Rune Allnor wrote:> I am preparing a course for math layfolk, but need > to communicate the concepts of 'continuous' and > 'discrete' variables.Step ladder vs ramp.> Continous variable = measurable variable > Discrete variable = countable variable > > Does this make sense to others than me?Doctor Rune, using smart words makes you look dumber then you actually are. VLV
Lingo for layfolk?
Started by ●September 2, 2011
Reply by ●September 3, 20112011-09-03
Reply by ●September 4, 20112011-09-04
On 4 Sep, 01:34, Vladimir Vassilevsky <nos...@nowhere.com> wrote:> Rune Allnor wrote: > > I am preparing a course for math layfolk, but need > > to communicate the concepts of 'continuous' and > > 'discrete' variables. > > Step ladder vs ramp. > > > Continous variable = measurable variable > > Discrete variable = countable variable > > > Does this make sense to others than me? > > Doctor Rune, using smart words makes you look dumber then you actually are.Indeed. I have always thought that the true masters of any craft are those who make whatever they do, however complicated or skillful, look easy. Rune
Reply by ●September 4, 20112011-09-04
On 9/3/2011 4:23 AM, Rune Allnor wrote:> On Sep 3, 1:56 am, Richard Dobson<richarddob...@blueyonder.co.uk> > wrote: >> On 02/09/2011 23:59, Rich Webb wrote: >> >>> On Fri, 2 Sep 2011 15:49:48 -0700 (PDT), Rune Allnor >>> <all...@tele.ntnu.no> wrote: >> >>>> Hi all, >> >>>> I am preparing a course for math layfolk, but need >>>> to communicate the concepts of 'continuous' and >>>> 'discrete' variables. Users of a software package >>>> will need to use these concepts in order to select >>>> the proper analysis methods for whatever data >>>> they need to proces. >> >>>> I can't use those terms, or participants will likely >>>> flee the course. >> >> That is really a bit worrying! > > The context is simple data analysis (statistical process > control, SPC), for layfolk users where nothing can be > assumed or expected wrt prior education. I have found > that most people understand the concepts when described > to them, but that terminology and nomenclature might > become unnecessary hurdles foe learning, if introduced > at the wrong time. > > I usually explain the concepts as accurately as possible > in everyday language first, and then wrap up with something > like 'mathematicians or engineers use the term > <whatever> fot these things'. For some reason this > works better than first stating the term and then > explaining it. > > RuneRune, I think your motivation is a very good one. It's the implementation that's difficult. And, so, you ask here. That's a good idea. I'll not attack your proposals as they were the best you could do at the time. But my sense is that they are still a bit too formal/mathematical. And, there have been some good suggestions ike the string of beads. My notion would be to demonstrate what you mean by illustrative example. For example: -show or draw a picture of a continuous function. - then mark it at discrete points. - then talk about the apparent relationship between the independent variables. It seems to me that the notion of continuous and discrete comes fairly easy with this kind of introduction. In fact, isn't the independent variable at the core of the whole issue here really? Fred
Reply by ●September 5, 20112011-09-05
On Sep 4, 8:00�pm, Fred Marshall <fmarshallxremove_th...@acm.org> wrote:> On 9/3/2011 4:23 AM, Rune Allnor wrote: > > > > > > > On Sep 3, 1:56 am, Richard Dobson<richarddob...@blueyonder.co.uk> > > wrote: > >> On 02/09/2011 23:59, Rich Webb wrote: > > >>> On Fri, 2 Sep 2011 15:49:48 -0700 (PDT), Rune Allnor > >>> <all...@tele.ntnu.no> � �wrote: > > >>>> Hi all, > > >>>> I am preparing a course for math layfolk, but need > >>>> to communicate the concepts of 'continuous' and > >>>> 'discrete' variables. Users of a software package > >>>> will need to use these concepts in order to select > >>>> the proper analysis methods for whatever data > >>>> they need to proces. > > >>>> I can't use those terms, or participants will likely > >>>> flee the course. > > >> That is really a bit worrying! > > > The context is simple data analysis (statistical process > > control, SPC), for layfolk users where nothing can be > > assumed or expected wrt prior education. I have found > > that most people understand the concepts when described > > to them, but that terminology and nomenclature might > > become unnecessary hurdles foe learning, if introduced > > at the wrong time. > > > I usually explain the concepts as accurately as possible > > in everyday language first, and then wrap up with something > > like 'mathematicians or engineers use the term > > <whatever> �fot these things'. For some reason this > > works better than first stating the term and then > > explaining it. > > > Rune > > Rune, I think your motivation is a very good one. > > It's the implementation that's difficult. �And, so, you ask here. > That's a good idea. > > I'll not attack your proposals as they were the best you could do at the > time. �But my sense is that they are still a bit too > formal/mathematical. �And, there have been some good suggestions ike the > string of beads. > > My notion would be to demonstrate what you mean by illustrative example. > For example: > -show or draw a picture of a continuous function. > - then mark it at discrete points. > - then talk about the apparent relationship between the independent > variables. > It seems to me that the notion of continuous and discrete comes fairly > easy with this kind of introduction. �In fact, isn't the independent > variable at the core of the whole issue here really?I'n not sure. The measurements in this application will be done at discrete points in time; the trick is to select the correct representations of the various types of measurements: - physical dimensions of a produced item is a continuously distributed quantity - the number of defects or flaws associated with the same item is a discretely distributed quantity. The objective is to track such quantities over time in order to diagnosticize troublespots and improve production. The mechanics of doing the anslyses are the same in each case, but the underlying sw functionality differs. The users need to understand the difference well enough to select the correct options. Rune
Reply by ●September 5, 20112011-09-05
On 9/5/2011 1:30 AM, Rune Allnor wrote:> > I'n not sure. The measurements in this application > will be done at discrete points in time; the trick is > to select the correct representations of the various > types of measurements: > > - physical dimensions of a produced item is a continuously > distributed quantity > - the number of defects or flaws associated with the same > item is a discretely distributed quantity. > > The objective is to track such quantities over time > in order to diagnosticize troublespots and improve > production. > > The mechanics of doing the anslyses are the same in > each case, but the underlying sw functionality differs. > The users need to understand the difference well > enough to select the correct options. > > RuneOh, well then I didn't understand the objective very well I guess. But now you have me curious: The physical dimensions of a produced item, or should one say: the physical dimensions of produced items?, is a population of discrete events it seems to me. That there may be the possibility of any value down to the limits of measurement being recorded doesn't make it any less discrete does it? Well, I do understand that these values would appear to have some physical character that suggests the values come from a possbily continuous distribution. Of course the number of defects or flaws is an integer. So, it's a matter of counting. I'd have to wonder if putting the dimensions in a computer using 32-bit binary, suitably scaled, is any different than counting? They seem the same to me but perhaps there's a philosophical difference? I obviously know nothing about the software you're referring to so am probably missing a lot. In a way this reminds me of a discussion I had with Jerry where I was seeking some help in measuring wastewater concentrations. I *know* that the sample rate is "too low" and worried over that quite a bit. Eventually I decided that the sample rate and ordering of samples wasn't really necessary at all - and that the low sample rate would be fine. What was more important was to calculate the distribution of the samples. In turn, this gave rise to the idea that the samples should not be taken at the same time on the same day of the week but should be rotated to remove the bias of possible weekly or daily trends. But I digress.... Fred
Reply by ●September 5, 20112011-09-05
On 9/3/2011 7:54 AM, Rune Allnor wrote:> On 3 Sep, 01:56, Richard Dobson<richarddob...@blueyonder.co.uk> > wrote: >> On 02/09/2011 23:59, Rich Webb wrote: >> >>> On Fri, 2 Sep 2011 15:49:48 -0700 (PDT), Rune Allnor >>> <all...@tele.ntnu.no> wrote: >> >>>> Hi all, >> >>>> I am preparing a course for math layfolk, but need >>>> to communicate the concepts of 'continuous' and >>>> 'discrete' variables. Users of a software package >>>> will need to use these concepts in order to select >>>> the proper analysis methods for whatever data >>>> they need to proces. >> >>>> I can't use those terms, or participants will likely >>>> flee the course. >> >> That is really a bit worrying! > > It's not as bad as it sounds. This is a class for people who want > to use Statistical Process Control, SPC, but where nothing > can be assumed or expected wrt prior education. Choosing the > correct method is crucial, even if the nasty bits are wrapped > inside some software package. > > I have found that first explaining whatever concept accurately > but in familiar language, and only introducing the terminology > afterwards, works far better than introducing terminology first > and then explaining it. I don't know why, but it seems seeing > 'complicated' words or terms tend to intimidate people. > Particularly people who haven's got that much of an academic > education.An excellent book for beginning practitioners in statistical process control is "Facts from Figures" by M.J. Moroney. A statistician gave it to my wife-to-be around 1956. I don't know if it is still in print, but I got a copy for a friend about 20 years ago. Paperback, by Pelican Books. A search turns up http://www.alibris.com/search/books/qwork/2230822/used/Facts%20from%20figures http://www.amazon.com/FACTS-FIGURES-M-J-MORONEY/dp/B0014OFV5A It's being still prominent speaks well for it. Jerry -- Engineering is the art of making what you want from things you can get.
Reply by ●September 6, 20112011-09-06
On Sep 5, 10:34�pm, Jerry Avins <j...@ieee.org> wrote:> On 9/3/2011 7:54 AM, Rune Allnor wrote: > > > > > > > On 3 Sep, 01:56, Richard Dobson<richarddob...@blueyonder.co.uk> > > wrote: > >> On 02/09/2011 23:59, Rich Webb wrote: > > >>> On Fri, 2 Sep 2011 15:49:48 -0700 (PDT), Rune Allnor > >>> <all...@tele.ntnu.no> � �wrote: > > >>>> Hi all, > > >>>> I am preparing a course for math layfolk, but need > >>>> to communicate the concepts of 'continuous' and > >>>> 'discrete' variables. Users of a software package > >>>> will need to use these concepts in order to select > >>>> the proper analysis methods for whatever data > >>>> they need to proces. > > >>>> I can't use those terms, or participants will likely > >>>> flee the course. > > >> That is really a bit worrying! > > > It's not as bad as it sounds. This is a class for people who want > > to use Statistical Process Control, SPC, but where nothing > > can be assumed or expected wrt prior education. Choosing the > > correct method is crucial, even if the nasty bits are wrapped > > inside some software package. > > > I have found that first explaining whatever concept accurately > > but in familiar language, and only introducing the terminology > > afterwards, works far better than introducing terminology first > > and then explaining it. I don't know why, but it seems seeing > > 'complicated' words or terms tend to intimidate people. > > Particularly people who haven's got that much of an academic > > education. > > An excellent book for beginning practitioners in statistical process > control is "Facts from Figures" by M.J. Moroney. A statistician gave it > to my wife-to-be around 1956. I don't know if it is still in print, but > I got a copy for a friend about 20 years ago. Paperback, by Pelican > Books. A search turns up > > http://www.alibris.com/search/books/qwork/2230822/used/Facts%20from%2... > > http://www.amazon.com/FACTS-FIGURES-M-J-MORONEY/dp/B0014OFV5A > > It's being still prominent speaks well for it. > > Jerry > -- > Engineering is the art of making what you want from things you can get.Wheeler have written a lot of books on spc. I prefer oakland's book. Sorry for not providing links, writing from phone. Rune
Reply by ●September 6, 20112011-09-06
On Sep 5, 10:01�pm, Fred Marshall <fmarshallxremove_th...@acm.org> wrote:> On 9/5/2011 1:30 AM, Rune Allnor wrote: > > > > > > > > > I'n not sure. The measurements in this application > > will be done at discrete points in time; the trick is > > to select the correct representations of the various > > types of measurements: > > > - physical dimensions of a produced item is a continuously > > � �distributed quantity > > - the number of defects or flaws associated with the same > > � �item is a discretely distributed quantity. > > > The objective is to track such quantities over time > > in order to diagnosticize troublespots and improve > > production. > > > The mechanics of doing the anslyses are the same in > > each case, but the underlying sw functionality differs. > > The users need to understand the difference well > > enough to select the correct options. > > > Rune > > Oh, well then I didn't understand the objective very well I guess. > > But now you have me curious: > > The physical dimensions of a produced item, or should one say: the > physical dimensions of produced items?, is a population of discrete > events it seems to me. �That there may be the possibility of any value > down to the limits of measurement being recorded doesn't make it any > less discrete does it? �Well, I do understand that these values would > appear to have some physical character that suggests the values come > from a possbily continuous distribution.One measures some items, and attempt to infer conclusions about the population. The main differences between SPC and 'regular' statistics are that - SPC uses some rather simplified computations - SPC deliberately aims to track temporal developments on a sample-to-sample basis, whereas 'regular' statistics usually is based on stationary properties across the sample.> Of course the number of defects or flaws is an integer. �So, it's a > matter of counting. > > I'd have to wonder if putting the dimensions in a computer using 32-bit > binary, suitably scaled, is any different than counting? �They seem the > same to me but perhaps there's a philosophical difference?Computer number systems have a limited number of bits and so a finite number of states. The bit pattern points to the represented number value, depending on encoding. Rune
Reply by ●September 6, 20112011-09-06
On 9/5/2011 10:44 PM, Rune Allnor wrote:> On Sep 5, 10:01 pm, Fred Marshall<fmarshallxremove_th...@acm.org> > wrote: >> On 9/5/2011 1:30 AM, Rune Allnor wrote: >> >> >> >> >> >> >> >>> I'n not sure. The measurements in this application >>> will be done at discrete points in time; the trick is >>> to select the correct representations of the various >>> types of measurements: >> >>> - physical dimensions of a produced item is a continuously >>> distributed quantity >>> - the number of defects or flaws associated with the same >>> item is a discretely distributed quantity. >> >>> The objective is to track such quantities over time >>> in order to diagnosticize troublespots and improve >>> production. >> >>> The mechanics of doing the anslyses are the same in >>> each case, but the underlying sw functionality differs. >>> The users need to understand the difference well >>> enough to select the correct options. >> >>> Rune >> >> Oh, well then I didn't understand the objective very well I guess. >> >> But now you have me curious: >> >> The physical dimensions of a produced item, or should one say: the >> physical dimensions of produced items?, is a population of discrete >> events it seems to me. That there may be the possibility of any value >> down to the limits of measurement being recorded doesn't make it any >> less discrete does it? Well, I do understand that these values would >> appear to have some physical character that suggests the values come >> from a possbily continuous distribution. > > One measures some items, and attempt to infer > conclusions about the population. The main > differences between SPC and 'regular' statistics > are that > > - SPC uses some rather simplified computations > - SPC deliberately aims to track temporal developments > on a sample-to-sample basis, whereas 'regular' > statistics usually is based on stationary properties > across the sample. > >> Of course the number of defects or flaws is an integer. So, it's a >> matter of counting. >> >> I'd have to wonder if putting the dimensions in a computer using 32-bit >> binary, suitably scaled, is any different than counting? They seem the >> same to me but perhaps there's a philosophical difference? > > Computer number systems have a limited number > of bits and so a finite number of states. The bit pattern > points to the represented number value, depending > on encoding. > > Rune >Yeah, I understand about computer number systems. I was trying to relate that to the counting flaws example. Both result in "integers" if you like. Seems to me that SPC isn't any different. Maybe you calculate mean and variance of dimensions over some termporal window and then compare results window-to-window. Isn't that essentially what a control chart does with mean values? Fred
Reply by ●September 6, 20112011-09-06
>Well, I usually don't feel bad talking about "reconstructing an analog >waveform from a digital signal", for example. As long as it's my >presentation, it's me who's defining the terms, no one else. >If somebody comes up with an incompatible definition, that's his problem, >not mine."reconstructing an analog waveform from a digital signal" is OK if you drop the "re". DSP people love to talk about reconstructing analogue signals. A digital record/replay process may reconstruct an analogue signal, but the DAC at the backend of some DSP is usually creating an analogue signal that was never analogue before. We are usually "constructing an analog signal from a digital signal". Steve
