[R] Need Help To Solve An Equation In R

[Kenneth Knoblauch]

This looks an awful lot like you are trying to solve for d' in an 
m-alternative forced choice experiment for an unbiased observer.  Try 
the function dprime.mAFC from the psyphy package.  For comparison with 
your example, it's code is:


 psyphy:::dprime.mAFC
function (Pc, m)
{
m <- as.integer(m)
if (m < 2)
stop("m must be an integer greater than 1")
if (!is.integer(m))
stop("m must be an integer")
if (Pc <= 0 || Pc >= 1)
stop("Pc must be in (0,1)")
est.dp <- function(dp) {
pr <- function(x) dnorm(x - dp) * pnorm(x)^(m - 1)
Pc - integrate(pr, lower = -Inf, upper = Inf)$value
}
dp.res <- uniroot(est.dp, interval = c(-10, 10))
dp.res$root
}


Hope that helps,

best,

Ken


On Sat, May 27, 2017 at 9:16 AM, Neetu Shah  
wrote:

Dear Sir/Ma'am,

I am trying to make a function to solve an equation that is given 
below:

findH <- function(p_star, k){
fun <- function(y){
(pnorm(y+h))^(k-1)*dnorm(y)
}
lhs <- integrate(fun, -Inf, Inf)$value
return(uniroot(lhs, lower = -10, upper = 10,
tol = p_star)$root)
}
In lhs, I integrated a function with respect to y and there would be an
unknown h that I need to find.
I need to equate this lhs to p_star value in order to find h. Which
function should I use to solve this equation?
Please guide me regarding this.
Thank you.

--
With Regards,
Neetu Shah,
B.Tech.(CS),
3rd Year,
IIIT Vadodara.

--
Kenneth Knoblauch
Inserm U1208
Stem-cell and Brain Research Institute
18 avenue du Doyen Lépine
69500 Bron
France
tel: +33 (0)4 72 91 34 77
fax: +33 (0)4 72 91 34 61
portable: +33 (0)6 84 10 64 10
http://www.sbri.fr/members/kenneth-knoblauch.html

__
R-help@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.

Re: [R] Need Help To Solve An Equation In R

[Bert Gunter]

Then:

1. Always cc the list;

2. Read and follow the posting guide: no HTML, plain text only.


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 )


On Sat, May 27, 2017 at 11:05 AM, Neetu Shah  wrote:
> Dear Sir,
>
> It is not homework. I am trying to develop a library in R as my project. My
> mentor said to ask this doubt on R forum. As I am not able to solve that
> equation in R. I need to know the alternative for uniroot function. Please
> help me regarding this.
>
>
> --
> With Regards,
> Neetu Shah,
> B.Tech.(CS),
> 3rd Year,
> IIIT Vadodara.
>
>
> On Sat, May 27, 2017 at 11:11 PM, Bert Gunter 
> wrote:
>>
>> Homework? We generally don't do homework here.
>>
>> Cheers,
>> Bert
>> 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 )
>>
>>
>> On Sat, May 27, 2017 at 9:16 AM, Neetu Shah  wrote:
>> > Dear Sir/Ma'am,
>> >
>> > I am trying to make a function to solve an equation that is given below:
>> > findH <- function(p_star, k){
>> > fun <- function(y){
>> > (pnorm(y+h))^(k-1)*dnorm(y)
>> > }
>> > lhs <- integrate(fun, -Inf, Inf)$value
>> > return(uniroot(lhs, lower = -10, upper = 10,
>> > tol = p_star)$root)
>> > }
>> > In lhs, I integrated a function with respect to y and there would be an
>> > unknown h that I need to find.
>> > I need to equate this lhs to p_star value in order to find h. Which
>> > function should I use to solve this equation?
>> > Please guide me regarding this.
>> > Thank you.
>> >
>> > --
>> > With Regards,
>> > Neetu Shah,
>> > B.Tech.(CS),
>> > 3rd Year,
>> > IIIT Vadodara.
>> >
>> > [[alternative HTML version deleted]]
>> >
>> > __
>> > R-help@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.
>
>
>
>
>

__
R-help@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.

Re: [R] Need Help To Solve An Equation In R

[Bert Gunter]

Homework? We generally don't do homework here.

Cheers,
Bert
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 )


On Sat, May 27, 2017 at 9:16 AM, Neetu Shah  wrote:
> Dear Sir/Ma'am,
>
> I am trying to make a function to solve an equation that is given below:
> findH <- function(p_star, k){
> fun <- function(y){
> (pnorm(y+h))^(k-1)*dnorm(y)
> }
> lhs <- integrate(fun, -Inf, Inf)$value
> return(uniroot(lhs, lower = -10, upper = 10,
> tol = p_star)$root)
> }
> In lhs, I integrated a function with respect to y and there would be an
> unknown h that I need to find.
> I need to equate this lhs to p_star value in order to find h. Which
> function should I use to solve this equation?
> Please guide me regarding this.
> Thank you.
>
> --
> With Regards,
> Neetu Shah,
> B.Tech.(CS),
> 3rd Year,
> IIIT Vadodara.
>
> [[alternative HTML version deleted]]
>
> __
> R-help@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.

__
R-help@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.

Re: [R] Need Help To Solve An Equation In R

[David Winsemius]

> On May 27, 2017, at 9:16 AM, Neetu Shah  wrote:
> 
> Dear Sir/Ma'am,
> 
> I am trying to make a function to solve an equation that is given below:
> findH <- function(p_star, k){
> fun <- function(y){
> (pnorm(y+h))^(k-1)*dnorm(y)
> }
> lhs <- integrate(fun, -Inf, Inf)$value
> return(uniroot(lhs, lower = -10, upper = 10,
> tol = p_star)$root)
> }
> In lhs, I integrated a function with respect to y and there would be an
> unknown h that I need to find.

uniroot needs a function as its first argument. `integrate(fun, -Inf, 
Inf)$value` does not return a function. it will return a numeric value (if it 
succeeds). 

I have no idea whether this makes any mathematical sense because you have not 
described the background for this effort and have not shown how you expect to 
call `findH`. Is `h` supposed to be some sort of non-centrality parameter with 
`k` representing degrees of freedom?

I tried this code that does run, although it fails gracefully at runtime:

findH <- function(p_star= 0.004, k=2){
   fun <- function(y,h){
(pnorm(y+h))^(k-1)*dnorm(y)
   }
lhs <- function(x) { integrate(fun, lower=-Inf, upper=Inf, h=x)$value }
return(uniroot(lhs, lower = -10, upper = 10, tol = p_star)$root)
}
#---
> findH(k=6)
Error in uniroot(lhs, lower = -10, upper = 10, tol = p_star) : 
  f() values at end points not of opposite sign



> I need to equate this lhs to p_star value in order to find h.

> Which
> function should I use to solve this equation?
> Please guide me regarding this.
> Thank you.
> 
> -- 
> With Regards,
> Neetu Shah,
> B.Tech.(CS),
> 3rd Year,
> IIIT Vadodara.
> 
>   [[alternative HTML version deleted]]
> 
> __
> R-help@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.

David Winsemius
Alameda, CA, USA

__
R-help@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.

[R] Need Help To Solve An Equation In R

[Neetu Shah]

Dear Sir/Ma'am,

I am trying to make a function to solve an equation that is given below:
findH <- function(p_star, k){
fun <- function(y){
(pnorm(y+h))^(k-1)*dnorm(y)
}
lhs <- integrate(fun, -Inf, Inf)$value
return(uniroot(lhs, lower = -10, upper = 10,
tol = p_star)$root)
}
In lhs, I integrated a function with respect to y and there would be an
unknown h that I need to find.
I need to equate this lhs to p_star value in order to find h. Which
function should I use to solve this equation?
Please guide me regarding this.
Thank you.

-- 
With Regards,
Neetu Shah,
B.Tech.(CS),
3rd Year,
IIIT Vadodara.

[[alternative HTML version deleted]]

__
R-help@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.