## Results from MAXQDA coding have been exported into an excel sheet and each analysis collated into one
## database 'NEW' from which the following exploratory analysis is conducted
setwd("C:\\Users\\Rhonda\\Desktop\\CC\\Thesis\\Analysis\\Results") # laptop
library(xtable)
library(dplyr)
## Warning: package 'dplyr' was built under R version 3.4.4
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(RColorBrewer)
Data <- read.csv("NEW.csv")
## Labels for newspaper name
PaperLabel <- c('Farmers Journal', 'Irish Times', 'Independent', 'The Journal') ## PaperName
Data$PaperName <- PaperLabel[Data$Paper]
## Labels for article tone
Data$Tone <- 'Neg' ## Tone
Data$Tone[which(Data$Positive == 1)] <- 'Pos'
Data$Tone[which(Data$Neutral == 1)] <- 'Neu'
## labels for article period
PeriodLabel <- c("Before","During","After") ## Period
Data$PeriodName <- PeriodLabel[Data$Period]
## labels for article scale - reliance upon evidence
ScaleLabel <- c("None","Low","Medium", "High", "Very High") ## Reliance upon evidence (scale)
Data$ScaleName <- ScaleLabel[Data$Scale]
### Separating time periods
Before <- Data[which(Data$PeriodName == 'Before'),] ## Calls only the data relevant to March-May 2017
During <- Data[which(Data$PeriodName == 'During'),] ## Calls only the data relevant to Sept-Nov (inclusive) 2017
After <- Data[which(Data$PeriodName == 'After'),] ## Calls only the data relevant to Dec 2017 - May 2018
### Separating media sources
FJ <- Data[which(Data$PaperName == 'Farmers Journal'),] ## Calls only the data relevant to the Farmers Journal
IT <- Data[which(Data$PaperName == 'Irish Times'),] ## Calls only the data relevant to the Irish Times
Ind <- Data[which(Data$PaperName == 'Independent'),] ## Calls only the data relevant to the Irish Independent
TJ <- Data[which(Data$PaperName == 'The Journal'),] ## Calls only the data relevant to The Journal
## Action codes from variables
N <- nrow(Data) ## Action coding
Data$ActionCode <- rep(NA,N)
for(i in 1:N) Data$ActionCode[i] <- paste(Data[i,4],Data[i,5],Data[i,6],Data[i,7],Data[i,8],
Data[i,9],Data[i,10],Data[i,11],Data[i,12],Data[i,13],
Data[i,14],Data[i,15],sep="")
cumsum((sort(table(Data$ActionCode),decreasing=T))) ## Decreasing values by cumulative sum
## 000000000000 000010000000 000000001000 000000000100 000100000000
## 292 348 402 447 491
## 000000000001 000000100000 001000000000 100000000000 000000010000
## 522 550 571 592 607
## 000000000010 100000001000 000000110000 000000101000 000000001100
## 617 626 633 639 644
## 001000000100 110000000000 000000000011 000001000000 110000001000
## 649 654 658 662 666
## 000000000101 000000001001 000010001000 000100000100 000100100000
## 669 672 675 678 681
## 001000000001 001000100000 001100000000 010000000001 100000000001
## 684 687 690 693 696
## 100000001110 100000100000 000010100000 000100001000 010010000000
## 699 702 704 706 708
## 100000000010 110000000111 000000001010 000000001011 000000001111
## 710 712 713 714 715
## 000000010010 000000100001 000000100010 000000100100 000000101001
## 716 717 718 719 720
## 000001000100 000010000010 000010000011 000010000111 000100000001
## 721 722 723 724 725
## 000101000000 000110000000 001000001001 001000001101 001000001111
## 726 727 728 729 730
## 010000000000 010000000010 011000001111 100000000011 100000000100
## 731 732 733 734 735
## 100000000101 100000000110 100000000111 100000010000 100000011000
## 736 737 738 739 740
## 100000100100 100001000001 100100001000 100100100000 101000000000
## 741 742 743 744 745
## 110000000001 110000000010
## 746 747
100*cumsum((sort(table(Data$ActionCode),decreasing=T)))/747 ## Decreasing percentage by cumulative sum
## 000000000000 000010000000 000000001000 000000000100 000100000000
## 39.08969 46.58635 53.81526 59.83936 65.72959
## 000000000001 000000100000 001000000000 100000000000 000000010000
## 69.87952 73.62784 76.43909 79.25033 81.25837
## 000000000010 100000001000 000000110000 000000101000 000000001100
## 82.59705 83.80187 84.73896 85.54217 86.21151
## 001000000100 110000000000 000000000011 000001000000 110000001000
## 86.88086 87.55020 88.08568 88.62115 89.15663
## 000000000101 000000001001 000010001000 000100000100 000100100000
## 89.55823 89.95984 90.36145 90.76305 91.16466
## 001000000001 001000100000 001100000000 010000000001 100000000001
## 91.56627 91.96787 92.36948 92.77108 93.17269
## 100000001110 100000100000 000010100000 000100001000 010010000000
## 93.57430 93.97590 94.24364 94.51138 94.77912
## 100000000010 110000000111 000000001010 000000001011 000000001111
## 95.04685 95.31459 95.44846 95.58233 95.71620
## 000000010010 000000100001 000000100010 000000100100 000000101001
## 95.85007 95.98394 96.11780 96.25167 96.38554
## 000001000100 000010000010 000010000011 000010000111 000100000001
## 96.51941 96.65328 96.78715 96.92102 97.05489
## 000101000000 000110000000 001000001001 001000001101 001000001111
## 97.18876 97.32262 97.45649 97.59036 97.72423
## 010000000000 010000000010 011000001111 100000000011 100000000100
## 97.85810 97.99197 98.12584 98.25971 98.39357
## 100000000101 100000000110 100000000111 100000010000 100000011000
## 98.52744 98.66131 98.79518 98.92905 99.06292
## 100000100100 100001000001 100100001000 100100100000 101000000000
## 99.19679 99.33066 99.46452 99.59839 99.73226
## 110000000001 110000000010
## 99.86613 100.00000
CodeList <- names(sort(table(Data$ActionCode),decreasing=T)) ## Provides a code list, needs to be transformed from numbers to names
nCode <- length(CodeList)
ActionType <- rep("Mixed",nCode) ## Changing the code list from numbers to names
ActionType[1:11] <- c("None","Other","Policy","Agriculture","Impacts","Energy",
"Communication","C.Assembly","Action","Arts","Transport")
ActionType[12:15] <- c("Mixed")
ActionType[16] <- c("C.Assembly")
ActionType[17] <- c("Funding")
ActionType[18] <- c("Mixed")
ActionType[19] <- c("Health")
ActionType[20] <- c("Funding")
ActionType[21:25] <- c("Mixed")
ActionType[26:28] <- c("C.Assembly")
ActionType[29] <- c("Funding")
ActionType[30:34] <- c("Mixed")
ActionType[35] <- c("Funding")
ActionType[36] <- c("Mixed")
ActionType[37] <- c("Funding")
ActionType[38:52] <- c("Mixed")
ActionType[53:55] <- c("C.Assembly")
ActionType[56:58] <- c("Funding")
ActionType[59:69] <- c("Action")
ActionType[70] <- c("C.Assembly")
ActionType[71:72] <- c("Action")
x.lkp <-match(Data$ActionCode,CodeList)
Data$ActionLabel <- ActionType[x.lkp]
table(Data$PaperName, Data$ActionLabel)
##
## Action Agriculture Arts C.Assembly Communication Energy
## Farmers Journal 7 14 0 10 9 6
## Independent 10 23 3 15 8 11
## Irish Times 14 8 9 11 8 11
## The Journal 3 0 3 3 3 3
##
## Funding Health Impacts Mixed None Other Policy Transport
## Farmers Journal 0 0 1 11 32 10 19 0
## Independent 0 2 13 30 100 17 5 6
## Irish Times 13 0 16 29 130 16 24 0
## The Journal 6 2 14 6 30 13 6 4
ActionType2 <- ActionType ## ONLY use DataAction for exploring action codes
ActionType2[1] <- NA
Data$ActionLabel2 <- ActionType2[x.lkp]
DataAction <- Data[- which(Data$ActionLabel == 'None'),] ## Remove all values in database that are zero, and therefore do not refer to any action code
table(DataAction$PaperName, DataAction$ActionLabel)
##
## Action Agriculture Arts C.Assembly Communication Energy
## Farmers Journal 7 14 0 10 9 6
## Independent 10 23 3 15 8 11
## Irish Times 14 8 9 11 8 11
## The Journal 3 0 3 3 3 3
##
## Funding Health Impacts Mixed Other Policy Transport
## Farmers Journal 0 0 1 11 10 19 0
## Independent 0 2 13 30 17 5 6
## Irish Times 13 0 16 29 16 24 0
## The Journal 6 2 14 6 13 6 4
###################################################
### Code listed according to location in thesis ###
###################################################
### Chapter 5.4 Pooled Analysis ###
## 5.4.1 Tone of Language
table(Data$Tone, Data$PaperName) ## Tone by PaperName
##
## Farmers Journal Independent Irish Times The Journal
## Neg 64 172 196 65
## Neu 43 36 57 12
## Pos 12 35 36 19
chisq.test(table(Data$Tone, Data$PaperName)) ## Chi Square Test
##
## Pearson's Chi-squared test
##
## data: table(Data$Tone, Data$PaperName)
## X-squared = 29.479, df = 6, p-value = 4.937e-05
chisq.test(table(Data$Tone, Data$PaperName))$stdres ## Standardised residuals
##
## Farmers Journal Independent Irish Times The Journal
## Neg -3.21499516 1.70890149 0.59226898 0.26146500
## Neu 4.87192069 -2.37958196 -0.04869582 -1.92554026
## Pos -1.23718310 0.41379135 -0.75740334 1.87588243
## 5.4.2 Reliance on Evidence
table(Data$ScaleName, Data$PaperName) ## ScaleName by PaperName
##
## Farmers Journal Independent Irish Times The Journal
## High 31 50 77 24
## Low 25 55 76 20
## Medium 46 66 61 17
## None 10 55 68 20
## Very High 7 17 7 15
chisq.test(table(Data$ScaleName, Data$PaperName)) ## Chi square test
##
## Pearson's Chi-squared test
##
## data: table(Data$ScaleName, Data$PaperName)
## X-squared = 47.84, df = 12, p-value = 3.332e-06
chisq.test(table(Data$ScaleName, Data$PaperName))$stdres ## Standardised residuals
##
## Farmers Journal Independent Irish Times The Journal
## High 0.46735696 -1.67462606 1.15284810 0.15546732
## Low -0.71559468 -0.41462131 1.40005385 -0.67457253
## Medium 3.61172257 0.75189856 -2.15754862 -1.86216407
## None -3.56082814 1.01189441 1.63945533 0.09138939
## Very High -0.13640653 0.66150508 -3.37400007 4.13334898
## 5.4.3 Relationship between tone and reliance on evidence
table(Data$ScaleName, Data$Tone) ## Tone vs. Scale
##
## Neg Neu Pos
## High 87 44 51
## Low 156 17 3
## Medium 75 77 38
## None 152 0 1
## Very High 27 10 9
chisq.test(table(Data$ScaleName, Data$Tone)) ## Chi square test
##
## Pearson's Chi-squared test
##
## data: table(Data$ScaleName, Data$Tone)
## X-squared = 222.71, df = 8, p-value < 2.2e-16
chisq.test(table(Data$ScaleName, Data$Tone))$stdres ## Standardised Residuals
##
## Neg Neu Pos
## High -6.1573787 1.6980765 6.4906679
## Low 7.1077693 -3.8653638 -5.2809226
## Medium -9.1536747 8.2955310 2.9499041
## None 9.6458205 -6.8949360 -5.2520760
## Very High -1.1628147 0.3384045 1.2051812
### Chapter 5.5 Individual Analysis ###
## 5.5.1 Tone of language per period and per paper
table(Before$Tone, Before$PaperName) ## BEFORE Tone by PaperName
##
## Farmers Journal Independent Irish Times The Journal
## Neg 14 37 42 14
## Neu 6 2 17 4
## Pos 5 1 10 8
chisq.test(table(Before$Tone, Before$PaperName)) ## Chi square test
## Warning in chisq.test(table(Before$Tone, Before$PaperName)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(Before$Tone, Before$PaperName)
## X-squared = 20.307, df = 6, p-value = 0.002441
chisq.test(table(Before$Tone, Before$PaperName))$stdres ## Standardised Residuals
## Warning in chisq.test(table(Before$Tone, Before$PaperName)): Chi-squared
## approximation may be incorrect
##
## Farmers Journal Independent Irish Times The Journal
## Neg -1.2577159 3.9760643 -1.4053952 -1.5423764
## Neu 0.8301495 -2.4881927 1.8621257 -0.3963612
## Pos 0.7622159 -2.5565500 -0.1564688 2.4606491
table(During$Tone, During$PaperName) ## DURING Tone by PaperName
##
## Farmers Journal Independent Irish Times The Journal
## Neg 33 91 117 41
## Neu 22 26 30 3
## Pos 6 25 22 7
chisq.test(table(During$Tone, During$PaperName)) ## Chi square test
##
## Pearson's Chi-squared test
##
## data: table(During$Tone, During$PaperName)
## X-squared = 19.378, df = 6, p-value = 0.00357
chisq.test(table(During$Tone, During$PaperName))$stdres ## Standardised Residuals
##
## Farmers Journal Independent Irish Times The Journal
## Neg -2.2509395 -0.8008488 0.9125115 2.2172666
## Neu 3.6297747 -0.3117797 -0.5958266 -2.5676019
## Pos -1.0522402 1.4336916 -0.5609796 -0.1001659
table(After$Tone, After$PaperName) ## AFTER Tone by PaperName
##
## Farmers Journal Independent Irish Times The Journal
## Neg 17 44 37 10
## Neu 15 8 10 5
## Pos 1 9 4 4
chisq.test(table(After$Tone, After$PaperName)) ## Chi square test
## Warning in chisq.test(table(After$Tone, After$PaperName)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(After$Tone, After$PaperName)
## X-squared = 17.247, df = 6, p-value = 0.008417
chisq.test(table(After$Tone, After$PaperName))$stdres ## Standardised Residuals
## Warning in chisq.test(table(After$Tone, After$PaperName)): Chi-squared
## approximation may be incorrect
##
## Farmers Journal Independent Irish Times The Journal
## Neg -1.9435026 1.3046444 1.2147300 -1.2925652
## Neu 3.3946855 -2.3488717 -0.7265020 0.3455494
## Pos -1.6337480 1.1912900 -0.8621567 1.4944386
## Each media Sources for the entire period ##
table(FJ$Tone, FJ$PeriodName) ## Farmers Journal
##
## After Before During
## Neg 17 14 33
## Neu 15 6 22
## Pos 1 5 6
chisq.test(table(FJ$Tone, FJ$PeriodName)) ## Chi square test
## Warning in chisq.test(table(FJ$Tone, FJ$PeriodName)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(FJ$Tone, FJ$PeriodName)
## X-squared = 5.9373, df = 4, p-value = 0.2039
table(IT$Tone, IT$PeriodName) ## Irish Times
##
## After Before During
## Neg 37 42 117
## Neu 10 17 30
## Pos 4 10 22
chisq.test(table(IT$Tone, IT$PeriodName)) ## Chi square test
##
## Pearson's Chi-squared test
##
## data: table(IT$Tone, IT$PeriodName)
## X-squared = 3.0314, df = 4, p-value = 0.5526
table(Ind$Tone, Ind$PeriodName) ## Irish Independent
##
## After Before During
## Neg 44 37 91
## Neu 8 2 26
## Pos 9 1 25
chisq.test(table(Ind$Tone, Ind$PeriodName)) ## Chi square test
##
## Pearson's Chi-squared test
##
## data: table(Ind$Tone, Ind$PeriodName)
## X-squared = 12.423, df = 4, p-value = 0.01447
chisq.test(table(Ind$Tone, Ind$PeriodName))$stdres ## Standardised Residuals
##
## After Before During
## Neg 0.26775595 3.30460806 -2.72210470
## Neu -0.43188353 -1.91177630 1.81848265
## Pos 0.09016546 -2.34580977 1.68575659
table(TJ$Tone, TJ$PeriodName) ## The Journal
##
## After Before During
## Neg 10 14 41
## Neu 5 4 3
## Pos 4 8 7
chisq.test(table(TJ$Tone, TJ$PeriodName)) ## Chi square test
## Warning in chisq.test(table(TJ$Tone, TJ$PeriodName)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(TJ$Tone, TJ$PeriodName)
## X-squared = 9.9953, df = 4, p-value = 0.04051
chisq.test(table(TJ$Tone, TJ$PeriodName))$stdres ## Standardised Residuals
## Warning in chisq.test(table(TJ$Tone, TJ$PeriodName)): Chi-squared
## approximation may be incorrect
##
## After Before During
## Neg -1.5693096 -1.7702659 2.8294260
## Neu 2.0332170 0.5208374 -2.0871757
## Pos 0.1540349 1.6452364 -1.5881026
## 5.5.1 Reliance on Evidence
table(Data$ScaleName, Data$PaperName) ## ScaleName by PaperName
##
## Farmers Journal Independent Irish Times The Journal
## High 31 50 77 24
## Low 25 55 76 20
## Medium 46 66 61 17
## None 10 55 68 20
## Very High 7 17 7 15
chisq.test(table(Data$ScaleName, Data$PaperName)) ## Chi square test
##
## Pearson's Chi-squared test
##
## data: table(Data$ScaleName, Data$PaperName)
## X-squared = 47.84, df = 12, p-value = 3.332e-06
chisq.test(table(Data$ScaleName, Data$PaperName))$stdres ## Standardised Residuals
##
## Farmers Journal Independent Irish Times The Journal
## High 0.46735696 -1.67462606 1.15284810 0.15546732
## Low -0.71559468 -0.41462131 1.40005385 -0.67457253
## Medium 3.61172257 0.75189856 -2.15754862 -1.86216407
## None -3.56082814 1.01189441 1.63945533 0.09138939
## Very High -0.13640653 0.66150508 -3.37400007 4.13334898
# Per Period:
chisq.test(table(Before$ScaleName, Before$PaperName)) ## BEFORE ScaleName by PaperName
## Warning in chisq.test(table(Before$ScaleName, Before$PaperName)): Chi-
## squared approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(Before$ScaleName, Before$PaperName)
## X-squared = 13.64, df = 12, p-value = 0.3243
chisq.test(table(During$ScaleName, During$PaperName)) ## DURING ScaleName by PaperName
## Warning in chisq.test(table(During$ScaleName, During$PaperName)): Chi-
## squared approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(During$ScaleName, During$PaperName)
## X-squared = 50.51, df = 12, p-value = 1.137e-06
chisq.test(table(After$ScaleName, After$PaperName)) ## AFTER ScaleName by PaperName
## Warning in chisq.test(table(After$ScaleName, After$PaperName)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(After$ScaleName, After$PaperName)
## X-squared = 30.62, df = 12, p-value = 0.002251
chisq.test(table(During$ScaleName, During$PaperName))$stdres ## Standardised Residuals DURING
## Warning in chisq.test(table(During$ScaleName, During$PaperName)): Chi-
## squared approximation may be incorrect
##
## Farmers Journal Independent Irish Times The Journal
## High -0.44909333 -2.38303819 3.23372990 -0.92366435
## Low 0.43123594 -1.20679810 1.43794401 -0.87803586
## Medium 2.88291586 1.89493819 -2.93011188 -1.45091123
## None -3.26543533 1.10767907 0.31807406 1.43807904
## Very High 0.06023293 1.23670174 -3.56839613 3.50905701
chisq.test(table(After$ScaleName, After$PaperName))$stdres ## Standardised Residuals AFTER
## Warning in chisq.test(table(After$ScaleName, After$PaperName)): Chi-squared
## approximation may be incorrect
##
## Farmers Journal Independent Irish Times The Journal
## High 1.8715774 1.4316735 -3.2918650 0.2545829
## Low -1.2544640 -0.1334052 0.1207213 1.5982736
## Medium 2.0097889 -1.2001194 0.4729577 -1.3892496
## None -1.3027434 0.1874287 2.3266796 -2.0162744
## Very High -1.8059764 -0.2875011 0.1737952 2.4450766
## Assess reliance on evidence for each media source over the entire period
chisq.test(table(FJ$ScaleName, FJ$PeriodName)) ## Farmers Journal
## Warning in chisq.test(table(FJ$ScaleName, FJ$PeriodName)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(FJ$ScaleName, FJ$PeriodName)
## X-squared = 8.9503, df = 8, p-value = 0.3465
chisq.test(table(IT$ScaleName, IT$PeriodName)) ## Irish Times
## Warning in chisq.test(table(IT$ScaleName, IT$PeriodName)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(IT$ScaleName, IT$PeriodName)
## X-squared = 29.235, df = 8, p-value = 0.0002884
chisq.test(table(Ind$ScaleName, Ind$PeriodName)) ## Irish Independent
## Warning in chisq.test(table(Ind$ScaleName, Ind$PeriodName)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(Ind$ScaleName, Ind$PeriodName)
## X-squared = 7.8011, df = 8, p-value = 0.4531
chisq.test(table(TJ$ScaleName, TJ$PeriodName)) ## The Journal
## Warning in chisq.test(table(TJ$ScaleName, TJ$PeriodName)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(TJ$ScaleName, TJ$PeriodName)
## X-squared = 12.094, df = 8, p-value = 0.1471
chisq.test(table(IT$ScaleName, IT$PeriodName))$stdres ## Standardised Residuals Irish Times
## Warning in chisq.test(table(IT$ScaleName, IT$PeriodName)): Chi-squared
## approximation may be incorrect
##
## After Before During
## High -4.04461520 -1.05618160 4.04285856
## Low 0.20617105 -0.04554762 -0.12009594
## Medium 0.84523122 0.82367020 -1.36652120
## None 2.18259851 0.57402739 -2.18517994
## Very High 2.77490781 -0.60247800 -1.62553658
## 5.5.1 Relationship between tone and reliance on evidence, Individual Analysis
chisq.test(table(FJ$ScaleName, FJ$Tone)) ## Farmers Journal
## Warning in chisq.test(table(FJ$ScaleName, FJ$Tone)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(FJ$ScaleName, FJ$Tone)
## X-squared = 43.893, df = 8, p-value = 5.96e-07
chisq.test(table(FJ$ScaleName, FJ$Tone))$stdres
## Warning in chisq.test(table(FJ$ScaleName, FJ$Tone)): Chi-squared
## approximation may be incorrect
##
## Neg Neu Pos
## High -0.7005402 -0.5224519 1.9934020
## Low 3.8611440 -2.8263307 -1.8839887
## Medium -2.9222774 3.6749912 -1.0244369
## None 3.0630324 -2.4853506 -1.1065192
## Very High -2.9418609 1.1926485 2.9682166
chisq.test(table(IT$ScaleName, IT$Tone)) ## Irish Times
## Warning in chisq.test(table(IT$ScaleName, IT$Tone)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(IT$ScaleName, IT$Tone)
## X-squared = 96.395, df = 8, p-value < 2.2e-16
chisq.test(table(IT$ScaleName, IT$Tone))$stdres
## Warning in chisq.test(table(IT$ScaleName, IT$Tone)): Chi-squared
## approximation may be incorrect
##
## Neg Neu Pos
## High -4.6201250 1.2750752 4.9995901
## Low 3.8487593 -2.0112589 -3.0212889
## Medium -5.9769547 5.7850467 1.4847680
## None 6.1987781 -4.6741288 -3.1371802
## Very High 1.0259222 -0.3660047 -1.0103326
chisq.test(table(Ind$ScaleName, Ind$Tone)) ## Irish Independent
## Warning in chisq.test(table(Ind$ScaleName, Ind$Tone)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(Ind$ScaleName, Ind$Tone)
## X-squared = 80.106, df = 8, p-value = 4.654e-14
chisq.test(table(Ind$ScaleName, Ind$Tone))$stdres
## Warning in chisq.test(table(Ind$ScaleName, Ind$Tone)): Chi-squared
## approximation may be incorrect
##
## Neg Neu Pos
## High -2.57900637 0.26470707 3.07244299
## Low 4.06875493 -2.22158919 -3.02206060
## Medium -6.56998456 4.15011092 4.31041442
## None 5.41714559 -3.51618433 -3.45866032
## Very High -0.01820627 1.75673133 -1.75378250
chisq.test(table(TJ$ScaleName, TJ$Tone)) ## The Journal
## Warning in chisq.test(table(TJ$ScaleName, TJ$Tone)): Chi-squared
## approximation may be incorrect
##
## Pearson's Chi-squared test
##
## data: table(TJ$ScaleName, TJ$Tone)
## X-squared = 34.169, df = 8, p-value = 3.786e-05
chisq.test(table(TJ$ScaleName, TJ$Tone))$stdres
## Warning in chisq.test(table(TJ$ScaleName, TJ$Tone)): Chi-squared
## approximation may be incorrect
##
## Neg Neu Pos
## High -4.1586407 2.8507866 2.5142111
## Low 2.3961835 -0.3799486 -2.4967511
## Medium -0.8636307 0.7073700 0.4263883
## None 3.4711069 -1.8997428 -2.4967511
## Very High -0.6950770 -1.5936381 2.1385446
### END ###