[R] Bootstrapping One- and Two-Sample Hypothesis Tests of Proportion

Discussion:

Janh Anni

2018-11-27 22:33:11 UTC

Hello R Experts!

Does anyone know of a relatively straightforward way to bootstrap
hypothesis tests for proportion in R?

Thanks in advance!

Janh

[[alternative HTML version deleted]]

______________________________________________
R-***@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.

Rui Barradas

2018-11-28 17:38:18 UTC

Permalink

Hello,

What have you tried?
Reproducible example please.

http://adv-r.had.co.nz/Reproducibility.html
https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example
https://www.r-bloggers.com/minimal-reproducible-examples/

Rui Barradas

Post by Janh Anni
Hello R Experts!
Does anyone know of a relatively straightforward way to bootstrap
hypothesis tests for proportion in R?
Thanks in advance!
Janh
[[alternative HTML version deleted]]
______________________________________________
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.

______________________________________________
R-***@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.

Janh Anni

2018-11-29 23:30:27 UTC

Permalink

Hi Rui,

Thanks a lot for responding and I apologize for my late response. I tried
using the *boot.two.per* function in the wBoot package which stated that it
could bootstrap 2-sample tests for both means and proportions but it turned
out that it only works for the mean.

Thanks again,
Janh

Post by Rui Barradas
Hello,
What have you tried?
Reproducible example please.
http://adv-r.had.co.nz/Reproducibility.html
https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example
https://www.r-bloggers.com/minimal-reproducible-examples/
Rui Barradas

http://www.R-project.org/posting-guide.html

Post by Janh Anni
and provide commented, minimal, self-contained, reproducible code.

[[alternative HTML version deleted]]

______________________________________________
R-***@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.

Bert Gunter

2018-11-29 23:45:24 UTC

Permalink

... but as Duncan pointed out already, I believe, a proportion **is** a
mean -- of 0/1 responses.

Bert Gunter

"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )

Post by Janh Anni
Hi Rui,
Thanks a lot for responding and I apologize for my late response. I tried
using the *boot.two.per* function in the wBoot package which stated that it
could bootstrap 2-sample tests for both means and proportions but it turned
out that it only works for the mean.
Thanks again,
Janh

Post by Rui Barradas
Hello,
What have you tried?
Reproducible example please.
http://adv-r.had.co.nz/Reproducibility.html

https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example

Post by Rui Barradas
https://www.r-bloggers.com/minimal-reproducible-examples/
Rui Barradas

http://www.R-project.org/posting-guide.html

Post by Janh Anni
and provide commented, minimal, self-contained, reproducible code.

[[alternative HTML version deleted]]
______________________________________________
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.

Janh Anni

2018-11-29 23:57:19 UTC

Permalink

Hi Bert,

You mean, just compute the test specifying the mean as the parameter but
using 1's and 0's for the data? Also I don't get how a proportion is a
mean of 0/1 responses. Could you please elaborate? Thanks!

Janh

Post by Bert Gunter
... but as Duncan pointed out already, I believe, a proportion **is** a
mean -- of 0/1 responses.
Bert Gunter
"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )

Post by Rui Barradas
Hello,
What have you tried?
Reproducible example please.
http://adv-r.had.co.nz/Reproducibility.html

https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example

Post by Rui Barradas
https://www.r-bloggers.com/minimal-reproducible-examples/
Rui Barradas

http://www.R-project.org/posting-guide.html

Post by Janh Anni
and provide commented, minimal, self-contained, reproducible code.

Janh Anni

2018-11-30 00:23:37 UTC

Permalink

Hi Marc,

I see what you are saying. I will try re-running the* boot.two.per*
function using 1's and 0's for the data and specifying mean as the
parameter and see what happens. I will report back. Thanks so much for
your kind assistance!

Janh

Hi,

1 / 4

[1] 0.25

mean(c(1, 0, 0, 0))

[1] 0.25

3 / 9

[1] 0.3333333

mean(c(1, 1, 1, 0, 0, 0, 0, 0, 0))

[1] 0.3333333
Regards,
Marc Schwartz
Hi Bert,
You mean, just compute the test specifying the mean as the parameter but
using 1's and 0's for the data? Also I don't get how a proportion is a
mean of 0/1 responses. Could you please elaborate? Thanks!
Janh
... but as Duncan pointed out already, I believe, a proportion **is** a
mean -- of 0/1 responses.
Bert Gunter
"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )
Hi Rui,
Thanks a lot for responding and I apologize for my late response. I tried
using the *boot.two.per* function in the wBoot package which stated that it
could bootstrap 2-sample tests for both means and proportions but it turned
out that it only works for the mean.
Thanks again,
Janh
Hello,
What have you tried?
Reproducible example please.
http://adv-r.had.co.nz/Reproducibility.html
https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example
https://www.r-bloggers.com/minimal-reproducible-examples/
Rui Barradas
Hello R Experts!
Does anyone know of a relatively straightforward way to bootstrap
hypothesis tests for proportion in R?
Thanks in advance!
Janh