Hi, I have one basic doubt. Suppose X ~ N(50,10). I need to calculate Probability X = 50. dnorm(50, 50, 10) gives me [1] 0.03989423 My understanding is (which is bit statistical or may be mathematical) on a continuous scale, Probability of the type P(X = .....) are nothing but 1/Infinity i.e. = 0. So as per my understanding P(X = 50) should be 0, but even excel also gives 0.03989422. Obviously my understanding is wrong. If I put value of x = 0 in the normal density function, I do get 0.03989422. My confusion is on the continuous scale if the probability (X = x) doesn't make sense, 0.03989423 is significant to neglect. Please clarify Regards Vincy [[alternative HTML version deleted]]
You have calculated density, not probability. Probability is in [0,1]; density is in [0,Inf) And for a continuous variable, density cannot be interpreted as a probability or a frequency. S> -----Original Message----- > From: r-help-bounces at r-project.org > [mailto:r-help-bounces at r-project.org] On Behalf Of Vincy Pyne > Sent: 14 September 2011 12:24 > To: r-help at r-project.org > Subject: [R] Question regarding dnorm() > > Hi, > > I have one basic doubt. Suppose X ~ N(50,10). > > I need to calculate Probability X = 50. > > dnorm(50, 50, 10) gives me > [1] 0.03989423 > > My understanding is (which is bit statistical or may be > mathematical) on a continuous scale, Probability of the type > P(X = .....) are nothing but 1/Infinity i.e. = 0. So as per > my understanding P(X = 50) should be 0, but even excel also > gives 0.03989422. Obviously my understanding is wrong. If I > put value of x = 0 in the normal density function, I do get > 0.03989422. > > My confusion is on the continuous scale if the probability (X > = x) doesn't make sense, 0.03989423 is significant to neglect. > > Please clarify > > Regards > > Vincy > > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at r-project.org mailing list > 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. > *******************************************************************This email and any attachments are confidential. Any use...{{dropped:8}}
Dear Sirs, Thanks a lot for your explanation. This was such a hugh conceptual error from my end. I never realized probability and density are two different things. I used to feel I have strated understanding stats a bit. This explanation has changed everything again. Thanks a lot again Mr Ellison and Mr Mark for your guidance. Regards Vincy --- On Wed, 9/14/11, S Ellison <S.Ellison@LGCGroup.com> wrote: From: S Ellison <S.Ellison@LGCGroup.com> Subject: RE: [R] Question regarding dnorm() To: "Vincy Pyne" <vincy_pyne@yahoo.ca>, "r-help@r-project.org" <r-help@r-project.org> Received: Wednesday, September 14, 2011, 11:37 AM You have calculated density, not probability. Probability is in [0,1]; density is in [0,Inf) And for a continuous variable, density cannot be interpreted as a probability or a frequency. S> -----Original Message----- > From: r-help-bounces@r-project.org > [mailto:r-help-bounces@r-project.org] On Behalf Of Vincy Pyne > Sent: 14 September 2011 12:24 > To: r-help@r-project.org > Subject: [R] Question regarding dnorm() > > Hi, > > I have one basic doubt. Suppose X ~ N(50,10). > > I need to calculate Probability X = 50. > >dnorm(50, 50, 10) gives me> [1] 0.03989423 > > My understanding is (which is bit statistical or may be > mathematical) on a continuous scale, Probability of the type > P(X = .....) are nothing but 1/Infinity i.e. = 0. So as per > my understanding P(X = 50) should be 0, but even excel also > gives 0.03989422. Obviously my understanding is wrong. If I > put value of x = 0 in the normal density function, I do get > 0.03989422. > > My confusion is on the continuous scale if the probability (X > = x) doesn't make sense, 0.03989423 is significant to neglect. > > Please clarify > > Regards > > Vincy > > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help@r-project.org mailing list > 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. > *******************************************************************This email and any attachments are confidential. Any use...{{dropped:11}}