DATA 607 Final Project - MongoDB Statistical Analysis - Global Perspective
Jason Givens-Doyle, Romerl Elizes & Soumya Ghosh
December 12, 2018
library(RODBC)
library(mongolite)
library(knitr)
library(psych)
library(kableExtra)
library(stringr)
library(dplyr)
library(tidyr)
library(scales)
library(ggplot2)
library(plotly)
library(maps)
library(mapdata)
library(ggrepel) #not using this at the moment, but it does give the option to add labels. While not useful for the
options(knitr.table.format = "html")mbreast <- mongo("breast")
mdigothr <- mongo("digothr")
mmalegen <- mongo("malegen")
mfemgen <- mongo("femgent")
mother <- mongo("other")
mrespir <- mongo("respir")
mcolrect <- mongo("colrect")
mlymyleuk <- mongo("lymyleuk")
murinary <- mongo("urinary")breastDF <- mbreast$find(
query = '{"birthYear" : { "$gt" : 1979 }, "ageDiagnosis" : { "$gt" : 19 }, "survivalMonths" : { "$lt" : 9999 } }',
fields = '{ "ageDiagnosis" : true, "yearDiagnosis" : true, "survivalMonths" : true, "_id" : false }')
digothrDF <- mdigothr$find(
query = '{"birthYear" : { "$gt" : 1979 }, "ageDiagnosis" : { "$gt" : 19 }, "survivalMonths" : { "$lt" : 9999 } }',
fields = '{ "ageDiagnosis" : true, "yearDiagnosis" : true, "survivalMonths" : true, "_id" : false }')
malegenDF <- mmalegen$find(
query = '{"birthYear" : { "$gt" : 1979 }, "ageDiagnosis" : { "$gt" : 19 }, "survivalMonths" : { "$lt" : 9999 } }',
fields = '{ "ageDiagnosis" : true, "yearDiagnosis" : true, "survivalMonths" : true, "_id" : false }')
femgenDF <- mfemgen$find(
query = '{"birthYear" : { "$gt" : 1979 }, "ageDiagnosis" : { "$gt" : 19 }, "survivalMonths" : { "$lt" : 9999 } }',
fields = '{ "ageDiagnosis" : true, "yearDiagnosis" : true, "survivalMonths" : true, "_id" : false }')
otherDF <- mother$find(
query = '{"birthYear" : { "$gt" : 1979 }, "ageDiagnosis" : { "$gt" : 19 }, "survivalMonths" : { "$lt" : 9999 } }',
fields = '{ "ageDiagnosis" : true, "yearDiagnosis" : true, "survivalMonths" : true, "_id" : false }')
respirDF <- mrespir$find(
query = '{"birthYear" : { "$gt" : 1979 }, "ageDiagnosis" : { "$gt" : 19 }, "survivalMonths" : { "$lt" : 9999 } }',
fields = '{ "ageDiagnosis" : true, "yearDiagnosis" : true, "survivalMonths" : true, "_id" : false }')
colrectDF <- mcolrect$find(
query = '{"birthYear" : { "$gt" : 1979 }, "ageDiagnosis" : { "$gt" : 19 }, "survivalMonths" : { "$lt" : 9999 } }',
fields = '{ "ageDiagnosis" : true, "yearDiagnosis" : true, "survivalMonths" : true, "_id" : false }')
lymyleukDF <- mlymyleuk$find(
query = '{"birthYear" : { "$gt" : 1979 }, "ageDiagnosis" : { "$gt" : 19 }, "survivalMonths" : { "$lt" : 9999 } }',
fields = '{ "ageDiagnosis" : true, "yearDiagnosis" : true, "survivalMonths" : true, "_id" : false }')
urinaryDF <- murinary$find(
query = '{"birthYear" : { "$gt" : 1979 }, "ageDiagnosis" : { "$gt" : 19 }, "survivalMonths" : { "$lt" : 9999 } }',
fields = '{ "ageDiagnosis" : true, "yearDiagnosis" : true, "survivalMonths" : true, "_id" : false }')
breastDF <- na.omit(breastDF)
digothrDF <- na.omit(digothrDF)
malegenDF <- na.omit(malegenDF)
femgenDF <- na.omit(femgenDF)
otherDF <- na.omit(otherDF)
respirDF <- na.omit(respirDF)
colrectDF <- na.omit(colrectDF)
lymyleukDF <- na.omit(lymyleukDF)
urinaryDF <- na.omit(urinaryDF)
nrow(breastDF)## [1] 6187## [1] 2751## [1] 10007## [1] 8094## [1] 47067## [1] 1312## [1] 3373## [1] 15810## [1] 2071breastDF <- mutate(breastDF,survivalYears = survivalMonths/12, currentYear = survivalYears + yearDiagnosis)
digothrDF <- mutate(digothrDF,survivalYears = survivalMonths/12, currentYear = survivalYears + yearDiagnosis)
malegenDF <- mutate(malegenDF,survivalYears = survivalMonths/12, currentYear = survivalYears + yearDiagnosis)
femgenDF <- mutate(femgenDF,survivalYears = survivalMonths/12, currentYear = survivalYears + yearDiagnosis)
otherDF <- mutate(otherDF,survivalYears = survivalMonths/12, currentYear = survivalYears + yearDiagnosis)
respirDF <- mutate(respirDF,survivalYears = survivalMonths/12, currentYear = survivalYears + yearDiagnosis)
colrectDF <- mutate(colrectDF,survivalYears = survivalMonths/12, currentYear = survivalYears + yearDiagnosis)
lymyleukDF <- mutate(lymyleukDF,survivalYears = survivalMonths/12, currentYear = survivalYears + yearDiagnosis)
urinaryDF <- mutate(urinaryDF,survivalYears = survivalMonths/12, currentYear = survivalYears + yearDiagnosis)
breastDF <- breastDF[ which(breastDF$currentYear < 2016), ]
digothrDF <- digothrDF[ which(digothrDF$currentYear < 2016), ]
malegenDF <- malegenDF[ which(malegenDF$currentYear < 2016), ]
femgenDF <- femgenDF[ which(femgenDF$currentYear < 2016), ]
otherDF <- otherDF[ which(otherDF$currentYear < 2016), ]
respirDF <- respirDF[ which(respirDF$currentYear < 2016), ]
colrectDF <- colrectDF[ which(colrectDF$currentYear < 2016), ]
lymyleukDF <- lymyleukDF[ which(lymyleukDF$currentYear < 2016), ]
urinaryDF <- urinaryDF[ which(urinaryDF$currentYear < 2016), ]plot_ss <- function(x, y, maintitle, showSquares = FALSE, leastSquares = FALSE){
plot(x,y,xlab="Diagnosis Year", ylab = "Survival Years", main = maintitle)
if(leastSquares){
m1 <- lm(y~x)
y.hat <- m1$fit
} else{
pt1 <- locator(1)
points(pt1$x, pt1$y, pch = 4)
pt2 <- locator(1)
points(pt2$x, pt2$y, pch = 4)
pts <- data.frame("x" = c(pt1$x, pt2$x),"y" = c(pt1$y, pt2$y))
m1 <- lm(y ~ x, data = pts)
y.hat <- predict(m1, newdata = data.frame(x))
}
r <- y - y.hat
abline(m1)
oSide <- x - r
LLim <- par()$usr[1]
RLim <- par()$usr[2]
oSide[oSide < LLim | oSide > RLim] <- c(x + r)[oSide < LLim | oSide > RLim] # move boxes to avoid margins
n <- length(y.hat)
for(i in 1:n){
lines(rep(x[i], 2), c(y[i], y.hat[i]), lty = 2, col = "blue")
if(showSquares){
lines(rep(oSide[i], 2), c(y[i], y.hat[i]), lty = 3, col = "orange")
lines(c(oSide[i], x[i]), rep(y.hat[i],2), lty = 3, col = "orange")
lines(c(oSide[i], x[i]), rep(y[i],2), lty = 3, col = "orange")
}
}
}
summaryTable <- function(cancerType,maintitle = ""){
survivalYears = cancerType$survivalYears
yearDiagnosis = cancerType$yearDiagnosis
meanTable <- tapply(survivalYears,yearDiagnosis,mean)
show(nrow(cancerType))
show(describeBy(survivalYears, group = yearDiagnosis, mat=TRUE))
barplot(meanTable,beside=T,col=c("#ee7700","#3333ff")
,main=maintitle,xlab="Diagnosis Year",ylab="Survival Years")
}
inferenceTests <- function(cancerType, maintitle = "") {
yearDiagnosis <- cancerType$yearDiagnosis
survivalYears <- cancerType$survivalYears
plot_ss(x = yearDiagnosis, y = survivalYears, maintitle, showSquares = FALSE)
m2 <- lm(survivalYears ~ yearDiagnosis, data = cancerType)
summary(m2)
}
inferenceTest0 <- function(cancerType) {
m2 <- lm(survivalYears ~ yearDiagnosis, data = cancerType)
hist(m2$residuals)
qqnorm(m2$residuals)
qqline(m2$residuals)
}## [1] 6187
## item group1 vars n mean sd median trimmed
## X11 1 2000 1 1 4.8333333 NA 4.8333333 4.8333333
## X12 2 2001 1 4 11.2500000 6.4481551 14.3750000 11.2500000
## X13 3 2002 1 8 8.7187500 4.0362783 8.1666667 8.7187500
## X14 4 2003 1 25 8.4800000 4.8088629 11.7500000 8.8015873
## X15 5 2004 1 36 9.0000000 3.7311431 11.1250000 9.4750000
## X16 6 2005 1 52 7.4535256 4.0209965 10.0833333 7.9047619
## X17 7 2006 1 110 7.3901515 2.9913427 9.0833333 7.8399621
## X18 8 2007 1 167 6.7085828 2.5418827 8.0833333 7.1432099
## X19 9 2008 1 213 6.1799687 2.1934915 7.1666667 6.6033138
## X110 10 2009 1 294 5.2814626 1.9273094 6.1250000 5.6295904
## X111 11 2010 1 380 4.6989035 1.4272917 5.1666667 5.0052083
## X112 12 2011 1 542 3.8831488 1.0787816 4.2500000 4.1027266
## X113 13 2012 1 742 3.0940027 0.7670125 3.2500000 3.2330247
## X114 14 2013 1 922 2.1900759 0.6302859 2.3333333 2.3020551
## X115 15 2014 1 1204 1.3306340 0.4141566 1.3333333 1.3723202
## X116 16 2015 1 1487 0.4263058 0.2864006 0.4166667 0.4208648
## mad min max range skew kurtosis
## X11 0.000000 4.8333333 4.8333333 0.0000000 NA NA
## X12 0.370650 1.5833333 14.6666667 13.0833333 -0.74743079 -1.6892610
## X13 5.992175 3.3333333 13.6666667 10.3333333 0.02933688 -1.8303679
## X14 1.606150 0.6666667 12.9166667 12.2500000 -0.57176243 -1.5495128
## X15 0.926625 1.1666667 11.9166667 10.7500000 -1.00612693 -0.6902704
## X16 1.111950 0.0000000 10.9166667 10.9166667 -0.72250143 -1.2674157
## X17 0.988400 0.4166667 9.9166667 9.5000000 -1.07570346 -0.4758606
## X18 0.741300 0.0000000 8.9166667 8.9166667 -1.27574746 0.2345301
## X19 0.741300 0.0000000 7.9166667 7.9166667 -1.49460194 0.8460625
## X110 0.864850 0.0000000 6.9166667 6.9166667 -1.37294026 0.5221796
## X111 0.617750 0.0000000 5.9166667 5.9166667 -1.79145247 2.1844618
## X112 0.494200 0.0000000 4.9166667 4.9166667 -1.82058148 2.6078321
## X113 0.494200 0.0000000 3.9166667 3.9166667 -1.82604429 3.3642527
## X114 0.370650 0.0000000 2.9166667 2.9166667 -1.67463537 2.6260787
## X115 0.370650 0.0000000 1.9166667 1.9166667 -0.97996611 1.2579829
## X116 0.370650 0.0000000 0.9166667 0.9166667 0.12436243 -1.1749750
## se
## X11 NA
## X12 3.224077531
## X13 1.427039885
## X14 0.961772573
## X15 0.621857177
## X16 0.557611894
## X17 0.285213333
## X18 0.196696787
## X19 0.150295562
## X110 0.112402967
## X111 0.073218520
## X112 0.046337637
## X113 0.028157915
## X114 0.020757359
## X115 0.011935794
## X116 0.007427086
## [1] 2751
## item group1 vars n mean sd median trimmed mad
## X11 1 2000 1 1 0.0000000 NA 0.0000000 0.0000000 0.000000
## X12 2 2001 1 4 7.0416667 7.0120597 6.7083333 7.0416667 8.401400
## X13 3 2002 1 25 6.5033333 6.0540811 2.5000000 6.4206349 3.335850
## X14 4 2003 1 18 3.3796296 5.0072025 0.9583333 2.9947917 1.050175
## X15 5 2004 1 40 5.0479167 4.9439842 2.0416667 4.8463542 2.903425
## X16 6 2005 1 54 4.3503086 4.2719522 1.7083333 4.1174242 2.285675
## X17 7 2006 1 74 5.0078829 4.0398078 4.7083333 5.0291667 6.486375
## X18 8 2007 1 112 4.7328869 3.6154133 4.4583333 4.8046296 5.745075
## X19 9 2008 1 127 4.2749344 3.0771301 4.7500000 4.3495146 4.077150
## X110 10 2009 1 161 3.8995859 2.7140344 5.2500000 4.0109819 2.223900
## X111 11 2010 1 195 3.3089744 2.2985747 4.3333333 3.4007431 2.223900
## X112 12 2011 1 240 2.8833333 1.7975589 3.9166667 2.9913194 1.235500
## X113 13 2012 1 336 2.2418155 1.3598404 2.9583333 2.3120370 1.173725
## X114 14 2013 1 357 1.6979458 0.9852583 2.0833333 1.7572590 0.864850
## X115 15 2014 1 482 1.0937068 0.5643574 1.1666667 1.1247841 0.617750
## X116 16 2015 1 525 0.3979365 0.2896714 0.3333333 0.3873713 0.370650
## min max range skew kurtosis se
## X11 0.00000000 0.0000000 0.0000000 NA NA NA
## X12 0.50000000 14.2500000 13.7500000 0.03045457 -2.3851378 3.50602986
## X13 0.00000000 13.8333333 13.8333333 0.21167918 -1.9628543 1.21081622
## X14 0.08333333 12.8333333 12.7500000 1.18568524 -0.5526444 1.18020895
## X15 0.00000000 11.8333333 11.8333333 0.33422363 -1.7918197 0.78171254
## X16 0.00000000 10.9166667 10.9166667 0.42874584 -1.6643959 0.58133906
## X17 0.00000000 9.8333333 9.8333333 -0.00374778 -1.7948115 0.46961812
## X18 0.00000000 8.9166667 8.9166667 -0.07806678 -1.8345818 0.34162445
## X19 0.00000000 7.9166667 7.9166667 -0.15853819 -1.7474296 0.27305114
## X110 0.00000000 6.9166667 6.9166667 -0.33537151 -1.6899573 0.21389587
## X111 0.00000000 5.9166667 5.9166667 -0.30473273 -1.6849115 0.16460435
## X112 0.00000000 4.9166667 4.9166667 -0.45477198 -1.5115634 0.11603193
## X113 0.00000000 3.9166667 3.9166667 -0.40991629 -1.4414820 0.07418537
## X114 0.00000000 2.9166667 2.9166667 -0.53315576 -1.2703405 0.05214540
## X115 0.00000000 1.9166667 1.9166667 -0.47500423 -0.8386924 0.02570577
## X116 0.00000000 0.9166667 0.9166667 0.21437922 -1.2163451 0.01264230
## [1] 10007
## item group1 vars n mean sd median trimmed
## X11 1 2000 1 15 14.9222222 0.5321664 15.0833333 14.9487179
## X12 2 2001 1 63 13.0436508 3.4531509 14.2500000 13.9967320
## X13 3 2002 1 122 11.8422131 3.7454565 13.1666667 12.9030612
## X14 4 2003 1 174 10.9631226 3.3284823 12.1666667 11.8619048
## X15 5 2004 1 259 9.9350064 3.3234692 11.2500000 10.8197767
## X16 6 2005 1 332 8.9879518 3.0375609 10.2500000 9.7453008
## X17 7 2006 1 414 8.1050725 2.6939117 9.1666667 8.7735944
## X18 8 2007 1 548 7.2718978 2.4084870 8.2500000 7.8532197
## X19 9 2008 1 614 6.5605320 1.9686920 7.2500000 7.0628388
## X110 10 2009 1 754 5.7393899 1.5529718 6.2500000 6.1207230
## X111 11 2010 1 863 4.7932599 1.4422518 5.2500000 5.1431500
## X112 12 2011 1 929 3.9175637 1.1610983 4.3333333 4.1814318
## X113 13 2012 1 1050 3.0260317 0.9452198 3.3333333 3.2305556
## X114 14 2013 1 1197 2.1032442 0.7801287 2.3333333 2.2367918
## X115 15 2014 1 1341 1.2644171 0.4978179 1.3333333 1.3258776
## X116 16 2015 1 1332 0.3999625 0.2912436 0.3333333 0.3892276
## mad min max range skew kurtosis
## X11 0.61775 13.916667 15.5833333 1.6666667 -0.4882215 -1.1731810
## X12 0.37065 1.166667 14.9166667 13.7500000 -2.5402678 5.0939138
## X13 0.61775 0.000000 13.9166667 13.9166667 -2.4144538 4.3800296
## X14 0.74130 0.000000 12.9166667 12.9166667 -2.2863806 3.8959040
## X15 0.49420 0.000000 11.9166667 11.9166667 -2.2208680 3.3923638
## X16 0.61775 0.000000 10.9166667 10.9166667 -1.9733311 2.3827282
## X17 0.74130 0.000000 9.9166667 9.9166667 -1.9963119 2.6150102
## X18 0.49420 0.000000 8.9166667 8.9166667 -1.9611846 2.4359881
## X19 0.61775 0.000000 7.9166667 7.9166667 -2.1699348 3.4885641
## X110 0.49420 0.000000 6.9166667 6.9166667 -2.4212024 5.1671078
## X111 0.49420 0.000000 5.9166667 5.9166667 -2.1380289 3.5604130
## X112 0.49420 0.000000 4.9166667 4.9166667 -2.0345731 3.3480521
## X113 0.49420 0.000000 3.9166667 3.9166667 -1.9333999 3.0314334
## X114 0.49420 0.000000 2.9166667 2.9166667 -1.4130029 1.0086906
## X115 0.49420 0.000000 1.9166667 1.9166667 -0.9610746 0.3508472
## X116 0.37065 0.000000 0.9166667 0.9166667 0.2137514 -1.1854673
## se
## X11 0.137404769
## X12 0.435056120
## X13 0.339097698
## X14 0.252331591
## X15 0.206510325
## X16 0.166707812
## X17 0.132398536
## X18 0.102885464
## X19 0.079449942
## X110 0.056555897
## X111 0.049094821
## X112 0.038094401
## X113 0.029170116
## X114 0.022548579
## X115 0.013594277
## X116 0.007980024
## [1] 8094
## item group1 vars n mean sd median trimmed
## X11 1 2000 1 13 13.2820513 4.7093212 15.2500000 14.1666667
## X12 2 2001 1 47 12.3581560 4.0371507 14.1666667 13.1837607
## X13 3 2002 1 90 11.2657407 4.0349769 13.0416667 12.2013889
## X14 4 2003 1 144 11.2216435 3.1166951 12.3333333 12.0905172
## X15 5 2004 1 167 10.3822355 2.6684426 11.2500000 11.0864198
## X16 6 2005 1 272 8.7876838 3.1988371 10.1666667 9.5309633
## X17 7 2006 1 289 7.8194925 2.9737796 9.1666667 8.4445637
## X18 8 2007 1 345 7.0045894 2.7381850 8.2500000 7.5737064
## X19 9 2008 1 471 6.1475584 2.3707525 7.2500000 6.6366048
## X110 10 2009 1 569 5.3598418 2.0546839 6.2500000 5.7711524
## X111 11 2010 1 621 4.6298980 1.5502598 5.2500000 4.9523810
## X112 12 2011 1 745 3.6623043 1.3913272 4.2500000 3.9124791
## X113 13 2012 1 865 2.9251445 1.0015783 3.2500000 3.1108706
## X114 14 2013 1 923 2.0811665 0.7780727 2.3333333 2.2095174
## X115 15 2014 1 1173 1.2473714 0.4828535 1.3333333 1.3012957
## X116 16 2015 1 1360 0.3949755 0.2834579 0.3333333 0.3825061
## mad min max range skew kurtosis
## X11 0.370650 1.25000000 15.5833333 14.3333333 -1.7494770 1.3073755
## X12 0.494200 0.00000000 14.9166667 14.9166667 -1.8616069 2.0115736
## X13 0.679525 0.00000000 13.9166667 13.9166667 -1.7780638 1.6943768
## X14 0.494200 0.41666667 12.9166667 12.5000000 -2.5816628 5.3915540
## X15 0.494200 0.08333333 11.9166667 11.8333333 -2.7264030 6.4690347
## X16 0.741300 0.00000000 10.9166667 10.9166667 -1.8201064 1.7540934
## X17 0.741300 0.00000000 9.9166667 9.9166667 -1.6527736 1.1836903
## X18 0.617750 0.00000000 8.9166667 8.9166667 -1.6207744 1.0042703
## X19 0.617750 0.00000000 7.9166667 7.9166667 -1.5748017 0.9644577
## X110 0.617750 0.00000000 6.9166667 6.9166667 -1.5869224 0.9622148
## X111 0.494200 0.00000000 5.9166667 5.9166667 -1.6751411 1.5518152
## X112 0.617750 0.00000000 4.9166667 4.9166667 -1.4233457 0.6429668
## X113 0.494200 0.00000000 3.9166667 3.9166667 -1.5220534 1.2720098
## X114 0.494200 0.00000000 2.9166667 2.9166667 -1.3733708 0.8404641
## X115 0.494200 0.00000000 1.9166667 1.9166667 -0.8949719 0.2688231
## X116 0.370650 0.00000000 0.9166667 0.9166667 0.2806307 -1.0513799
## se
## X11 1.306130708
## X12 0.588878946
## X13 0.425323909
## X14 0.259724590
## X15 0.206490291
## X16 0.193957990
## X17 0.174928209
## X18 0.147418927
## X19 0.109238509
## X110 0.086136832
## X111 0.062209782
## X112 0.050974286
## X113 0.034054685
## X114 0.025610577
## X115 0.014098287
## X116 0.007686331
## [1] 1312
## item group1 vars n mean sd median trimmed mad
## X11 1 2000 1 3 5.0833333 7.9385662 0.500000 5.083333 0.000000
## X12 2 2001 1 7 7.6190476 6.3113392 5.916667 7.619048 8.030750
## X13 3 2002 1 18 8.0787037 5.8365168 10.416667 8.213542 5.065550
## X14 4 2003 1 18 8.7592593 5.1427251 11.791667 9.052083 1.359050
## X15 5 2004 1 36 6.6597222 5.1095295 10.875000 6.802778 1.420825
## X16 6 2005 1 53 5.5974843 4.5687044 6.250000 5.643411 6.301050
## X17 7 2006 1 39 5.8824786 3.8944742 8.333333 6.060606 2.100350
## X18 8 2007 1 69 4.9879227 3.4807558 5.833333 5.074561 4.200700
## X19 9 2008 1 79 4.2858650 3.0871622 4.666667 4.366667 4.077150
## X110 10 2009 1 84 3.8134921 2.4676494 4.083333 3.898284 3.459400
## X111 11 2010 1 113 3.3997050 2.2520427 4.666667 3.494505 1.729700
## X112 12 2011 1 123 2.8604336 1.8398572 3.833333 2.957071 1.482600
## X113 13 2012 1 134 2.4322139 1.2432847 3.000000 2.544753 0.988400
## X114 14 2013 1 157 1.8253715 0.9407190 2.166667 1.913386 0.741300
## X115 15 2014 1 171 1.1530214 0.5500080 1.166667 1.196472 0.617750
## X116 16 2015 1 208 0.4014423 0.2750505 0.375000 0.390873 0.308875
## min max range skew kurtosis se
## X11 0.50000000 14.2500000 13.7500000 0.38490018 -2.3333333 4.58333333
## X12 0.50000000 14.2500000 13.7500000 0.08691345 -2.1263827 2.38546200
## X13 0.08333333 13.9166667 13.8333333 -0.28505468 -1.8614169 1.37568020
## X14 0.00000000 12.8333333 12.8333333 -0.69232173 -1.4943969 1.21215193
## X15 0.00000000 11.9166667 11.9166667 -0.20058282 -1.9204423 0.85158825
## X16 0.00000000 10.9166667 10.9166667 -0.05316921 -1.8783755 0.62755981
## X17 0.00000000 9.8333333 9.8333333 -0.34640948 -1.7115492 0.62361496
## X18 0.00000000 8.9166667 8.9166667 -0.18655038 -1.7919717 0.41903375
## X19 0.00000000 7.9166667 7.9166667 -0.18960012 -1.7425643 0.34733288
## X110 0.00000000 6.9166667 6.9166667 -0.16388037 -1.6645718 0.26924263
## X111 0.00000000 5.9166667 5.9166667 -0.32585411 -1.6921376 0.21185436
## X112 0.00000000 4.9166667 4.9166667 -0.39881135 -1.5707762 0.16589434
## X113 0.00000000 3.9166667 3.9166667 -0.66511742 -1.0695465 0.10740344
## X114 0.00000000 2.9166667 2.9166667 -0.77654935 -0.9243973 0.07507755
## X115 0.00000000 1.9166667 1.9166667 -0.60474181 -0.6060992 0.04206016
## X116 0.00000000 0.9166667 0.9166667 0.31758379 -1.0091003 0.01907132
## [1] 3373
## item group1 vars n mean sd median trimmed
## X11 1 2000 1 2 15.0000000 0.0000000 15.0000000 15.0000000
## X12 2 2001 1 8 6.8750000 6.4406632 3.5833333 6.8750000
## X13 3 2002 1 10 6.9416667 5.9093003 7.5000000 6.9583333
## X14 4 2003 1 27 7.6913580 5.4204531 10.9166667 7.8804348
## X15 5 2004 1 62 8.0766129 4.3051918 10.9166667 8.5666667
## X16 6 2005 1 47 7.3989362 3.8959108 9.8333333 7.7970085
## X17 7 2006 1 93 6.1164875 3.7503852 8.7500000 6.3688889
## X18 8 2007 1 109 5.5145260 3.2126863 7.2500000 5.7106742
## X19 9 2008 1 130 5.2519231 2.8257701 7.0833333 5.5440705
## X110 10 2009 1 177 4.7655367 2.3455178 6.0833333 5.0565268
## X111 11 2010 1 224 3.8232887 1.9563605 5.0000000 4.0226852
## X112 12 2011 1 291 3.3719931 1.5115169 4.1666667 3.5625894
## X113 13 2012 1 390 2.6722222 1.1852350 3.1666667 2.8373397
## X114 14 2013 1 430 1.9443798 0.8522849 2.2500000 2.0513566
## X115 15 2014 1 604 1.2580022 0.4717761 1.3333333 1.3102617
## X116 16 2015 1 769 0.4024707 0.2940239 0.4166667 0.3918152
## mad min max range skew kurtosis
## X11 0.000000 15.00000000 15.0000000 0.0000000 NaN NaN
## X12 3.521175 0.75000000 14.6666667 13.9166667 0.33550940 -2.0210282
## X13 8.833825 0.25000000 13.5000000 13.2500000 -0.01543171 -2.0216641
## X14 2.841650 0.25000000 12.9166667 12.6666667 -0.34245042 -1.8458635
## X15 1.050175 0.08333333 11.9166667 11.8333333 -0.79445584 -1.1111647
## X16 1.359050 0.00000000 10.9166667 10.9166667 -0.82307381 -0.9793109
## X17 1.359050 0.00000000 9.9166667 9.9166667 -0.45007454 -1.6265609
## X18 2.223900 0.00000000 8.9166667 8.9166667 -0.39814366 -1.5765905
## X19 1.111950 0.00000000 7.9166667 7.9166667 -0.72098320 -1.2046739
## X110 0.864850 0.00000000 6.9166667 6.9166667 -0.90994785 -0.8328925
## X111 1.111950 0.00000000 5.9166667 5.9166667 -0.67327189 -1.0686429
## X112 0.864850 0.00000000 4.9166667 4.9166667 -0.91227499 -0.6362036
## X113 0.741300 0.00000000 3.9166667 3.9166667 -1.06085297 -0.2578700
## X114 0.617750 0.00000000 2.9166667 2.9166667 -0.96710630 -0.2703407
## X115 0.370650 0.00000000 1.9166667 1.9166667 -0.89683473 0.3303978
## X116 0.370650 0.00000000 0.9166667 0.9166667 0.17197686 -1.1959179
## se
## X11 0.00000000
## X12 2.27711832
## X13 1.86868484
## X14 1.04316668
## X15 0.54675990
## X16 0.56827699
## X17 0.38889683
## X18 0.30771954
## X19 0.24783644
## X110 0.17629992
## X111 0.13071483
## X112 0.08860669
## X113 0.06001671
## X114 0.04110083
## X115 0.01919630
## X116 0.01060277
## [1] 15810
## item group1 vars n mean sd median trimmed
## X11 1 2000 1 51 9.6388889 7.0359526 15.0000000 10.0772358
## X12 2 2001 1 146 10.3835616 5.5435275 14.0000000 11.0381356
## X13 3 2002 1 223 9.0164425 5.5580343 12.7500000 9.5204842
## X14 4 2003 1 374 9.2653743 4.7722213 12.0833333 9.9330556
## X15 5 2004 1 471 8.5658174 4.3142518 11.0833333 9.1657825
## X16 6 2005 1 636 8.0061583 3.8015767 10.1666667 8.5906863
## X17 7 2006 1 785 7.2599788 3.4319061 9.0833333 7.8003445
## X18 8 2007 1 897 6.4783538 3.0392023 8.1666667 6.9390357
## X19 9 2008 1 1053 5.8186135 2.6250002 7.1666667 6.2492092
## X110 10 2009 1 1144 5.0777244 2.2451841 6.1666667 5.4504185
## X111 11 2010 1 1252 4.3706736 1.8325120 5.1666667 4.6862941
## X112 12 2011 1 1486 3.5810902 1.4612352 4.2500000 3.8271008
## X113 13 2012 1 1596 2.8782895 1.0766159 3.2500000 3.0713354
## X114 14 2013 1 1812 2.0277318 0.8083840 2.2500000 2.1474713
## X115 15 2014 1 1891 1.2708444 0.4883064 1.3333333 1.3299185
## X116 16 2015 1 1993 0.4185483 0.2876103 0.4166667 0.4124347
## mad min max range skew kurtosis se
## X11 0.86485 0 15.6666667 15.6666667 -0.4394575 -1.81869191 0.985230436
## X12 1.11195 0 14.9166667 14.9166667 -0.8481886 -1.06931356 0.458785601
## X13 1.48260 0 13.9166667 13.9166667 -0.6571649 -1.40566244 0.372193507
## X14 0.98840 0 12.9166667 12.9166667 -1.0393957 -0.73650517 0.246765691
## X15 0.98840 0 11.9166667 11.9166667 -1.0168391 -0.74676391 0.198790231
## X16 0.86485 0 10.9166667 10.9166667 -1.1351040 -0.44886427 0.150742320
## X17 0.86485 0 9.9166667 9.9166667 -1.1799383 -0.34569199 0.122489980
## X18 0.86485 0 8.9166667 8.9166667 -1.1454111 -0.39247486 0.101476010
## X19 0.74130 0 7.9166667 7.9166667 -1.2284365 -0.15514855 0.080893784
## X110 0.74130 0 6.9166667 6.9166667 -1.2509971 -0.04121102 0.066380258
## X111 0.74130 0 5.9166667 5.9166667 -1.3247583 0.20067010 0.051789852
## X112 0.61775 0 4.9166667 4.9166667 -1.3085414 0.27475664 0.037906240
## X113 0.49420 0 3.9166667 3.9166667 -1.4506606 0.91154716 0.026949106
## X114 0.49420 0 2.9166667 2.9166667 -1.1865344 0.30935753 0.018990596
## X115 0.49420 0 1.9166667 1.9166667 -0.9562487 0.41036932 0.011229144
## X116 0.37065 0 0.9166667 0.9166667 0.1331035 -1.19023429 0.006442447
## [1] 2071
## item group1 vars n mean sd median trimmed
## X11 1 2000 1 1 15.0833333 NA 15.0833333 15.0833333
## X12 2 2001 1 7 12.2738095 5.3443277 14.0833333 12.2738095
## X13 3 2002 1 7 12.0833333 2.5617377 13.4166667 12.0833333
## X14 4 2003 1 23 10.4746377 3.6034000 12.1666667 11.0131579
## X15 5 2004 1 25 10.0633333 3.7141247 11.5833333 10.8293651
## X16 6 2005 1 41 8.8414634 3.3642733 10.3333333 9.5883838
## X17 7 2006 1 52 7.3573718 3.4537615 9.1666667 7.9126984
## X18 8 2007 1 72 6.6597222 2.9570395 8.1666667 7.1867816
## X19 9 2008 1 96 5.6788194 2.7185732 7.0833333 6.0448718
## X110 10 2009 1 128 5.3580729 2.0337635 6.2500000 5.7363782
## X111 11 2010 1 138 4.8272947 1.4750437 5.3333333 5.1882440
## X112 12 2011 1 209 3.5741627 1.4667849 4.1666667 3.8249507
## X113 13 2012 1 236 3.0716808 0.9138478 3.3750000 3.2614035
## X114 14 2013 1 250 2.0296667 0.7753473 2.2500000 2.1625000
## X115 15 2014 1 356 1.2673221 0.4604596 1.3333333 1.3196387
## X116 16 2015 1 430 0.4044574 0.2892289 0.4166667 0.3948643
## mad min max range skew kurtosis
## X11 0.000000 15.08333333 15.0833333 0.0000000 NA NA
## X12 0.247100 0.16666667 14.6666667 14.5000000 -1.6127063 0.7816982
## X13 0.494200 7.83333333 13.9166667 6.0833333 -0.7726650 -1.4911531
## X14 0.617750 2.83333333 12.9166667 10.0833333 -1.3163970 -0.1541933
## X15 0.494200 0.08333333 11.9166667 11.8333333 -2.1218300 2.7578731
## X16 0.494200 0.41666667 10.9166667 10.5000000 -1.7067668 1.1672779
## X17 0.741300 0.00000000 9.9166667 9.9166667 -1.2322516 -0.2345104
## X18 0.617750 0.08333333 8.9166667 8.8333333 -1.4134617 0.3870985
## X19 0.988400 0.08333333 7.9166667 7.8333333 -1.1179675 -0.4647938
## X110 0.617750 0.00000000 6.9166667 6.9166667 -1.5304521 0.8081577
## X111 0.494200 0.00000000 5.9166667 5.9166667 -2.2293506 3.9125863
## X112 0.617750 0.00000000 4.9166667 4.9166667 -1.3735918 0.4969708
## X113 0.432425 0.00000000 3.9166667 3.9166667 -1.9396044 3.0473382
## X114 0.370650 0.00000000 2.9166667 2.9166667 -1.4252670 1.0198441
## X115 0.370650 0.00000000 1.9166667 1.9166667 -0.9509548 0.6532527
## X116 0.370650 0.00000000 0.9166667 0.9166667 0.1689730 -1.1606098
## se
## X11 NA
## X12 2.01996600
## X13 0.96824584
## X14 0.75136084
## X15 0.74282494
## X16 0.52541122
## X17 0.47895055
## X18 0.34849045
## X19 0.27746322
## X110 0.17976100
## X111 0.12556406
## X112 0.10145963
## X113 0.05948642
## X114 0.04903727
## X115 0.02440431
## X116 0.01394786
## [1] 47067
## item group1 vars n mean sd median trimmed
## X11 1 2000 1 76 11.8026316 5.6964713 15.0833333 12.6518817
## X12 2 2001 1 227 11.6174743 4.8363106 14.0833333 12.5560109
## X13 3 2002 1 422 11.0491706 4.3201427 13.1666667 11.9733728
## X14 4 2003 1 616 10.2195617 3.9381780 12.1666667 11.0543185
## X15 5 2004 1 1135 9.5611601 3.5633420 11.1666667 10.3745875
## X16 6 2005 1 1467 8.9190525 3.0391071 10.2500000 9.6552482
## X17 7 2006 1 1780 8.0466292 2.7428164 9.2500000 8.6986774
## X18 8 2007 1 2204 7.1564958 2.5178313 8.2500000 7.7442366
## X19 9 2008 1 2647 6.3954477 2.1130324 7.2500000 6.8964921
## X110 10 2009 1 3229 5.5849850 1.8006077 6.2500000 6.0169890
## X111 11 2010 1 3808 4.6887693 1.5260534 5.2500000 5.0318788
## X112 12 2011 1 4412 3.8652539 1.2621613 4.3333333 4.1508026
## X113 13 2012 1 5117 3.0147385 0.9827431 3.3333333 3.2248067
## X114 14 2013 1 5665 2.1314063 0.7498012 2.3333333 2.2714354
## X115 15 2014 1 6681 1.2748092 0.4768585 1.3333333 1.3361397
## X116 16 2015 1 7581 0.4035308 0.2938067 0.4166667 0.3937345
## mad min max range skew kurtosis se
## X11 0.61775 0 15.8333333 15.8333333 -1.1779759 -0.4291945 0.653430075
## X12 0.74130 0 14.9166667 14.9166667 -1.4903066 0.5624016 0.320997206
## X13 0.74130 0 13.9166667 13.9166667 -1.6262512 1.0034717 0.210301256
## X14 0.74130 0 12.9166667 12.9166667 -1.6000670 0.9832322 0.158673713
## X15 0.61775 0 11.9166667 11.9166667 -1.7549313 1.4866455 0.105769287
## X16 0.61775 0 10.9166667 10.9166667 -1.9167504 2.2357118 0.079347079
## X17 0.61775 0 9.9166667 9.9166667 -1.8664227 2.0791928 0.065010982
## X18 0.49420 0 8.9166667 8.9166667 -1.8260935 1.8826980 0.053631610
## X19 0.61775 0 7.9166667 7.9166667 -1.9288946 2.4466829 0.041070425
## X110 0.49420 0 6.9166667 6.9166667 -2.0044366 2.7759574 0.031687288
## X111 0.49420 0 5.9166667 5.9166667 -1.8743631 2.3454865 0.024729837
## X112 0.49420 0 4.9166667 4.9166667 -1.9031351 2.5647548 0.019001904
## X113 0.49420 0 3.9166667 3.9166667 -1.8394490 2.5103369 0.013738278
## X114 0.49420 0 2.9166667 2.9166667 -1.5769186 1.6716638 0.009961991
## X115 0.37065 0 1.9166667 1.9166667 -1.0365136 0.6951526 0.005834032
## X116 0.37065 0 0.9166667 0.9166667 0.1720125 -1.2146785 0.003374415
##
## Call:
## lm(formula = survivalYears ~ yearDiagnosis, data = cancerType)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.8860 -0.2762 0.1405 0.5572 3.1973
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.568e+03 1.178e+01 133.0 <2e-16 ***
## yearDiagnosis -7.777e-01 5.855e-03 -132.8 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.212 on 6185 degrees of freedom
## Multiple R-squared: 0.7404, Adjusted R-squared: 0.7404
## F-statistic: 1.764e+04 on 1 and 6185 DF, p-value: < 2.2e-16H0: There is no evidence that Breast Cancer Survival Years are improving as Diagnosis Year increases.
H1: There is sufficient evidence that Breast Cancer Survival Years are improving as Diagnosis Year increases.
##
## Call:
## lm(formula = survivalYears ~ yearDiagnosis, data = cancerType)
##
## Residuals:
## Min 1Q Median 3Q Max
## -7.6980 -0.9995 -0.0329 1.0674 7.0685
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 940.81931 25.60226 36.75 <2e-16 ***
## yearDiagnosis -0.46656 0.01273 -36.66 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.071 on 2749 degrees of freedom
## Multiple R-squared: 0.3284, Adjusted R-squared: 0.3281
## F-statistic: 1344 on 1 and 2749 DF, p-value: < 2.2e-16H0: There is no evidence that Digestive Cancer Survival Years are improving as Diagnosis Year increases.
H1: There is sufficient evidence that Digestive Cancer Survival Years are improving as Diagnosis Year increases.
##
## Call:
## lm(formula = survivalYears ~ yearDiagnosis, data = cancerType)
##
## Residuals:
## Min 1Q Median 3Q Max
## -11.7591 -0.1415 0.3572 0.7752 2.2832
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.762e+03 9.303e+00 189.4 <2e-16 ***
## yearDiagnosis -8.743e-01 4.626e-03 -189.0 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.608 on 10005 degrees of freedom
## Multiple R-squared: 0.7812, Adjusted R-squared: 0.7811
## F-statistic: 3.572e+04 on 1 and 10005 DF, p-value: < 2.2e-16H0: There is no evidence that Male Genital Cancer Survival Years are improving as Diagnosis Year increases.
H1: There is sufficient evidence that Male Genital Cancer Survival Years are improving as Diagnosis Year increases.
##
## Call:
## lm(formula = survivalYears ~ yearDiagnosis, data = cancerType)
##
## Residuals:
## Min 1Q Median 3Q Max
## -12.2799 -0.1660 0.3601 0.8415 2.6368
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.717e+03 1.084e+01 158.5 <2e-16 ***
## yearDiagnosis -8.519e-01 5.388e-03 -158.1 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.682 on 8092 degrees of freedom
## Multiple R-squared: 0.7555, Adjusted R-squared: 0.7555
## F-statistic: 2.5e+04 on 1 and 8092 DF, p-value: < 2.2e-16H0: There is no evidence that Female Genital Cancer Survival Years are improving as Diagnosis Year increases.
H1: There is sufficient evidence that Female Genital Cancer Survival Years are improving as Diagnosis Year increases.