=list(1:(n-par4), paste(colnames(x)[par1],'(t-',1:par4,')',sep=''))) for (i in 1:(n-par4)) { for (j in 1:par4) { x2[i,j] <- x[i+par4-j,par1] } } x <- cbind(x[(par4+1):n,], x2) n <- n - par4 } if(par5 > 0) { x2 <- array(0, dim=c(n-par5*12,par5), dimnames=list(1:(n-par5*12), paste(colnames(x)[par1],'(t-',1:par5,'s)',sep=''))) for (i in 1:(n-par5*12)) { for (j in 1:par5) { x2[i,j] <- x[i+par5*12-j*12,par1] } } x <- cbind(x[(par5*12+1):n,], x2) n <- n - par5*12 } if (par2 == 'Include Monthly Dummies'){ x2 <- array(0, dim=c(n,11), dimnames=list(1:n, paste('M', seq(1:11), sep =''))) for (i in 1:11){ x2[seq(i,n,12),i] <- 1 } x <- cbind(x, x2) } if (par2 == 'Include Quarterly Dummies'){ x2 <- array(0, dim=c(n,3), dimnames=list(1:n, paste('Q', seq(1:3), sep =''))) for (i in 1:3){ x2[seq(i,n,4),i] <- 1 } x <- cbind(x, x2) } (k <- length(x[n,])) if (par3 == 'Linear Trend'){ x <- cbind(x, c(1:n)) colnames(x)[k+1] <- 't' } x (k <- length(x[n,])) head(x) df <- as.data.frame(x) (mylm <- lm(df)) (mysum <- summary(mylm)) if (n > n25) { kp3 <- k + 3 nmkm3 <- n - k - 3 gqarr <- array(NA, dim=c(nmkm3-kp3+1,3)) numgqtests <- 0 numsignificant1 <- 0 numsignificant5 <- 0 numsignificant10 <- 0 for (mypoint in kp3:nmkm3) { j <- 0 numgqtests <- numgqtests + 1 for (myalt in c('greater', 'two.sided', 'less')) { j <- j + 1 gqarr[mypoint-kp3+1,j] <- gqtest(mylm, point=mypoint, alternative=myalt)$p.value } if (gqarr[mypoint-kp3+1,2] < 0.01) numsignificant1 <- numsignificant1 + 1 if (gqarr[mypoint-kp3+1,2] < 0.05) numsignificant5 <- numsignificant5 + 1 if (gqarr[mypoint-kp3+1,2] < 0.10) numsignificant10 <- numsignificant10 + 1 } gqarr } bitmap(file='test0.png') plot(x[,1], type='l', main='Actuals and Interpolation', ylab='value of Actuals and Interpolation (dots)', xlab='time or index') points(x[,1]-mysum$resid) grid() dev.off() bitmap(file='test1.png') plot(mysum$resid, type='b', pch=19, main='Residuals', ylab='value of Residuals', xlab='time or index') grid() dev.off() bitmap(file='test2.png') hist(mysum$resid, main='Residual Histogram', xlab='values of Residuals') grid() dev.off() bitmap(file='test3.png') densityplot(~mysum$resid,col='black',main='Residual Density Plot', xlab='values of Residuals') dev.off() bitmap(file='test4.png') qqnorm(mysum$resid, main='Residual Normal Q-Q Plot') qqline(mysum$resid) grid() dev.off() (myerror <- as.ts(mysum$resid)) bitmap(file='test5.png') dum <- cbind(lag(myerror,k=1),myerror) dum dum1 <- dum[2:length(myerror),] dum1 z <- as.data.frame(dum1) z plot(z,main=paste('Residual Lag plot, lowess, and regression line'), ylab='values of Residuals', xlab='lagged values of Residuals') lines(lowess(z)) abline(lm(z)) grid() dev.off() bitmap(file='test6.png') acf(mysum$resid, lag.max=length(mysum$resid)/2, main='Residual Autocorrelation Function') grid() dev.off() bitmap(file='test7.png') pacf(mysum$resid, lag.max=length(mysum$resid)/2, main='Residual Partial Autocorrelation Function') grid() dev.off() bitmap(file='test8.png') opar <- par(mfrow = c(2,2), oma = c(0, 0, 1.1, 0)) plot(mylm, las = 1, sub='Residual Diagnostics') par(opar) dev.off() if (n > n25) { bitmap(file='test9.png') plot(kp3:nmkm3,gqarr[,2], main='Goldfeld-Quandt test',ylab='2-sided p-value',xlab='breakpoint') grid() dev.off() } load(file='createtable') a<-table.start() a<-table.row.start(a) a<-table.element(a, 'Multiple Linear Regression - Estimated Regression Equation', 1, TRUE) a<-table.row.end(a) myeq <- colnames(x)[1] myeq <- paste(myeq, '[t] = ', sep='') for (i in 1:k){ if (mysum$coefficients[i,1] > 0) myeq <- paste(myeq, '+', '') myeq <- paste(myeq, signif(mysum$coefficients[i,1],6), sep=' ') if (rownames(mysum$coefficients)[i] != '(Intercept)') { myeq <- paste(myeq, rownames(mysum$coefficients)[i], sep='') if (rownames(mysum$coefficients)[i] != 't') myeq <- paste(myeq, '[t]', sep='') } } myeq <- paste(myeq, ' + e[t]') a<-table.row.start(a) a<-table.element(a, myeq) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, mywarning) a<-table.row.end(a) a<-table.end(a) table.save(a,file='mytable1.tab') a<-table.start() a<-table.row.start(a) a<-table.element(a,hyperlink('http://www.xycoon.com/ols1.htm','Multiple Linear Regression - Ordinary Least Squares',''), 6, TRUE) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a,'Variable',header=TRUE) a<-table.element(a,'Parameter',header=TRUE) a<-table.element(a,'S.D.',header=TRUE) a<-table.element(a,'T-STAT<br />H0: parameter = 0',header=TRUE) a<-table.element(a,'2-tail p-value',header=TRUE) a<-table.element(a,'1-tail p-value',header=TRUE) a<-table.row.end(a) for (i in 1:k){ a<-table.row.start(a) a<-table.element(a,rownames(mysum$coefficients)[i],header=TRUE) a<-table.element(a,formatC(signif(mysum$coefficients[i,1],5),format='g',flag='+')) a<-table.element(a,formatC(signif(mysum$coefficients[i,2],5),format='g',flag=' ')) a<-table.element(a,formatC(signif(mysum$coefficients[i,3],4),format='e',flag='+')) a<-table.element(a,formatC(signif(mysum$coefficients[i,4],4),format='g',flag=' ')) a<-table.element(a,formatC(signif(mysum$coefficients[i,4]/2,4),format='g',flag=' ')) a<-table.row.end(a) } a<-table.end(a) table.save(a,file='mytable2.tab') a<-table.start() a<-table.row.start(a) a<-table.element(a, 'Multiple Linear Regression - Regression Statistics', 2, TRUE) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'Multiple R',1,TRUE) a<-table.element(a,formatC(signif(sqrt(mysum$r.squared),6),format='g',flag=' ')) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'R-squared',1,TRUE) a<-table.element(a,formatC(signif(mysum$r.squared,6),format='g',flag=' ')) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'Adjusted R-squared',1,TRUE) a<-table.element(a,formatC(signif(mysum$adj.r.squared,6),format='g',flag=' ')) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'F-TEST (value)',1,TRUE) a<-table.element(a,formatC(signif(mysum$fstatistic[1],6),format='g',flag=' ')) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'F-TEST (DF numerator)',1,TRUE) a<-table.element(a, signif(mysum$fstatistic[2],6)) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'F-TEST (DF denominator)',1,TRUE) a<-table.element(a, signif(mysum$fstatistic[3],6)) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'p-value',1,TRUE) a<-table.element(a,formatC(signif(1-pf(mysum$fstatistic[1],mysum$fstatistic[2],mysum$fstatistic[3]),6),format='g',flag=' ')) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'Multiple Linear Regression - Residual Statistics', 2, TRUE) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'Residual Standard Deviation',1,TRUE) a<-table.element(a,formatC(signif(mysum$sigma,6),format='g',flag=' ')) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'Sum Squared Residuals',1,TRUE) a<-table.element(a,formatC(signif(sum(myerror*myerror),6),format='g',flag=' ')) a<-table.row.end(a) a<-table.end(a) table.save(a,file='mytable3.tab') if(n < 200) { a<-table.start() a<-table.row.start(a) a<-table.element(a, 'Multiple Linear Regression - Actuals, Interpolation, and Residuals', 4, TRUE) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a, 'Time or Index', 1, TRUE) a<-table.element(a, 'Actuals', 1, TRUE) a<-table.element(a, 'Interpolation<br />Forecast', 1, TRUE) a<-table.element(a, 'Residuals<br />Prediction Error', 1, TRUE) a<-table.row.end(a) for (i in 1:n) { a<-table.row.start(a) a<-table.element(a,i, 1, TRUE) a<-table.element(a,formatC(signif(x[i],6),format='g',flag=' ')) a<-table.element(a,formatC(signif(x[i]-mysum$resid[i],6),format='g',flag=' ')) a<-table.element(a,formatC(signif(mysum$resid[i],6),format='g',flag=' ')) a<-table.row.end(a) } a<-table.end(a) table.save(a,file='mytable4.tab') if (n > n25) { a<-table.start() a<-table.row.start(a) a<-table.element(a,'Goldfeld-Quandt test for Heteroskedasticity',4,TRUE) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a,'p-values',header=TRUE) a<-table.element(a,'Alternative Hypothesis',3,header=TRUE) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a,'breakpoint index',header=TRUE) a<-table.element(a,'greater',header=TRUE) a<-table.element(a,'2-sided',header=TRUE) a<-table.element(a,'less',header=TRUE) a<-table.row.end(a) for (mypoint in kp3:nmkm3) { a<-table.row.start(a) a<-table.element(a,mypoint,header=TRUE) a<-table.element(a,formatC(signif(gqarr[mypoint-kp3+1,1],6),format='g',flag=' ')) a<-table.element(a,formatC(signif(gqarr[mypoint-kp3+1,2],6),format='g',flag=' ')) a<-table.element(a,formatC(signif(gqarr[mypoint-kp3+1,3],6),format='g',flag=' ')) a<-table.row.end(a) } a<-table.end(a) table.save(a,file='mytable5.tab') a<-table.start() a<-table.row.start(a) a<-table.element(a,'Meta Analysis of Goldfeld-Quandt test for Heteroskedasticity',4,TRUE) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a,'Description',header=TRUE) a<-table.element(a,'# significant tests',header=TRUE) a<-table.element(a,'% significant tests',header=TRUE) a<-table.element(a,'OK/NOK',header=TRUE) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a,'1% type I error level',header=TRUE) a<-table.element(a,signif(numsignificant1,6)) a<-table.element(a,formatC(signif(numsignificant1/numgqtests,6),format='g',flag=' ')) if (numsignificant1/numgqtests < 0.01) dum <- 'OK' else dum <- 'NOK' a<-table.element(a,dum) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a,'5% type I error level',header=TRUE) a<-table.element(a,signif(numsignificant5,6)) a<-table.element(a,signif(numsignificant5/numgqtests,6)) if (numsignificant5/numgqtests < 0.05) dum <- 'OK' else dum <- 'NOK' a<-table.element(a,dum) a<-table.row.end(a) a<-table.row.start(a) a<-table.element(a,'10% type I error level',header=TRUE) a<-table.element(a,signif(numsignificant10,6)) a<-table.element(a,signif(numsignificant10/numgqtests,6)) if (numsignificant10/numgqtests < 0.1) dum <- 'OK' else dum <- 'NOK' a<-table.element(a,dum) a<-table.row.end(a) a<-table.end(a) table.save(a,file='mytable6.tab') } }
Compute
Summary of computational transaction
Raw Input
view raw input (R code)
Raw Output
view raw output of R engine
Computing time
1 seconds
R Server
Big Analytics Cloud Computing Center
Click here to blog (archive) this computation