Lecture 3

From Physiki
(Difference between revisions)
Jump to: navigation, search
(Created page with " Present the hamburger problem I feed students hamburgers to students and get the distribution of hamburgers eaten by a CSM student with mean=1.5 +- sigma=0.5. I get a histo...")
 
 
(2 intermediate revisions by one user not shown)
Line 1: Line 1:
 +
'''Value proposition for a University:''' what value do you get and how does that fit into this course?
  
 +
1.) Learn critical/analytical thinking.
  
Present the hamburger problem
+
2.) Learn content; how to construct a professional argument that data support a scientific model.
I feed students hamburgers to students and get the distribution of hamburgers eaten by a CSM student with mean=1.5 +- sigma=0.5. I get a histogram which when normalized looks like a bell curve. This is the prob density function. Assume this PDF is Gaussian. What are the units of this  density function? Think about charge density on a line.
+
  
I want to feed a class of 100 students being about 80% (integrating the pdf from 0 to 1 std dev above mean) sure that the class has enough to eat. How many hamburgers do I need to bring? Questions?
+
3.) Personal development;
  
What does this mean if the number eaten is negative in the Gaussian distribution? Hamburgers are vomited? Critical thinking: emphasize that we are modeling when using mean and standard deviations. Note that a gaussian distribution with a given mean does not go to zero at h = 0 . Rather it has a tail that extends to negative h . NO it means that a Gaussian distribution is not a valid model.
+
'''Comment; Value Proposition A (critical/analytical thinking)'''
 +
I often have students collect data then assume both that the model is valid and the data MUST support the model. After all the model is on wikipedia. That’s not science! I understand your whole education often has been a game of getting good grades when you say you understand the model that is being presented and bad grades when you question it. Many of the labs you do here are designed to kick you of that habit. Don’t assume that the data you get will support the model. Let the data drive that conclusion. Try not to get frustrated because this is the type of data that you will see when you get out of school.
  
Sketch population distribution and under it the distribution of the mean number of hamburgers eaten by a class. Note the difference in the axes, the upper has number of students vs number of burgers (with sigma) while the lower is number of classes vs mean number of hamburgers eaten by ONE student for the whole class (with sigmaMean = sigma/Sqrt[N]).
 
  
To get the number of burgers to buy for a class (burgers/class) multiply the mean  number of hamburgers per student for the class by the number of students in the class or  N (mean+sigma/Sqrt[N]).
+
'''Example; Value Proposition A (critical/analytical thinking)'''
  
Why do I only need to bring 155 hamburgers rather than 200? In a class some eat more and some less so the variation over 100 students is less than that for individuals. As the number in the class increases the PDF narrows. Does the student population PDF narrow as the number of students included in the histogram increases?
+
A company makes mechanical pencils. The lead cylinders have a mean diameter of 1.00 mm and standard deviation of 0.2 mm.  
  
Say you take 100 voltage measurements. You calculate the std dev for these getting sigma. Now you present your results as Vavg +- sigma/Sqrt[100} where the latter is the error.
+
Part (a) What diameter should I design the metal opening into which the lead fits so that 97 percent of the lead cylinders fit my pencil?
  
 +
Sketch a Gaussian and label the axes as probability density function, PDF, and “led” diameter. Ask what impression does the misspelling give you? Talk about charge density function for a charge uniformly distributed on a line or surface or volume. What is similar and different from the PDF? Talk about quantum mechanics and the PDF associated with finding an atom along the x-axis. Review the integration of the Gaussian here
 +
https://en.wikipedia.org/wiki/Standard_deviation
  
If we plotted this (the upper applet graph) would be number of students vs the number of hamburgers eaten. If we plotted this on the applet graph directly below it would be the number of classes vs the mean number of hamburgers eaten in a class = total number eaten in a class divided by the number of students in that class. This mean number has little significance. A number which is more important is how many total hamburgers are eaten since that’s what I have to purchase. To get this distribution just multiply the mean value by N. That shifts the histogram to the right. Both the mean and stnd dev increase, the first by a factor of N and the second by 1/Sqrt[N].
+
Ans: 1.0 mm + 0.4 = 1.4 mm or 2 std dev away from the mean of the population.
Ans: 150 plus sigma Sqrt[N]. Sketch gaussian dist and prob between points on that.
+
  
 +
Part (b) We sell a rectangular box into which 100 lead pieces fit together on the bottom of the box (it is an automatic dispenser which loads the lead into the mechanical pencil) dispenser which loads the lead into the mechanical pencil). If 98 percent (integrate from 0 to 2 sigma to right of mean) of the boxes can be cleanly (fit flat on the box bottom) loaded with pencil leads, what box length do I need? 2 percent of the boxes will then have some cylinders ajar in the box bottom.
  
 +
Here are two answers:
 +
-One answer is 100 (1.00 + 0.2) = 100 + 20 mm. To have this be the correct answer then the length distribution of 100 cylinders next to each other would have to consist of randomly taking one cylinder from the population and putting 100 cylinders which are of IDENTICAL diameter next to each other. Next take  a different cylinder from the population and putting 100 cylinders which are of IDENTICAL diameter next to each other. In this way you build up a distribution of lengths which has mean value 100 mm and standard deviation 20 mm.
  
The TAs and I will meet with you to talk about the lab reports you handed in last week. Take the comments with the understanding that we are trying to help you improve your writing and not as a personal criticism.  
+
-Another answer is to take 100 random samples and line them up. However, when you fill the box, the 100 cylinders are randomly drawn from the population and are NOT identical. In this case the distribution you get is the distribution of means for a random sample of 100 cylinders placed in a line. The mean diameter for these 100 is 1.00 + 0.2/Sqrt[100]. Now when you line up 100 of cylinders with this mean and standard deviation you get a distribution of total lengths given by 100 x( 1.0 +0.2/Sqrt[100]) = 102 mm for 1 standard deviation and 104 mm for 2 standard deviations.
 +
Why isn’t it 100 x(1.0) + 0.2/Sqrt[100]?
  
Your writing
+
Remember the derivation of error in an average value using derivatives? delVmean=Sqrt[(delV)^2/n] = delV/Sqrt[n]. This is an error in the average value NOT the error in the sum value. The sum value is the total length which is about 100 mm while the average value of 100 readings has a mean of 1 mm. Label the plots of the distributions for individual lead diameters (mean 1.0 mm), the length of 100 next to each other (mean 100 mm), and avg. values (mean 1.0 mm)
 +
 
 +
https://en.wikipedia.org/wiki/Standard_deviation
 +
This formula looks like the population stnd dev depends on 1/sqrt[N]. Why doesn’t it?
 +
 
 +
Show applet.
 +
http://onlinestatbook.com/stat_sim/sampling_dist/index.html
 +
 
 +
-Note the normalized distribution (increase number of samples but peak height stays same)
 +
-Note also the horizontal axes don’t have units. What is the physical significance of this math exercise? Say the distribution is of the failure time of light bulbs. You get the population distribution of number vs failure time. Next, take a group of 25 light bulbs and ask what is the average failure time for this group. What does this mean physically? The horizontal axis is the average failure time per light bulb in a group of 25 whereas the axis of the population distribution is the failure time per bulb. Not much physical significance to this information.
 +
The horizontal axes for the means is probability vs mean value (mean length of 100 cylinders). Without the labels the population and mean plots are confusing.
 +
 
 +
'''Example; Value Proposition C (Personal development): Writing'''
 +
 
 +
I submitted a manuscript paper and got the following reviewer comment:
  
Review of a recent paper of mine.
 
 
“The authors consider a bipartite system consisting of a particle and a mirror, whose respective positions are measured with a time-delay. A joint probability density is calculated, which exhibits a superposition of the mirror state.
 
“The authors consider a bipartite system consisting of a particle and a mirror, whose respective positions are measured with a time-delay. A joint probability density is calculated, which exhibits a superposition of the mirror state.
 
The paper is somewhat lengthy, not without redundancy, rather economical in the use of commas and now and then, one is taken by surprise by the syntax.”
 
The paper is somewhat lengthy, not without redundancy, rather economical in the use of commas and now and then, one is taken by surprise by the syntax.”
Line 33: Line 52:
 
What is most important on the reviewers mind? The writing and not the content!
 
What is most important on the reviewers mind? The writing and not the content!
  
Handback lab schedule
+
Ask the students: How do you respond to such criticism? Do you see it as the reviewers problem not to focus on the science? Do you go online and troll the journal? Do you get over your disgust and fix the manuscript up? Do you realize that it is not the journal's job to help you fix up your manuscript. They need only accept or reject manuscripts they think are of value to their readership. 
It may seem like I’m forcing you to jump through all sorts of hoops without giving you reasons. Here are some:
+
 
-I use a wiki because these are used in industry and academia to document group work. Log in and show how the edited pages are saved. How many have used a wiki?
+
How you respond is an illustration of your character. The comments the TAs and I provide about your lab reports are intended to help you develop into a professional writer.  
-I have you give talks on your lab to give you experience in verbally expressing your understanding.
+
 
-You write lab reports to practice expressing your understanding in writing.
+
'''Example; Value Proposition C (Personal development): Creativity'''
You may think you know how to talk and write. However, these skills change over time. I always enjoy hearing one of our grads return to give a physics colloquium. Just listening to them thoroughly present their ideas and answer questions demonstrates how they have continued to grow.
+
 
 +
What is art? I like the definition that art makes you think about the world in new ways. How does an artist know they have created a very special work of art? How do you know you’ve done a special job of conveying your data? When you do know it’s art.
 +
 
 +
 
 +
Data visualization Part (a).
 +
 
 +
Go over the population pyramid example found here
 +
http://www.randalolson.com/2015/07/14/rethinking-the-population-pyramid/

Latest revision as of 16:42, 16 September 2017

Value proposition for a University: what value do you get and how does that fit into this course?

1.) Learn critical/analytical thinking.

2.) Learn content; how to construct a professional argument that data support a scientific model.

3.) Personal development;

Comment; Value Proposition A (critical/analytical thinking) I often have students collect data then assume both that the model is valid and the data MUST support the model. After all the model is on wikipedia. That’s not science! I understand your whole education often has been a game of getting good grades when you say you understand the model that is being presented and bad grades when you question it. Many of the labs you do here are designed to kick you of that habit. Don’t assume that the data you get will support the model. Let the data drive that conclusion. Try not to get frustrated because this is the type of data that you will see when you get out of school.


Example; Value Proposition A (critical/analytical thinking)

A company makes mechanical pencils. The lead cylinders have a mean diameter of 1.00 mm and standard deviation of 0.2 mm.

Part (a) What diameter should I design the metal opening into which the lead fits so that 97 percent of the lead cylinders fit my pencil?

Sketch a Gaussian and label the axes as probability density function, PDF, and “led” diameter. Ask what impression does the misspelling give you? Talk about charge density function for a charge uniformly distributed on a line or surface or volume. What is similar and different from the PDF? Talk about quantum mechanics and the PDF associated with finding an atom along the x-axis. Review the integration of the Gaussian here https://en.wikipedia.org/wiki/Standard_deviation

Ans: 1.0 mm + 0.4 = 1.4 mm or 2 std dev away from the mean of the population.

Part (b) We sell a rectangular box into which 100 lead pieces fit together on the bottom of the box (it is an automatic dispenser which loads the lead into the mechanical pencil) dispenser which loads the lead into the mechanical pencil). If 98 percent (integrate from 0 to 2 sigma to right of mean) of the boxes can be cleanly (fit flat on the box bottom) loaded with pencil leads, what box length do I need? 2 percent of the boxes will then have some cylinders ajar in the box bottom.

Here are two answers: -One answer is 100 (1.00 + 0.2) = 100 + 20 mm. To have this be the correct answer then the length distribution of 100 cylinders next to each other would have to consist of randomly taking one cylinder from the population and putting 100 cylinders which are of IDENTICAL diameter next to each other. Next take a different cylinder from the population and putting 100 cylinders which are of IDENTICAL diameter next to each other. In this way you build up a distribution of lengths which has mean value 100 mm and standard deviation 20 mm.

-Another answer is to take 100 random samples and line them up. However, when you fill the box, the 100 cylinders are randomly drawn from the population and are NOT identical. In this case the distribution you get is the distribution of means for a random sample of 100 cylinders placed in a line. The mean diameter for these 100 is 1.00 + 0.2/Sqrt[100]. Now when you line up 100 of cylinders with this mean and standard deviation you get a distribution of total lengths given by 100 x( 1.0 +0.2/Sqrt[100]) = 102 mm for 1 standard deviation and 104 mm for 2 standard deviations. Why isn’t it 100 x(1.0) + 0.2/Sqrt[100]?

Remember the derivation of error in an average value using derivatives? delVmean=Sqrt[(delV)^2/n] = delV/Sqrt[n]. This is an error in the average value NOT the error in the sum value. The sum value is the total length which is about 100 mm while the average value of 100 readings has a mean of 1 mm. Label the plots of the distributions for individual lead diameters (mean 1.0 mm), the length of 100 next to each other (mean 100 mm), and avg. values (mean 1.0 mm)

https://en.wikipedia.org/wiki/Standard_deviation This formula looks like the population stnd dev depends on 1/sqrt[N]. Why doesn’t it?

Show applet. http://onlinestatbook.com/stat_sim/sampling_dist/index.html

-Note the normalized distribution (increase number of samples but peak height stays same) -Note also the horizontal axes don’t have units. What is the physical significance of this math exercise? Say the distribution is of the failure time of light bulbs. You get the population distribution of number vs failure time. Next, take a group of 25 light bulbs and ask what is the average failure time for this group. What does this mean physically? The horizontal axis is the average failure time per light bulb in a group of 25 whereas the axis of the population distribution is the failure time per bulb. Not much physical significance to this information. The horizontal axes for the means is probability vs mean value (mean length of 100 cylinders). Without the labels the population and mean plots are confusing.

Example; Value Proposition C (Personal development): Writing

I submitted a manuscript paper and got the following reviewer comment:

“The authors consider a bipartite system consisting of a particle and a mirror, whose respective positions are measured with a time-delay. A joint probability density is calculated, which exhibits a superposition of the mirror state. The paper is somewhat lengthy, not without redundancy, rather economical in the use of commas and now and then, one is taken by surprise by the syntax.”

Note that the first sentence reviews what the manuscript is about (like sending me your section and title), the reviewer is acknowledging having read it and that the review has been sent to the correct author. What is most important on the reviewers mind? The writing and not the content!

Ask the students: How do you respond to such criticism? Do you see it as the reviewers problem not to focus on the science? Do you go online and troll the journal? Do you get over your disgust and fix the manuscript up? Do you realize that it is not the journal's job to help you fix up your manuscript. They need only accept or reject manuscripts they think are of value to their readership.

How you respond is an illustration of your character. The comments the TAs and I provide about your lab reports are intended to help you develop into a professional writer.

Example; Value Proposition C (Personal development): Creativity

What is art? I like the definition that art makes you think about the world in new ways. How does an artist know they have created a very special work of art? How do you know you’ve done a special job of conveying your data? When you do know it’s art.


Data visualization Part (a).

Go over the population pyramid example found here http://www.randalolson.com/2015/07/14/rethinking-the-population-pyramid/

Personal tools
Namespaces
Variants
Actions
Navigation
Toolbox