comparaison IgG3 Exces VS normaux-deficit

Evaluation des conditions de validité:Normalité pour les données IgG 2 deficit Vs Normaux + Excès

la normalité va nous permettre de choisir le type de test pour comparer les données Un test de shapiro pour valider la normalité si la p-value est<0.05 la normalité n’est pas accepté on fait donc un test de Wilcoxon Si la normalité est respecté on fait le test de Student

Age à l’inclusion

shapiro.test(Ig$age_inclusion[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$age_inclusion[Ig$IgG3_Exces == "Oui"]
## W = 0.91391, p-value = 0.04941

la normalité est acceptée: T-test de Student

shapiro.test(Ig$age_inclusion[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$age_inclusion[Ig$IgG3_Exces == "Non"]
## W = 0.97336, p-value = 0.00021

Student

IMC

shapiro.test(Ig$IMC[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$IMC[Ig$IgG3_Exces == "Oui"]
## W = 0.93305, p-value = 0.2723

Wilcoxon

shapiro.test(Ig$IMC[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$IMC[Ig$IgG3_Exces == "Non"]
## W = 0.84363, p-value = 1.956e-11

Student

Nombre d’exacerbation sans biotherapie

shapiro.test(Ig$Nb_Exa_an.sans_biotherapie[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Nb_Exa_an.sans_biotherapie[Ig$IgG3_Exces == "Oui"]
## W = 0.63661, p-value = 3.379e-06

Student

shapiro.test(Ig$Nb_Exa_an.sans_biotherapie[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Nb_Exa_an.sans_biotherapie[Ig$IgG3_Exces == "Non"]
## W = 0.3831, p-value < 2.2e-16

Student

Dose de corticoides systemiques

shapiro.test(Ig$Corticoïde.systémique..dose.[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Corticoïde.systémique..dose.[Ig$IgG3_Exces == "Oui"]
## W = 0.51425, p-value = 1.793e-07

Student

shapiro.test(Ig$Corticoïde.systémique..dose.[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Corticoïde.systémique..dose.[Ig$IgG3_Exces == "Non"]
## W = 0.52324, p-value < 2.2e-16

Student

CSI

shapiro.test(Ig$CSI_µg[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$CSI_µg[Ig$IgG3_Exces == "Oui"]
## W = 0.86595, p-value = 0.005368

la normalité est acceptée : T de Student

shapiro.test(Ig$CSI_µg[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$CSI_µg[Ig$IgG3_Exces == "Non"]
## W = 0.87403, p-value = 1.134e-12

student

Montélukast

shapiro.test(Ig$Montélukast[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Montélukast[Ig$IgG3_Exces == "Oui"]
## W = 0.63917, p-value = 2.502e-06

Student

shapiro.test(Ig$Montélukast[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Montélukast[Ig$IgG3_Exces == "Non"]
## W = 0.60566, p-value < 2.2e-16

student

Réponse Biotherapie

shapiro.test(Ig$Rep_biotherapie_GETE[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Rep_biotherapie_GETE[Ig$IgG3_Exces == "Oui"]
## W = 0.48412, p-value = 6.065e-08

la normalité est acceptée : t-test de Student

shapiro.test(Ig$Rep_biotherapie_GETE[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Rep_biotherapie_GETE[Ig$IgG3_Exces == "Non"]
## W = 0.65893, p-value < 2.2e-16

Student

VEMS pre B2 (litre)

shapiro.test(Ig$VEMS_pre_B2_L[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$VEMS_pre_B2_L[Ig$IgG3_Exces == "Oui"]
## W = 0.94908, p-value = 0.3534

Wilcoxon

shapiro.test(Ig$VEMS_pre_B2_L[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$VEMS_pre_B2_L[Ig$IgG3_Exces == "Non"]
## W = 0.97651, p-value = 0.001829

student

VEMS pre B2 (%)

shapiro.test(Ig$VEMS_PreB2_Pct[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$VEMS_PreB2_Pct[Ig$IgG3_Exces == "Oui"]
## W = 0.87331, p-value = 0.01344

la normalité est acceptée : t-test de Student

shapiro.test(Ig$VEMS_PreB2_Pct[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$VEMS_PreB2_Pct[Ig$IgG3_Exces == "Non"]
## W = 0.98155, p-value = 0.008136

Student

Tiffe

shapiro.test(Ig$Tiffenau[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Tiffenau[Ig$IgG3_Exces == "Oui"]
## W = 0.98204, p-value = 0.9576

Wilcoxon

shapiro.test(Ig$Tiffenau[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Tiffenau[Ig$IgG3_Exces == "Non"]
## W = 0.98833, p-value = 0.09569

Wilcoxon

FeNO

shapiro.test(Ig$FeNo[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$FeNo[Ig$IgG3_Exces == "Non"]
## W = 0.79489, p-value = 4.306e-12

Student

shapiro.test(Ig$FeNo[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$FeNo[Ig$IgG3_Exces == "Oui"]
## W = 0.73914, p-value = 0.002632

Student

PNE G/L

shapiro.test(Ig$PNE_G_L[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$PNE_G_L[Ig$IgG3_Exces == "Oui"]
## W = 0.74793, p-value = 6.273e-05

Student

shapiro.test(Ig$PNE_G_L[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$PNE_G_L[Ig$IgG3_Exces == "Non"]
## W = 0.6906, p-value < 2.2e-16

student

IgGE total

shapiro.test(Ig$IgE_Total[Ig$IgG3_Exces =="Oui"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$IgE_Total[Ig$IgG3_Exces == "Oui"]
## W = 0.72288, p-value = 5.384e-05

Student

shapiro.test(Ig$IgE_Total[Ig$IgG3_Exces =="Non"])

## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$IgE_Total[Ig$IgG3_Exces == "Non"]
## W = 0.30682, p-value < 2.2e-16

Student

Comparaison des données IgG deficit Vs Normaux + Excès

Age

t.test(Ig$age_inclusion~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Two Sample t-test
## 
## data:  Ig$age_inclusion by Ig$IgG3_Exces
## t = 1.5055, df = 256, p-value = 0.1334
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -1.58289 11.86014
## sample estimates:
## mean in group Non mean in group Oui 
##          53.39515          48.25652

L’hypothèse nulle d’égalité des moyennes n’ est pas rejetée car la p-value est > 0.05.il n’y a pas de relation significative

IMC

wilcox.test(Ig$IMC~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$IMC by Ig$IgG3_Exces
## W = 1108, p-value = 0.5606
## alternative hypothesis: true location shift is not equal to 0

pas de relation entre les deux variables

Nombre d’exacerbation sans biotherapie

t.test(Ig$Nb_Exa_an.sans_biotherapie~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Two Sample t-test
## 
## data:  Ig$Nb_Exa_an.sans_biotherapie by Ig$IgG3_Exces
## t = -0.26688, df = 207, p-value = 0.7898
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -4.260890  3.244847
## sample estimates:
## mean in group Non mean in group Oui 
##          4.491979          5.000000

Dose de corticoides systemiques

t.test(Ig$Corticoïde.systémique..dose.~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Two Sample t-test
## 
## data:  Ig$Corticoïde.systémique..dose. by Ig$IgG3_Exces
## t = 0.47676, df = 229, p-value = 0.634
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -4.429460  7.257211
## sample estimates:
## mean in group Non mean in group Oui 
##          6.186603          4.772727

CSI

t.test(Ig$CSI_µg~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Two Sample t-test
## 
## data:  Ig$CSI_µg by Ig$IgG3_Exces
## t = -2.0977, df = 245, p-value = 0.03696
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -1119.56677   -35.23447
## sample estimates:
## mean in group Non mean in group Oui 
##          1551.643          2129.043

Montélukast

t.test(Ig$Montélukast~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Two Sample t-test
## 
## data:  Ig$Montélukast by Ig$IgG3_Exces
## t = -1.569, df = 254, p-value = 0.1179
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.37326736  0.04223545
## sample estimates:
## mean in group Non mean in group Oui 
##         0.3562232         0.5217391

Réponse Biotherapie

t.test(Ig$Rep_biotherapie_GETE~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Two Sample t-test
## 
## data:  Ig$Rep_biotherapie_GETE by Ig$IgG3_Exces
## t = 1.202, df = 242, p-value = 0.2305
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.2701826  1.1161397
## sample estimates:
## mean in group Non mean in group Oui 
##         1.0316742         0.6086957

VEMS pre B2 (litre)

wilcox.test(Ig$VEMS_pre_B2_L~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$VEMS_pre_B2_L by Ig$IgG3_Exces
## W = 2479.5, p-value = 0.09389
## alternative hypothesis: true location shift is not equal to 0

VEMS pre B2 (%)

t.test(Ig$VEMS_PreB2_Pct~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Two Sample t-test
## 
## data:  Ig$VEMS_PreB2_Pct by Ig$IgG3_Exces
## t = 2.1129, df = 225, p-value = 0.03571
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##   0.7994141 22.9304410
## sample estimates:
## mean in group Non mean in group Oui 
##          74.14493          62.28000

la relation entre la VEMS% et les patients les IgG3 en excès est significative

Tiffe

wilcox.test(Ig$Tiffenau~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$Tiffenau by Ig$IgG3_Exces
## W = 2450, p-value = 0.1275
## alternative hypothesis: true location shift is not equal to 0

Le test ne met pas en évidence de relation

FeNO

t.test(Ig$FeNo~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Two Sample t-test
## 
## data:  Ig$FeNo by Ig$IgG3_Exces
## t = 1.7419, df = 136, p-value = 0.0838
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -2.558612 40.374237
## sample estimates:
## mean in group Non mean in group Oui 
##          37.00781          18.10000

PNE_Gl

t.test(Ig$PNE_G_L~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Two Sample t-test
## 
## data:  Ig$PNE_G_L by Ig$IgG3_Exces
## t = 0.91881, df = 233, p-value = 0.3591
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.1034390  0.2842306
## sample estimates:
## mean in group Non mean in group Oui 
##         0.3556132         0.2652174

IgGE total

t.test(Ig$IgE_Total~Ig$IgG3_Exces, var.equal=TRUE)

## 
##  Two Sample t-test
## 
## data:  Ig$IgE_Total by Ig$IgG3_Exces
## t = -0.061382, df = 179, p-value = 0.9511
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -484.2767  455.0576
## sample estimates:
## mean in group Non mean in group Oui 
##          408.7237          423.3333

Test de comparaison des données qualitatives: IgG deficit Vs normaux+exces

comp_qual <- read.csv("C:/Users/mallah.s/Desktop/StatsTheses/Mauro anthony/comp_qual.csv", sep=";", stringsAsFactors=TRUE)

Pour le test de liaison entre deux variables qualitative: verification de la normalité -> selon la validation de la normalité :test de Chi2 ou test de fisher

le test du χ2 d’indépendance sert à étudier la liaison entre deux caractères qualitatifs XetY, lorsque les conditions ne sont pas remplies, il existe des corrections,dans notre cas je vais utiliser le tests exacts de Fisher

Sexe

xtabs(~Sexe+IgG3_Exces, data=comp_qual)

##     IgG3_Exces
## Sexe Non Oui
##    F 137  17
##    M  98   6

chisq.test(comp_qual$Sexe,comp_qual$IgG3_Exces)$expected

##               comp_qual$IgG3_Exces
## comp_qual$Sexe       Non       Oui
##              F 140.27132 13.728682
##              M  94.72868  9.271318

chisq.test(comp_qual$Sexe,comp_qual$IgG3_Exces, correct=FALSE)

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Sexe and comp_qual$IgG3_Exces
## X-squared = 2.123, df = 1, p-value = 0.1451

fisher.test(comp_qual$Sexe,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Sexe and comp_qual$IgG3_Exces
## p-value = 0.1833
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.153973 1.374774
## sample estimates:
## odds ratio 
##  0.4946569

les variables Sexe et deficit d’IgG sont independantes

Montélukast

xtabs(~Montélukast+IgG3_Exces, data=comp_qual)

##            IgG3_Exces
## Montélukast Non Oui
##         Non 150  11
##         Oui  83  12

chisq.test(comp_qual$Montélukast,comp_qual$IgG3_Exces)$expected

##                      comp_qual$IgG3_Exces
## comp_qual$Montélukast       Non       Oui
##                   Non 146.53516 14.464844
##                   Oui  86.46484  8.535156

chisq.test(comp_qual$Montélukast,comp_qual$IgG3_Exces, correct=FALSE)

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Montélukast and comp_qual$IgG3_Exces
## X-squared = 2.4573, df = 1, p-value = 0.117

fisher.test(comp_qual$Montélukast,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Montélukast and comp_qual$IgG3_Exces
## p-value = 0.1732
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.7572168 5.1564772
## sample estimates:
## odds ratio 
##   1.966062

Pour les IgG en deficit, il y’a seulement 3 qui sont traités par Montélukast, donc pas assez de patients, ce qui explique le le resultats de la p-value du test exact de fisher

Biotherapie

xtabs(~Biotherapie+IgG3_Exces, data=comp_qual)

##            IgG3_Exces
## Biotherapie Non Oui
##         Non 149  19
##         Oui  86   4

chisq.test(comp_qual$Biotherapie,comp_qual$IgG3_Exces)$expected

##                      comp_qual$IgG3_Exces
## comp_qual$Biotherapie       Non       Oui
##                   Non 153.02326 14.976744
##                   Oui  81.97674  8.023256

chisq.test(comp_qual$Biotherapie,comp_qual$IgG3_Exces, correct=FALSE)

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Biotherapie and comp_qual$IgG3_Exces
## X-squared = 3.4015, df = 1, p-value = 0.06514

fisher.test(comp_qual$Biotherapie,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Biotherapie and comp_qual$IgG3_Exces
## p-value = 0.07052
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.08765357 1.15090505
## sample estimates:
## odds ratio 
##  0.3659675

type de biotherapie

xtabs(~Biothérapie_type+IgG3_Exces, data=comp_qual)

##                 IgG3_Exces
## Biothérapie_type Non Oui
##     Benralizumab  10   0
##     Dupilumab      2   2
##     Mepolizumab   50   2
##     Omalixumab    24   0

chisq.test(comp_qual$Biothérapie_type,comp_qual$IgG3_Exces)$expected

## Warning in chisq.test(comp_qual$Biothérapie_type, comp_qual$IgG3_Exces): Chi-
## squared approximation may be incorrect

##                           comp_qual$IgG3_Exces
## comp_qual$Biothérapie_type       Non       Oui
##               Benralizumab  9.555556 0.4444444
##               Dupilumab     3.822222 0.1777778
##               Mepolizumab  49.688889 2.3111111
##               Omalixumab   22.933333 1.0666667

chisq.test(comp_qual$Biothérapie_type,comp_qual$IgG3_Exces, correct=FALSE)

## Warning in chisq.test(comp_qual$Biothérapie_type, comp_qual$IgG3_Exces, : Chi-
## squared approximation may be incorrect

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Biothérapie_type and comp_qual$IgG3_Exces
## X-squared = 21.172, df = 3, p-value = 9.697e-05

fisher.test(comp_qual$Biothérapie_type,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Biothérapie_type and comp_qual$IgG3_Exces
## p-value = 0.01425
## alternative hypothesis: two.sided

Tabac

xtabs(~Tabac+IgG3_Exces, data=comp_qual)

##         IgG3_Exces
## Tabac    Non Oui
##   Actif   21   4
##   Non     83   8
##   Passif   8   2
##   Sevré   78   7

chisq.test(comp_qual$Tabac,comp_qual$IgG3_Exces)$expected

## Warning in chisq.test(comp_qual$Tabac, comp_qual$IgG3_Exces): Chi-squared
## approximation may be incorrect

##                comp_qual$IgG3_Exces
## comp_qual$Tabac       Non       Oui
##          Actif  22.511848 2.4881517
##          Non    81.943128 9.0568720
##          Passif  9.004739 0.9952607
##          Sevré  76.540284 8.4597156

chisq.test(comp_qual$Tabac,comp_qual$IgG3_Exces, correct=FALSE)

## Warning in chisq.test(comp_qual$Tabac, comp_qual$IgG3_Exces, correct = FALSE):
## Chi-squared approximation may be incorrect

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Tabac and comp_qual$IgG3_Exces
## X-squared = 2.5632, df = 3, p-value = 0.464

fisher.test(comp_qual$Tabac,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Tabac and comp_qual$IgG3_Exces
## p-value = 0.3527
## alternative hypothesis: two.sided

Atopie

xtabs(~Atopie+IgG3_Exces, data=comp_qual)

##       IgG3_Exces
## Atopie Non Oui
##    Non 147  13
##    Oui  88  10

chisq.test(comp_qual$Atopie,comp_qual$IgG3_Exces)$expected

##                 comp_qual$IgG3_Exces
## comp_qual$Atopie       Non       Oui
##              Non 145.73643 14.263566
##              Oui  89.26357  8.736434

chisq.test(comp_qual$Atopie,comp_qual$IgG3_Exces, correct=FALSE)

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Atopie and comp_qual$IgG3_Exces
## X-squared = 0.32353, df = 1, p-value = 0.5695

fisher.test(comp_qual$Atopie,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Atopie and comp_qual$IgG3_Exces
## p-value = 0.6539
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.4818549 3.3229206
## sample estimates:
## odds ratio 
##   1.283666

FeNO > 20

xtabs(~FeNo_sup_20_ppb+IgG3_Exces, data=comp_qual)

##                IgG3_Exces
## FeNo_sup_20_ppb Non Oui
##             Non  49   7
##             Oui  79   3

chisq.test(comp_qual$FeNo_sup_20_ppb,comp_qual$IgG3_Exces)$expected

## Warning in chisq.test(comp_qual$FeNo_sup_20_ppb, comp_qual$IgG3_Exces): Chi-
## squared approximation may be incorrect

##                          comp_qual$IgG3_Exces
## comp_qual$FeNo_sup_20_ppb      Non      Oui
##                       Non 51.94203 4.057971
##                       Oui 76.05797 5.942029

chisq.test(comp_qual$FeNo_sup_20_ppb,comp_qual$IgG3_Exces, correct=FALSE)

## Warning in chisq.test(comp_qual$FeNo_sup_20_ppb, comp_qual$IgG3_Exces, correct =
## FALSE): Chi-squared approximation may be incorrect

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$FeNo_sup_20_ppb and comp_qual$IgG3_Exces
## X-squared = 3.8701, df = 1, p-value = 0.04915

fisher.test(comp_qual$FeNo_sup_20_ppb,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$FeNo_sup_20_ppb and comp_qual$IgG3_Exces
## p-value = 0.08994
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.04279835 1.24369022
## sample estimates:
## odds ratio 
##  0.2684385

PNN > 5

xtabs(~PNN_sup_5+IgG3_Exces, data=comp_qual)

##          IgG3_Exces
## PNN_sup_5 Non Oui
##       Non  98   8
##       Oui 116  14

chisq.test(comp_qual$PNN_sup_5,comp_qual$IgG3_Exces)$expected

##                    comp_qual$IgG3_Exces
## comp_qual$PNN_sup_5       Non       Oui
##                 Non  96.11864  9.881356
##                 Oui 117.88136 12.118644

chisq.test(comp_qual$PNN_sup_5,comp_qual$IgG3_Exces, correct=FALSE)

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$PNN_sup_5 and comp_qual$IgG3_Exces
## X-squared = 0.71712, df = 1, p-value = 0.3971

fisher.test(comp_qual$PNN_sup_5,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$PNN_sup_5 and comp_qual$IgG3_Exces
## p-value = 0.5014
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.5508048 4.2399968
## sample estimates:
## odds ratio 
##    1.47605

Les deux variable sont independantes

PNE > 0.15

xtabs(~PNE_sup_0.15G_L+IgG3_Exces, data=comp_qual)

##                IgG3_Exces
## PNE_sup_0.15G_L Non Oui
##             Non  88  10
##             Oui 124  13

chisq.test(comp_qual$PNE_sup_0.15G_L,comp_qual$IgG3_Exces)$expected

##                          comp_qual$IgG3_Exces
## comp_qual$PNE_sup_0.15G_L       Non       Oui
##                       Non  88.40851  9.591489
##                       Oui 123.59149 13.408511

chisq.test(comp_qual$PNE_sup_0.15G_L,comp_qual$IgG3_Exces, correct=FALSE)

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$PNE_sup_0.15G_L and comp_qual$IgG3_Exces
## X-squared = 0.033083, df = 1, p-value = 0.8557

fisher.test(comp_qual$PNE_sup_0.15G_L,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$PNE_sup_0.15G_L and comp_qual$IgG3_Exces
## p-value = 1
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.355467 2.466360
## sample estimates:
## odds ratio 
##  0.9228993

PNE >0.3G/L

xtabs(~PNE_sup_0.3.G_L+IgG3_Exces, data=comp_qual)

##                IgG3_Exces
## PNE_sup_0.3.G_L Non Oui
##             Non 118  15
##             Oui  94   8

chisq.test(comp_qual$PNE_sup_0.3.G_L,comp_qual$IgG3_Exces)$expected

##                          comp_qual$IgG3_Exces
## comp_qual$PNE_sup_0.3.G_L       Non       Oui
##                       Non 119.98298 13.017021
##                       Oui  92.01702  9.982979

chisq.test(comp_qual$PNE_sup_0.3.G_L,comp_qual$IgG3_Exces, correct=FALSE)

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$PNE_sup_0.3.G_L and comp_qual$IgG3_Exces
## X-squared = 0.77148, df = 1, p-value = 0.3798

fisher.test(comp_qual$PNE_sup_0.3.G_L,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$PNE_sup_0.3.G_L and comp_qual$IgG3_Exces
## p-value = 0.5073
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.2356114 1.7708934
## sample estimates:
## odds ratio 
##  0.6706184

CRP >5mg/l

xtabs(~CRP_sup_5.mg_l+IgG3_Exces, data=comp_qual)

##               IgG3_Exces
## CRP_sup_5.mg_l Non Oui
##            Non 101   5
##            Oui  42   7

chisq.test(comp_qual$CRP_sup_5.mg_l,comp_qual$IgG3_Exces)$expected

## Warning in chisq.test(comp_qual$CRP_sup_5.mg_l, comp_qual$IgG3_Exces): Chi-
## squared approximation may be incorrect

##                         comp_qual$IgG3_Exces
## comp_qual$CRP_sup_5.mg_l      Non      Oui
##                      Non 97.79355 8.206452
##                      Oui 45.20645 3.793548

chisq.test(comp_qual$CRP_sup_5.mg_l,comp_qual$IgG3_Exces, correct=FALSE)

## Warning in chisq.test(comp_qual$CRP_sup_5.mg_l, comp_qual$IgG3_Exces, correct =
## FALSE): Chi-squared approximation may be incorrect

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$CRP_sup_5.mg_l and comp_qual$IgG3_Exces
## X-squared = 4.2956, df = 1, p-value = 0.03821

fisher.test(comp_qual$CRP_sup_5.mg_l,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$CRP_sup_5.mg_l and comp_qual$IgG3_Exces
## p-value = 0.0524
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##   0.8568731 14.1292543
## sample estimates:
## odds ratio 
##   3.336814

IgE totale >30 KUA/l

xtabs(~IgE_Total_sup_30_kUA_l+IgG3_Exces, data=comp_qual)

##                       IgG3_Exces
## IgE_Total_sup_30_kUA_l Non Oui
##                    Non  28   2
##                    Oui 132  19

chisq.test(comp_qual$IgE_Total_sup_30_kUA_l,comp_qual$IgG3_Exces)$expected

## Warning in chisq.test(comp_qual$IgE_Total_sup_30_kUA_l, comp_qual$IgG3_Exces):
## Chi-squared approximation may be incorrect

##      comp_qual$IgG3_Exces
##             Non       Oui
##   Non  26.51934  3.480663
##   Oui 133.48066 17.519337

chisq.test(comp_qual$IgE_Total_sup_30_kUA_l,comp_qual$IgG3_Exces, correct=FALSE)

## Warning in chisq.test(comp_qual$IgE_Total_sup_30_kUA_l, comp_qual$IgG3_Exces, :
## Chi-squared approximation may be incorrect

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$IgE_Total_sup_30_kUA_l and comp_qual$IgG3_Exces
## X-squared = 0.8541, df = 1, p-value = 0.3554

fisher.test(comp_qual$IgE_Total_sup_30_kUA_l,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$IgE_Total_sup_30_kUA_l and comp_qual$IgG3_Exces
## p-value = 0.5354
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##   0.4418997 18.7738998
## sample estimates:
## odds ratio 
##   2.008838

Profil t2

xtabs(~Profil_T2+IgG3_Exces, data=comp_qual)

##          IgG3_Exces
## Profil_T2 Non Oui
##       Neg  78   7
##       Pos  42   3

chisq.test(comp_qual$Profil_T2,comp_qual$IgG3_Exces)$expected

## Warning in chisq.test(comp_qual$Profil_T2, comp_qual$IgG3_Exces): Chi-squared
## approximation may be incorrect

##                    comp_qual$IgG3_Exces
## comp_qual$Profil_T2      Non      Oui
##                 Neg 78.46154 6.538462
##                 Pos 41.53846 3.461538

chisq.test(comp_qual$Profil_T2,comp_qual$IgG3_Exces, correct=FALSE)

## Warning in chisq.test(comp_qual$Profil_T2, comp_qual$IgG3_Exces, correct =
## FALSE): Chi-squared approximation may be incorrect

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Profil_T2 and comp_qual$IgG3_Exces
## X-squared = 0.10196, df = 1, p-value = 0.7495

fisher.test(comp_qual$Profil_T2,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Profil_T2 and comp_qual$IgG3_Exces
## p-value = 1
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.1265426 3.7208357
## sample estimates:
## odds ratio 
##   0.797294

Réponse biotherapie

xtabs(~Rep_biotherapie_GETE+IgG3_Exces, data=comp_qual)

##                     IgG3_Exces
## Rep_biotherapie_GETE Non Oui
##                      162  19
##          Aggravation   9   0
##          Bonne        25   0
##          Excellent     5   0
##          Faible       26   2
##          modérée       8   2

chisq.test(comp_qual$Rep_biotherapie_GETE,comp_qual$IgG3_Exces)$expected

## Warning in chisq.test(comp_qual$Rep_biotherapie_GETE, comp_qual$IgG3_Exces):
## Chi-squared approximation may be incorrect

##                               comp_qual$IgG3_Exces
## comp_qual$Rep_biotherapie_GETE        Non        Oui
##                                164.864341 16.1356589
##                    Aggravation   8.197674  0.8023256
##                    Bonne        22.771318  2.2286822
##                    Excellent     4.554264  0.4457364
##                    Faible       25.503876  2.4961240
##                    modérée       9.108527  0.8914729

chisq.test(comp_qual$Rep_biotherapie_GETE,comp_qual$IgG3_Exces, correct=FALSE)

## Warning in chisq.test(comp_qual$Rep_biotherapie_GETE, comp_qual$IgG3_Exces, :
## Chi-squared approximation may be incorrect

## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Rep_biotherapie_GETE and comp_qual$IgG3_Exces
## X-squared = 5.9969, df = 5, p-value = 0.3065

fisher.test(comp_qual$Rep_biotherapie_GETE,comp_qual$IgG3_Exces)

## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Rep_biotherapie_GETE and comp_qual$IgG3_Exces
## p-value = 0.341
## alternative hypothesis: two.sided

comparaison IgG3 Exces VS normaux-deficit

MALLAH Siham

08/09/2021

Evaluation des conditions de validité:Normalité pour les données IgG 2 deficit Vs Normaux + Excès

Age à l’inclusion

IMC

Nombre d’exacerbation sans biotherapie

Dose de corticoides systemiques

CSI

Montélukast

Réponse Biotherapie

VEMS pre B2 (litre)

VEMS pre B2 (%)

Tiffe

FeNO

PNE G/L

IgGE total

Comparaison des données IgG deficit Vs Normaux + Excès

Age

IMC

Nombre d’exacerbation sans biotherapie

Dose de corticoides systemiques

CSI

Montélukast

Réponse Biotherapie

VEMS pre B2 (litre)

VEMS pre B2 (%)

Tiffe

FeNO

PNE_Gl

IgGE total

Test de comparaison des données qualitatives: IgG deficit Vs normaux+exces

Sexe

Montélukast

Biotherapie

type de biotherapie

Tabac

Atopie

FeNO > 20

PNN > 5

PNE > 0.15

PNE >0.3G/L

CRP >5mg/l

IgE totale >30 KUA/l

Profil t2

Réponse biotherapie