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$age_inclusion[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$age_inclusion[Ig$IgG2_deficit == "Oui"]
## W = 0.89563, p-value = 0.2637

la normalité n’est pas acceptée: test de Wilcoxon

shapiro.test(Ig$age_inclusion[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$age_inclusion[Ig$IgG2_deficit == "Non"]
## W = 0.98076, p-value = 0.001823

IMC

shapiro.test(Ig$IMC[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$IMC[Ig$IgG2_deficit == "Oui"]
## W = 0.98785, p-value = 0.9462

la normalité n’est pas acceptée: test de Wilcoxon

shapiro.test(Ig$IMC[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$IMC[Ig$IgG2_deficit == "Non"]
## W = 0.85351, p-value = 1.639e-11

la normalité n’est pas acceptés :test de student

Nombre d’exacerbation sans biotherapie

shapiro.test(Ig$Nb_Exa_an.sans_biotherapie[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Nb_Exa_an.sans_biotherapie[Ig$IgG2_deficit == "Oui"]
## W = 0.76879, p-value = 0.01986
shapiro.test(Ig$Nb_Exa_an.sans_biotherapie[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Nb_Exa_an.sans_biotherapie[Ig$IgG2_deficit == "Non"]
## W = 0.41157, p-value < 2.2e-16

la normalité est accepté: test de student

Dose de corticoides systemiques

shapiro.test(Ig$Corticoïde.systémique..dose.[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Corticoïde.systémique..dose.[Ig$IgG2_deficit == "Oui"]
## W = 0.76928, p-value = 0.02009
shapiro.test(Ig$Corticoïde.systémique..dose.[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Corticoïde.systémique..dose.[Ig$IgG2_deficit == "Non"]
## W = 0.51988, p-value < 2.2e-16

la normalité n’est pas acceptés :test de student

CSI

shapiro.test(Ig$CSI_µg[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$CSI_µg[Ig$IgG2_deficit == "Oui"]
## W = 0.90959, p-value = 0.3512
shapiro.test(Ig$CSI_µg[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$CSI_µg[Ig$IgG2_deficit == "Non"]
## W = 0.87299, p-value = 3.225e-13

la normalité est acceptée : Test de Student

Montélukast

shapiro.test(Ig$Montélukast[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Montélukast[Ig$IgG2_deficit == "Oui"]
## W = 0.6412, p-value = 0.0004791
shapiro.test(Ig$Montélukast[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Montélukast[Ig$IgG2_deficit == "Non"]
## W = 0.61178, p-value < 2.2e-16

la normalité est acceptés :test de Student

Réponse Biotherapie

shapiro.test(Ig$Rep_biotherapie_GETE[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Rep_biotherapie_GETE[Ig$IgG2_deficit == "Oui"]
## W = 0.7023, p-value = 0.002391

la normalité est acceptée : t-test de Student

shapiro.test(Ig$Rep_biotherapie_GETE[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Rep_biotherapie_GETE[Ig$IgG2_deficit == "Non"]
## W = 0.64379, p-value < 2.2e-16

la normalité est acceptée : t-test de Student

VEMS pre B2 (litre)

shapiro.test(Ig$VEMS_pre_B2_L[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$VEMS_pre_B2_L[Ig$IgG2_deficit == "Oui"]
## W = 0.93655, p-value = 0.6079

la normalité n’est pas acceptée : Test de Wilcoxon

shapiro.test(Ig$VEMS_pre_B2_L[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$VEMS_pre_B2_L[Ig$IgG2_deficit == "Non"]
## W = 0.97459, p-value = 0.0006348

la normalité est accepté :test de Student

VEMS pre B2 (%)

shapiro.test(Ig$VEMS_PreB2_Pct[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$VEMS_PreB2_Pct[Ig$IgG2_deficit == "Oui"]
## W = 0.88913, p-value = 0.2702

la normalité n’est pas acceptée : test de Wilcoxon

shapiro.test(Ig$VEMS_PreB2_Pct[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$VEMS_PreB2_Pct[Ig$IgG2_deficit == "Non"]
## W = 0.98011, p-value = 0.003396

la normalité est acceptée : test de student

Tiffe

shapiro.test(Ig$Tiffenau[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Tiffenau[Ig$IgG2_deficit == "Oui"]
## W = 0.90882, p-value = 0.3878

la normalité n’est pas acceptée : T de Wilcoxon

shapiro.test(Ig$Tiffenau[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$Tiffenau[Ig$IgG2_deficit == "Non"]
## W = 0.98796, p-value = 0.06577

la normalité n’est pas acceptée : T de Wilcoxon

FeNO

nous ne nouvons pas calculer la difference entre ceux qui sont en deficit d’IgG et les autres par manque de données. Seul 2 patients avec deficit d’IGG ont une donnée de FeNO

shapiro.test(Ig$FeNo[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$FeNo[Ig$IgG2_deficit == "Non"]
## W = 0.78759, p-value = 1.181e-12

la normalité est acceptée : test de student

shapiro.test(Ig$FeNo[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$FeNo[Ig$IgG2_deficit == "Oui"]
## W = 0.95439, p-value = 0.7436

test de Wilcoxon

PNE G/L

shapiro.test(Ig$PNE_G_L[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$PNE_G_L[Ig$IgG2_deficit == "Oui"]
## W = 0.82162, p-value = 0.09114

la normalité n’est pas acceptée : t-test de Wilcoxon

shapiro.test(Ig$PNE_G_L[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$PNE_G_L[Ig$IgG2_deficit == "Non"]
## W = 0.69081, p-value < 2.2e-16

la normalité est accéptée : student

IgGE total

shapiro.test(Ig$IgE_Total[Ig$IgG2_deficit =="Oui"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$IgE_Total[Ig$IgG2_deficit == "Oui"]
## W = 0.84861, p-value = 0.2217

la normalité n’est pas acceptée : t-test de Wilcoxon

shapiro.test(Ig$IgE_Total[Ig$IgG2_deficit =="Non"])
## 
##  Shapiro-Wilk normality test
## 
## data:  Ig$IgE_Total[Ig$IgG2_deficit == "Non"]
## W = 0.32211, p-value < 2.2e-16

T-test de Student

Comparaison des données IgG deficit Vs Normaux + Excès

Age

wilcox.test(Ig$age_inclusion~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$age_inclusion by Ig$IgG2_deficit
## W = 763.5, p-value = 0.256
## alternative hypothesis: true location shift is not equal to 0

L’hypothèse nulle d’égalité des moyennes est rejetée car la p-value est > 0.05. Le test ne met pas en évidence une différence significative entre l’age des patients ayant l’IgG2 de deficit et les autres

wilcox.test(Ig$age_inclusion~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$age_inclusion by Ig$IgG2_deficit
## W = 763.5, p-value = 0.256
## alternative hypothesis: true location shift is not equal to 0

même conclusion

IMC

t.test(Ig$IMC~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Two Sample t-test
## 
## data:  Ig$IMC by Ig$IgG2_deficit
## t = 0.23771, df = 166, p-value = 0.8124
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -6.142934  7.824641
## sample estimates:
## mean in group Non mean in group Oui 
##          26.59085          25.75000

L’hypothèse nulle d’égalité des moyennes n’est pas rejetée car la p-value est > 0.05. Ainsi, rien ne permet d’affirmer que les moyennes des IMC des patients ayant l’IgG2 en deficit et les autres patients sont différentes.

wilcox.test(Ig$IMC~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$IMC by Ig$IgG2_deficit
## W = 350, p-value = 0.8227
## alternative hypothesis: true location shift is not equal to 0

même conclusion

Nombre d’exacerbation sans biotherapie

t.test(Ig$Nb_Exa_an.sans_biotherapie~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Two Sample t-test
## 
## data:  Ig$Nb_Exa_an.sans_biotherapie by Ig$IgG2_deficit
## t = 0.40151, df = 207, p-value = 0.6885
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -5.096554  7.703343
## sample estimates:
## mean in group Non mean in group Oui 
##          4.589109          3.285714

Le test ne met pas en évidence une différence significative

Dose de corticoides systemiques

t.test(Ig$Corticoïde.systémique..dose.~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Two Sample t-test
## 
## data:  Ig$Corticoïde.systémique..dose. by Ig$IgG2_deficit
## t = 0.068535, df = 229, p-value = 0.9454
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -9.662919 10.359348
## sample estimates:
## mean in group Non mean in group Oui 
##          6.062500          5.714286

Le test ne met pas en évidence une différence significative

CSI

t.test(Ig$CSI_µg~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Two Sample t-test
## 
## data:  Ig$CSI_µg by Ig$IgG2_deficit
## t = 0.30987, df = 245, p-value = 0.7569
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -756.5196 1038.9861
## sample estimates:
## mean in group Non mean in group Oui 
##          1609.983          1468.750

Le test ne met pas en évidence une différence significative

Montélukast

t.test(Ig$Montélukast~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Two Sample t-test
## 
## data:  Ig$Montélukast by Ig$IgG2_deficit
## t = -0.023145, df = 254, p-value = 0.9816
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.3471230  0.3390584
## sample estimates:
## mean in group Non mean in group Oui 
##         0.3709677         0.3750000

Le test ne met pas en évidence une différence significative

Réponse Biotherapie

t.test(Ig$Rep_biotherapie_GETE~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Two Sample t-test
## 
## data:  Ig$Rep_biotherapie_GETE by Ig$IgG2_deficit
## t = -0.23783, df = 242, p-value = 0.8122
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -1.278316  1.002893
## sample estimates:
## mean in group Non mean in group Oui 
##         0.9872881         1.1250000

Le test ne met pas en évidence une différence significative

VEMS pre B2 (litre)

wilcox.test(Ig$VEMS_pre_B2_L~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$VEMS_pre_B2_L by Ig$IgG2_deficit
## W = 773.5, p-value = 0.9024
## alternative hypothesis: true location shift is not equal to 0

Le test ne met pas en évidence une différence significative

VEMS pre B2 (%)

wilcox.test(Ig$VEMS_PreB2_Pct~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$VEMS_PreB2_Pct by Ig$IgG2_deficit
## W = 662, p-value = 0.5297
## alternative hypothesis: true location shift is not equal to 0

Le test ne met pas en évidence une différence significative

Tiffe

wilcox.test(Ig$Tiffenau~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$Tiffenau by Ig$IgG2_deficit
## W = 811.5, p-value = 0.7434
## alternative hypothesis: true location shift is not equal to 0

Le test ne met pas en évidence une différence significative

FeNO

malgre les données insuffisantes, le test de wilcoxon a été fait ( attention à ne pas prendre en consideration)

wilcox.test(Ig$FeNo~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$FeNo by Ig$IgG2_deficit
## W = 200.5, p-value = 0.395
## alternative hypothesis: true location shift is not equal to 0

Le test ne met pas en évidence une différence significative

PNE_Gl

wilcox.test(Ig$PNE_G_L~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$PNE_G_L by Ig$IgG2_deficit
## W = 1073, p-value = 0.01757
## alternative hypothesis: true location shift is not equal to 0

Le test met en évidence une différence significative

IgGE total

wilcox.test(Ig$IgE_Total~Ig$IgG2_deficit, var.equal=TRUE)
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  Ig$IgE_Total by Ig$IgG2_deficit
## W = 394.5, p-value = 0.6995
## alternative hypothesis: true location shift is not equal to 0

Le test ne met pas en évidence une différence significative

Test de comparaison des données qualitatives: IgG2 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+IgG2_deficit, data=comp_qual)
##     IgG2_deficit
## Sexe Non Oui
##    F 148   6
##    M 102   2
chisq.test(comp_qual$Sexe,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$Sexe, comp_qual$IgG2_deficit): Chi-squared
## approximation may be incorrect
##               comp_qual$IgG2_deficit
## comp_qual$Sexe      Non      Oui
##              F 149.2248 4.775194
##              M 100.7752 3.224806
chisq.test(comp_qual$Sexe,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$Sexe, comp_qual$IgG2_deficit, correct = FALSE):
## Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Sexe and comp_qual$IgG2_deficit
## X-squared = 0.80428, df = 1, p-value = 0.3698
fisher.test(comp_qual$Sexe,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Sexe and comp_qual$IgG2_deficit
## p-value = 0.4804
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.04697675 2.78103300
## sample estimates:
## odds ratio 
##  0.4848991

les variables Sexe et deficit d’IgG 2 sont independantes

Montélukast

xtabs(~Montélukast+IgG2_deficit, data=comp_qual)
##            IgG2_deficit
## Montélukast Non Oui
##         Non 156   5
##         Oui  92   3
chisq.test(comp_qual$Montélukast,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$Montélukast, comp_qual$IgG2_deficit): Chi-
## squared approximation may be incorrect
##                      comp_qual$IgG2_deficit
## comp_qual$Montélukast       Non     Oui
##                   Non 155.96875 5.03125
##                   Oui  92.03125 2.96875
chisq.test(comp_qual$Montélukast,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$Montélukast, comp_qual$IgG2_deficit, correct =
## FALSE): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Montélukast and comp_qual$IgG2_deficit
## X-squared = 0.00053992, df = 1, p-value = 0.9815
fisher.test(comp_qual$Montélukast,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Montélukast and comp_qual$IgG2_deficit
## p-value = 1
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.1544207 5.3672921
## sample estimates:
## odds ratio 
##    1.01733

Pour les IgG2 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+IgG2_deficit, data=comp_qual)
##            IgG2_deficit
## Biotherapie Non Oui
##         Non 163   5
##         Oui  87   3
chisq.test(comp_qual$Biotherapie,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$Biotherapie, comp_qual$IgG2_deficit): Chi-
## squared approximation may be incorrect
##                      comp_qual$IgG2_deficit
## comp_qual$Biotherapie      Non      Oui
##                   Non 162.7907 5.209302
##                   Oui  87.2093 2.790698
chisq.test(comp_qual$Biotherapie,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$Biotherapie, comp_qual$IgG2_deficit, correct =
## FALSE): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Biotherapie and comp_qual$IgG2_deficit
## X-squared = 0.024879, df = 1, p-value = 0.8747
fisher.test(comp_qual$Biotherapie,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Biotherapie and comp_qual$IgG2_deficit
## p-value = 1
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.1704848 5.9316747
## sample estimates:
## odds ratio 
##   1.123615

Pour les IgG2 en deficit, il y’a seulement 3 qui sont traités par Biotherapie, donc pas assez de patients, ce qui explique le le resultats de la p-value du test exact de fisher

type de biotherapie

xtabs(~Biothérapie_type+IgG2_deficit, data=comp_qual)
##                 IgG2_deficit
## Biothérapie_type Non Oui
##     Benralizumab  10   0
##     Dupilumab      4   0
##     Mepolizumab   50   2
##     Omalixumab    23   1
chisq.test(comp_qual$Biothérapie_type,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$Biothérapie_type, comp_qual$IgG2_deficit): Chi-
## squared approximation may be incorrect
##                           comp_qual$IgG2_deficit
## comp_qual$Biothérapie_type       Non       Oui
##               Benralizumab  9.666667 0.3333333
##               Dupilumab     3.866667 0.1333333
##               Mepolizumab  50.266667 1.7333333
##               Omalixumab   23.200000 0.8000000
chisq.test(comp_qual$Biothérapie_type,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$Biothérapie_type, comp_qual$IgG2_deficit, : Chi-
## squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Biothérapie_type and comp_qual$IgG2_deficit
## X-squared = 0.57692, df = 3, p-value = 0.9017
fisher.test(comp_qual$Biothérapie_type,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Biothérapie_type and comp_qual$IgG2_deficit
## p-value = 1
## alternative hypothesis: two.sided

même resultats que pour les biotherapie

Tabac

xtabs(~Tabac+IgG2_deficit, data=comp_qual)
##         IgG2_deficit
## Tabac    Non Oui
##   Actif   23   2
##   Non     89   2
##   Passif   9   1
##   Sevré   82   3
chisq.test(comp_qual$Tabac,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$Tabac, comp_qual$IgG2_deficit): Chi-squared
## approximation may be incorrect
##                comp_qual$IgG2_deficit
## comp_qual$Tabac       Non       Oui
##          Actif  24.052133 0.9478673
##          Non    87.549763 3.4502370
##          Passif  9.620853 0.3791469
##          Sevré  81.777251 3.2227488
chisq.test(comp_qual$Tabac,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$Tabac, comp_qual$IgG2_deficit, correct = FALSE):
## Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Tabac and comp_qual$IgG2_deficit
## X-squared = 2.9202, df = 3, p-value = 0.4041
fisher.test(comp_qual$Tabac,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Tabac and comp_qual$IgG2_deficit
## p-value = 0.2295
## alternative hypothesis: two.sided

Atopie

xtabs(~Atopie+IgG2_deficit, data=comp_qual)
##       IgG2_deficit
## Atopie Non Oui
##    Non 153   7
##    Oui  97   1
chisq.test(comp_qual$Atopie,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$Atopie, comp_qual$IgG2_deficit): Chi-squared
## approximation may be incorrect
##                 comp_qual$IgG2_deficit
## comp_qual$Atopie       Non     Oui
##              Non 155.03876 4.96124
##              Oui  94.96124 3.03876
chisq.test(comp_qual$Atopie,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$Atopie, comp_qual$IgG2_deficit, correct =
## FALSE): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Atopie and comp_qual$IgG2_deficit
## X-squared = 2.2762, df = 1, p-value = 0.1314
fisher.test(comp_qual$Atopie,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Atopie and comp_qual$IgG2_deficit
## p-value = 0.2655
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.004953882 1.805617308
## sample estimates:
## odds ratio 
##  0.2263166

Il n y’a pas de correlation significative entre l’atopie et les IgG2 en deficit

FeNO > 20

xtabs(~FeNo_sup_20_ppb+IgG2_deficit, data=comp_qual)
##                IgG2_deficit
## FeNo_sup_20_ppb Non Oui
##             Non  55   1
##             Oui  79   3
chisq.test(comp_qual$FeNo_sup_20_ppb,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$FeNo_sup_20_ppb, comp_qual$IgG2_deficit): Chi-
## squared approximation may be incorrect
##                          comp_qual$IgG2_deficit
## comp_qual$FeNo_sup_20_ppb      Non      Oui
##                       Non 54.37681 1.623188
##                       Oui 79.62319 2.376812
chisq.test(comp_qual$FeNo_sup_20_ppb,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$FeNo_sup_20_ppb, comp_qual$IgG2_deficit, : Chi-
## squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$FeNo_sup_20_ppb and comp_qual$IgG2_deficit
## X-squared = 0.41468, df = 1, p-value = 0.5196
fisher.test(comp_qual$FeNo_sup_20_ppb,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$FeNo_sup_20_ppb and comp_qual$IgG2_deficit
## p-value = 0.6464
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##    0.1620354 111.5456197
## sample estimates:
## odds ratio 
##   2.078528

il n’y a clairement pas assez de patients pour pouvoir affirmer ou refuter une relation de dependance ou independance des données

PNN > 5

xtabs(~PNN_sup_5+IgG2_deficit, data=comp_qual)
##          IgG2_deficit
## PNN_sup_5 Non Oui
##       Non 105   1
##       Oui 125   5
chisq.test(comp_qual$PNN_sup_5,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$PNN_sup_5, comp_qual$IgG2_deficit): Chi-squared
## approximation may be incorrect
##                    comp_qual$IgG2_deficit
## comp_qual$PNN_sup_5      Non      Oui
##                 Non 103.3051 2.694915
##                 Oui 126.6949 3.305085
chisq.test(comp_qual$PNN_sup_5,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$PNN_sup_5, comp_qual$IgG2_deficit, correct =
## FALSE): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$PNN_sup_5 and comp_qual$IgG2_deficit
## X-squared = 1.9857, df = 1, p-value = 0.1588
fisher.test(comp_qual$PNN_sup_5,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$PNN_sup_5 and comp_qual$IgG2_deficit
## p-value = 0.2274
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##    0.4573631 200.3188242
## sample estimates:
## odds ratio 
##   4.178951

Les deux variable sont independantes

PNE > 0.15

xtabs(~PNE_sup_0.15G_L+IgG2_deficit, data=comp_qual)
##                IgG2_deficit
## PNE_sup_0.15G_L Non Oui
##             Non  93   5
##             Oui 136   1
chisq.test(comp_qual$PNE_sup_0.15G_L,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$PNE_sup_0.15G_L, comp_qual$IgG2_deficit): Chi-
## squared approximation may be incorrect
##                          comp_qual$IgG2_deficit
## comp_qual$PNE_sup_0.15G_L       Non      Oui
##                       Non  95.49787 2.502128
##                       Oui 133.50213 3.497872
chisq.test(comp_qual$PNE_sup_0.15G_L,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$PNE_sup_0.15G_L, comp_qual$IgG2_deficit, : Chi-
## squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$PNE_sup_0.15G_L and comp_qual$IgG2_deficit
## X-squared = 4.3895, df = 1, p-value = 0.03616
fisher.test(comp_qual$PNE_sup_0.15G_L,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$PNE_sup_0.15G_L and comp_qual$IgG2_deficit
## p-value = 0.08468
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.002876064 1.259896153
## sample estimates:
## odds ratio 
##  0.1378348

PNE >0.3G/L

xtabs(~PNE_sup_0.3.G_L+IgG2_deficit, data=comp_qual)
##                IgG2_deficit
## PNE_sup_0.3.G_L Non Oui
##             Non 127   6
##             Oui 102   0
chisq.test(comp_qual$PNE_sup_0.3.G_L,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$PNE_sup_0.3.G_L, comp_qual$IgG2_deficit): Chi-
## squared approximation may be incorrect
##                          comp_qual$IgG2_deficit
## comp_qual$PNE_sup_0.3.G_L       Non      Oui
##                       Non 129.60426 3.395745
##                       Oui  99.39574 2.604255
chisq.test(comp_qual$PNE_sup_0.3.G_L,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$PNE_sup_0.3.G_L, comp_qual$IgG2_deficit, : Chi-
## squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$PNE_sup_0.3.G_L and comp_qual$IgG2_deficit
## X-squared = 4.7221, df = 1, p-value = 0.02978
fisher.test(comp_qual$PNE_sup_0.3.G_L,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$PNE_sup_0.3.G_L and comp_qual$IgG2_deficit
## p-value = 0.0374
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.000000 1.087454
## sample estimates:
## odds ratio 
##          0

CRP >5mg/l

xtabs(~CRP_sup_5.mg_l+IgG2_deficit, data=comp_qual)
##               IgG2_deficit
## CRP_sup_5.mg_l Non Oui
##            Non 103   3
##            Oui  48   1
chisq.test(comp_qual$CRP_sup_5.mg_l,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$CRP_sup_5.mg_l, comp_qual$IgG2_deficit): Chi-
## squared approximation may be incorrect
##                         comp_qual$IgG2_deficit
## comp_qual$CRP_sup_5.mg_l       Non      Oui
##                      Non 103.26452 2.735484
##                      Oui  47.73548 1.264516
chisq.test(comp_qual$CRP_sup_5.mg_l,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$CRP_sup_5.mg_l, comp_qual$IgG2_deficit, : Chi-
## squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$CRP_sup_5.mg_l and comp_qual$IgG2_deficit
## X-squared = 0.083054, df = 1, p-value = 0.7732
fisher.test(comp_qual$CRP_sup_5.mg_l,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$CRP_sup_5.mg_l and comp_qual$IgG2_deficit
## p-value = 1
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.01335548 9.19259308
## sample estimates:
## odds ratio 
##  0.7167176

IgE totale >30 KUA/l

xtabs(~IgE_Total_sup_30_kUA_l+IgG2_deficit, data=comp_qual)
##                       IgG2_deficit
## IgE_Total_sup_30_kUA_l Non Oui
##                    Non  29   1
##                    Oui 148   3
chisq.test(comp_qual$IgE_Total_sup_30_kUA_l,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$IgE_Total_sup_30_kUA_l, comp_qual$IgG2_deficit):
## Chi-squared approximation may be incorrect
##      comp_qual$IgG2_deficit
##             Non       Oui
##   Non  29.33702 0.6629834
##   Oui 147.66298 3.3370166
chisq.test(comp_qual$IgE_Total_sup_30_kUA_l,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$IgE_Total_sup_30_kUA_l,
## comp_qual$IgG2_deficit, : Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$IgE_Total_sup_30_kUA_l and comp_qual$IgG2_deficit
## X-squared = 0.20999, df = 1, p-value = 0.6468
fisher.test(comp_qual$IgE_Total_sup_30_kUA_l,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$IgE_Total_sup_30_kUA_l and comp_qual$IgG2_deficit
## p-value = 0.5188
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##   0.0455098 31.9120864
## sample estimates:
## odds ratio 
##  0.5898704

profil T2

xtabs(~Profil_T2+IgG2_deficit, data=comp_qual)
##          IgG2_deficit
## Profil_T2 Non Oui
##       Neg  83   2
##       Pos  44   1
chisq.test(comp_qual$Profil_T2,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$Profil_T2, comp_qual$IgG2_deficit): Chi-squared
## approximation may be incorrect
##                    comp_qual$IgG2_deficit
## comp_qual$Profil_T2      Non      Oui
##                 Neg 83.03846 1.961538
##                 Pos 43.96154 1.038462
chisq.test(comp_qual$Profil_T2,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$Profil_T2, comp_qual$IgG2_deficit, correct =
## FALSE): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Profil_T2 and comp_qual$IgG2_deficit
## X-squared = 0.0022301, df = 1, p-value = 0.9623
fisher.test(comp_qual$Profil_T2,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Profil_T2 and comp_qual$IgG2_deficit
## p-value = 1
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##   0.01564158 18.60629071
## sample estimates:
## odds ratio 
##  0.9435989

il n’ya clairement pas assez de patients pour que la significativité puisse etre validée ou refutée

Réponse biotherapie

xtabs(~Rep_biotherapie_GETE+IgG2_deficit, data=comp_qual)
##                     IgG2_deficit
## Rep_biotherapie_GETE Non Oui
##                      176   5
##          Aggravation   8   1
##          Bonne        23   2
##          Excellent     5   0
##          Faible       28   0
##          modérée      10   0
chisq.test(comp_qual$Rep_biotherapie_GETE,comp_qual$IgG2_deficit)$expected
## Warning in chisq.test(comp_qual$Rep_biotherapie_GETE, comp_qual$IgG2_deficit):
## Chi-squared approximation may be incorrect
##                               comp_qual$IgG2_deficit
## comp_qual$Rep_biotherapie_GETE        Non       Oui
##                                175.387597 5.6124031
##                    Aggravation   8.720930 0.2790698
##                    Bonne        24.224806 0.7751938
##                    Excellent     4.844961 0.1550388
##                    Faible       27.131783 0.8682171
##                    modérée       9.689922 0.3100775
chisq.test(comp_qual$Rep_biotherapie_GETE,comp_qual$IgG2_deficit, correct=FALSE)
## Warning in chisq.test(comp_qual$Rep_biotherapie_GETE, comp_qual$IgG2_deficit, :
## Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  comp_qual$Rep_biotherapie_GETE and comp_qual$IgG2_deficit
## X-squared = 5.3641, df = 5, p-value = 0.3731
fisher.test(comp_qual$Rep_biotherapie_GETE,comp_qual$IgG2_deficit)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  comp_qual$Rep_biotherapie_GETE and comp_qual$IgG2_deficit
## p-value = 0.2931
## alternative hypothesis: two.sided