Preparation of variables for binary logistic regression - r

Question

I want to perform a binary logistic regression of a binary variable. The variable "burdened" (german: "belastet") has the two values agree (1) and disagree (2).
The formula I am working with is glm () and family = "binomial".
When I put my independent variables into the model (both categorical and metric) and then calculate the p-value using pchisq, I get 0.
belastet0 <- glm(belastetB ~ 1, data = MF, family = binomial (), subset = (sex == 2))
summary(belastet0)
belastet1 <- glm(belastetB ~ age + SES_3 + eig_Kinder + Zufriedenh_BZ + LZ + Angst + guteSeiten + finanzielleEinb + persKontakt, data = MF, family = "binomial", subset = (sex == 2))
summary(belastet1)
bel_chi <- belastet0$null.deviance - belastet1$deviance
bel_chidf <- belastet1$df.null - belastet1$df.residual
bel_pchisq <- 1 - pchisq(bel_chi, bel_chidf)
The output i get:
Deviance Residuals:
Min 1Q Median 3Q Max
-3.0832 -0.5579 0.4269 0.7315 2.1323
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 3.933019 0.345034 11.399 < 2e-16 ***
age -0.017936 0.005805 -3.090 0.00200 **
SES_3mittel -0.252995 0.081740 -3.095 0.00197 **
SES_3niedrig -0.426660 0.131045 -3.256 0.00113 **
eig_Kinder 0.195782 0.044914 4.359 1.31e-05 ***
Zufriedenh_BZ 0.074256 0.021855 3.398 0.00068 ***
LZ -0.452521 0.026458 -17.103 < 2e-16 ***
Angststimme zu 0.955357 0.073680 12.966 < 2e-16 ***
Angstweder noch 0.554067 0.109405 5.064 4.10e-07 ***
guteSeitenstimme zu -1.312848 0.105667 -12.424 < 2e-16 ***
guteSeitenweder noch -0.451338 0.144038 -3.133 0.00173 **
finanzielleEinbstimme zu 0.759940 0.092765 8.192 2.57e-16 ***
finanzielleEinbweder noch 0.814164 0.136931 5.946 2.75e-09 ***
persKontaktstimme zu 1.001333 0.082896 12.079 < 2e-16 ***
persKontaktweder noch 0.538896 0.124962 4.312 1.61e-05 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for binomial family taken to be 1)
Null deviance: 6691.7 on 5928 degrees of freedom
Residual deviance: 5366.5 on 5914 degrees of freedom
(14325 Beobachtungen als fehlend gelöscht)
AIC: 5396.5
And for:
bel_pchisq <- 1 - pchisq(bel_chi, bel_chidf)
I receive: bel_pchisq = 0
I think the problem is that I have not cleaned my data?
I have already done a revision of my metric variables: data$Age[is.na(data$Age)] <- mean(data$Age,na.rm=T)
and categorically: MF$belastetB <- as.factor(MF$belastetB), unfortunately with only partial success. In addition, by applying the metric formula, I had overwritten all my variables, but I still need them in their original form.
Unfortunately, I am not at all sure how to prepare my variables for binary logistic regression so that I get a p-value that is not 0. Because that indicates that I have an error in my formula, or my variables are not prepared correctly.
My categorical independent variables are: SES (high, medium, low), Angst (agree, neither, disagree), guteSeiten (agree, neither, disagree), finanzielleEinb (agree, neither, disagree), persKontakt (agree, neither, disagree)
My metric independent variables are: age, eig_Kinder, Zufriedenh_BZ (scale: 0-10), LZ (scale: 0-10)
For example, the output of LZ (metric) looks like this:
summary(MF$LZ)
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
0.000 6.000 7.000 6.794 8.000 10.000 707
table(MF$LZ)
0 1 2 3 4 5 6 7 8 9 10
231 261 728 1551 1775 4024 4166 7937 9792 4085 1710
And for Angst (categorial):
table(MF$Angst)
stimme nicht zu stimme zu weder noch
16918 14607 5255
summary(MF$Angst)
Length Class Mode
36967 character character
What formulas can I apply or how do I need to change/adjust my variables so that I get an output for the p-value, other than 0?