R help - Aug 2023 - Plotting Fitted vs Observed Values in Logistic Regression Model

Dear friends,

I hope  this email finds you all well. This is the dataset I am working
with:
dput(random_mod12_data2)
structure(list(Index = c(1L, 5L, 11L, 3L, 2L, 8L, 9L, 4L), x = c(5,
13, 25, 9, 7, 19, 21, 11), n = c(500, 500, 500, 500, 500, 500,
500, 500), r = c(100, 211, 391, 147, 122, 310, 343, 176), ratio = c(0.2,
0.422, 0.782, 0.294, 0.244, 0.62, 0.686, 0.352)), row.names = c(NA,
-8L), class = "data.frame")

A brief description of the dataset:
Index: is just a column that shows the ID of each observation (row)
x: is a column which gives information on the discount rate of the coupon
n: is the sample or number of observations
r: is the count of redeemed coupons
ratio: is just the ratio of redeemed coupons to n (total number of
observations)

#Fitting a logistic regression model to response variable y for problem 13.4
logistic_regmod2 <- glm(formula = ratio~x, family = binomial(logit), data
random_mod12_data2)

I would like to plot the value of r (in the y-axis) vs x (the different
discount rates) and then superimpose the logistic regression fitted values
all in the same plot.

How could I accomplish this?

Any help and/or guidance will be greatly appreciated.

Kind regards,
Paul

	[[alternative HTML version deleted]]

logistic_regmod2 <- glm(formula = ratio~x, family = binomial(logit), data
random_mod12_data2, weights =n)

plot(ratio ~ x, data = random_mod12_data2)

pframe <- data.frame(x = sort(random_mod12_data2$x))
pframe$ratio <- predict(logistic_regmod2, newdata = pframe, type = 
"response")
with(pframe, lines(x, ratio))



On 2023-08-01 9:57 a.m., Paul Bernal wrote:
> Dear friends,
> 
> I hope  this email finds you all well. This is the dataset I am working
> with:
> dput(random_mod12_data2)
> structure(list(Index = c(1L, 5L, 11L, 3L, 2L, 8L, 9L, 4L), x = c(5,
> 13, 25, 9, 7, 19, 21, 11), n = c(500, 500, 500, 500, 500, 500,
> 500, 500), r = c(100, 211, 391, 147, 122, 310, 343, 176), ratio = c(0.2,
> 0.422, 0.782, 0.294, 0.244, 0.62, 0.686, 0.352)), row.names = c(NA,
> -8L), class = "data.frame")
> 
> A brief description of the dataset:
> Index: is just a column that shows the ID of each observation (row)
> x: is a column which gives information on the discount rate of the coupon
> n: is the sample or number of observations
> r: is the count of redeemed coupons
> ratio: is just the ratio of redeemed coupons to n (total number of
> observations)
> 
> #Fitting a logistic regression model to response variable y for problem
13.4
> logistic_regmod2 <- glm(formula = ratio~x, family = binomial(logit),
data > random_mod12_data2)
> 
> I would like to plot the value of r (in the y-axis) vs x (the different
> discount rates) and then superimpose the logistic regression fitted values
> all in the same plot.
> 
> How could I accomplish this?
> 
> Any help and/or guidance will be greatly appreciated.
> 
> Kind regards,
> Paul
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
-- 
Dr. Benjamin Bolker
Professor, Mathematics & Statistics and Biology, McMaster University
Director, School of Computational Science and Engineering
(Acting) Graduate chair, Mathematics & Statistics
 > E-mail is sent at my convenience; I don't expect replies outside of 
working hours.

?s 14:57 de 01/08/2023, Paul Bernal escreveu:
> Dear friends,
> 
> I hope  this email finds you all well. This is the dataset I am working
> with:
> dput(random_mod12_data2)
> structure(list(Index = c(1L, 5L, 11L, 3L, 2L, 8L, 9L, 4L), x = c(5,
> 13, 25, 9, 7, 19, 21, 11), n = c(500, 500, 500, 500, 500, 500,
> 500, 500), r = c(100, 211, 391, 147, 122, 310, 343, 176), ratio = c(0.2,
> 0.422, 0.782, 0.294, 0.244, 0.62, 0.686, 0.352)), row.names = c(NA,
> -8L), class = "data.frame")
> 
> A brief description of the dataset:
> Index: is just a column that shows the ID of each observation (row)
> x: is a column which gives information on the discount rate of the coupon
> n: is the sample or number of observations
> r: is the count of redeemed coupons
> ratio: is just the ratio of redeemed coupons to n (total number of
> observations)
> 
> #Fitting a logistic regression model to response variable y for problem
13.4
> logistic_regmod2 <- glm(formula = ratio~x, family = binomial(logit),
data > random_mod12_data2)
> 
> I would like to plot the value of r (in the y-axis) vs x (the different
> discount rates) and then superimpose the logistic regression fitted values
> all in the same plot.
> 
> How could I accomplish this?
> 
> Any help and/or guidance will be greatly appreciated.
> 
> Kind regards,
> Paul
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
Hello,

Here is another way with ggplot2.
It doesn't give you the fitted values but it plots the fitted line.


library(ggplot2)

ggplot(random_mod12_data2, aes(x, ratio)) +
   geom_point() +
   stat_smooth(
     formula = y ~ x,
     method = glm,
     method.args = list(family = binomial),
     se = FALSE
   )


Hope this helps,

Rui Barradas