Summary+of+Big+Ideas

​ ​Here are the big ideas we are thinking about in class (the most recent posted on top). Announcement: Here is a website: http://www.usatoday.com/news/snapshot.htm that provides many graphs from USA Today newspaper. Click through and ask yourself questions similar to those from p 37 in the text

12-7-09 Monday in class we discussed in depth the program batter, and when we would use this program. The way to determine when to use this program, is by looking at the details given in the problem. When a problem states trial length you know batter is one of the programs can be used. An example problem would be: What is StudentA's probability of getting 75% or better on a a 20 question, true or false test? (conduct 100 Trials). We know here the length of one trial is one 16 question. Here we are not looking to get 6 of every action figure, and we are not looking for someone to take a seriesof tests until they all get the questions correct. These two scenarios would use the shooter or sixpens program. In class, we also went over a few problems on page 176, and found a program that would best fit the problem scenario. We not only found a program that fit the particular problem, but we also found alternative ways we could run the trials for a particular problem, such as using the rand int function on the home screen, or using probsims etc.

12-09-09 Today in class we wrapped up the last of what we needed to know before the final. We first went over and decided that through a quick poll that we were going to have a study review session on Sunday from 2-4 in the Bernhard Center. -After that Dr. B asked if we had anymore questions on pg. 176 which we had started to go over on Mon. There were are few questions that were brought up on this page. We went over problem 9 which was the Michigan duck hunters problem. In this problem we discussed that you would could use the randInt program feature on the calculator. The numbers that you would input would be randInt (1,10,10). The first 1 and 10 representing the ducks and the second 10 representing the 10 hunters shooting a particular duck. - The other problem that we went over on this page was 7. This problem was where Bob was fishing at two different lakes. We decided that you could use the randInt for this problem as well but that you could also use a modified BATTER program as well (very modified since the probabilities aren't the same, unlike prob #1 with the family of 4, where you could modify batter to determine the outcome of how many boys (or girls) you get in each family). The numbers that you would be randInt(1,10) #'s 1-7 would be catching the legal limit and 8-10 not getting legal limit. ( For Blue Lake fishing on Mon.) The other numbers would be randInt(1,10) #'s 1-6 would be catching the legal limit and 7-10 not getting the legal limit.(For Green Lake fishing on Tues.) However because they both use the same numbers to make it easier you could just use randInt(1,10,2). 1-10 representing the samethings as above but the 2 represents the Green and the Blue lake. This led us to the discussion of what programs could be used on what problems on pg 176. This is what we came up with....problem -Next, we went over the SHOOTER program on page 180. We discussed what each of the lines meant in this program. We discussed that N is how many trials you want. S represents the number of shots in this case S,3. R<# would represent the percent of how many shots are made so in this problem it would be R</= 6. We also talked about how a new number under the list category would not change in this problem until the "S" would have a minimum of three shots made. -After this we went over the probability tree diagram and area model for problem 4 on page 196. This was the marble problem. We talked about how in the area model the square represents 1 or 100% and how each space in between is what you want to count when drawing the line in your square. We showed how the tree diagram provides just the number (fraction) probability where the area model shows more of a visual representation of the probability. -Finally, Dr. B passed back all of our quizzes and test. We got to look at them and record what we got wrong or ask any questions we might have about them. She also showed us how to figure out our grade if we had any questions about that. That was all for today and remember that we have a final review study session this Sunday from 2-4p.m. on the main level of the Bernhard Center.
 * 1) 1-batter
 * 2) 2-batter
 * 3) 3-shooter
 * 4) 4-batter
 * 5) 5-batter
 * 6) 6-batter
 * 7) 7-batter (very modified)
 * 8) 8-batter(very modified).

12/2/09
 * Today in class, we got a lot accomplished! We handed in our Monte Carlo descriptions for the chocolate chip cookie problem. Then Dr. B randomly selected a few of our fellow classmates' papers to show on the overhead so we could discuss and analyze each others answers. I personally feel this was a good way to recognize all of the vocabulary we have been going over and so we could all recognize what we did correct or incorrect in our own explanations of the Monte Carlo process.
 * Then, we practiced writing the first step of the Monte Carlo procedure for the kisses problem and the birth month off of our PIQ:
 * In the kisses problem, the model matched each of the two but not equally likely, outcomes of tossing a kiss (landing on its bottom or on its side) with 3 integers; 1 representing landing on the bottom of the kiss (1/3 chance) and 2 and 3 representing landing on the side of t he kiss (2/3 chance).
 * In the birth month problem, the model matched each of the 12 equally-likely birthmonths, Jan-Dec, with one of the equally likely outcomes of 12 randomly generated numbers, 1-12, using randint on the calculator. In the birth month problem, A single trial consisted of rolling a 12 sided die 5 times generating 5 random numbers from 1-12, simulating picking 5 people and asking what month they were born . The success associated with the trial was having 2 or more of the same number in the set of 5, representing having 2 or more people with the same birth month in the group of 5 people . If there was no match of any numbers, the trial was considered a failure.
 * Remember, we discussed why we could NOT use rolling two dice to be a model for this problem. WHY NOT???
 * I personally feel that this helped a lot and I hope the rest of the class feels the same!
 * Don't forget to start working on your projects. They are due next week! Don't put it off! :)
 * AHE: p.176 #1-11; p.180 #12
 * Working ahead option: p.193 #1-8 (might be a good idea if you've got the time!) :)

11/30/09
 * Today in class we began by going over page 170 #5. We as a class discussed how to use randInt to generate random numbers to determine chip placements into the cookies. We then tied this problem to #4cii. and #4d. using the numbers that were generated from #5.
 * We then went over the program Sixpens that was assigned for homework (even though we have the program in our calculators already under the title "Six") that is on page 169. Dr. B then explained how to input the program into your calculator and what each command is telling the calculator to do.We used p.181 to take notes on what the commands mean.
 * AHE for Wednesday Dec. 2: Quiz Wednesday on experimental probability and measures of variability! . Be prepared to turn in your answers on a seperate piece of paper for page 174 and then we are to read p. 178 and do the exploration.

11/25/09
 * Today was a great success! Personally (and my groupmates agreed) I think that going over homework using QuickPoll was more efficient and we got through many more problems than we normally do. We sent in our answers to: pg. 153 #3 B and the extension right below it. We came to the same answers of 90% and 255 students, respectively. Next was pg. 154 #6 d: 30%. Pg. 154 #7a, c iv., d ii: Right hand/right eye, right hand/ left eye, left hand/right eye, and left hand/left eye; 33.93%, and 66%.Pg. 155 #8 b, iii: 40%.
 * Some of the actual big ideas we summarized that the denominator is determined by the total number of trials. Also, there are two kinds of probability and they are theoretical (thinking about the problem, but not actually doing anything) and experimental (doing the problem trials, etc. and then determining probablity). There are two important characteristics for probability: each value should be a non-negative number between 0 and 1 inclusive; the sum of the values should equal 1. (pg. 158).
 * We got three new programs on our calculators and we played with one titled "six" which was like rolling a die on the calculator. We also played with ProbSim Application as well.
 * If you missed class today, then you missed out on a good session! But see Dr.B or your groupmates with questions or with homework problems because we got a lot done.

11/16/09
 * Today we started class by going over #3 on page 133. We made sure that all 3 data sets were entered into our calculators and then compared them in box plots. Data Set A had whiskers and boxes (if you had folded it at the median, it would have completely matched up); Data Set B was just a median and whiskers because the median, LQ and UQ were all equal (4) with a min and a max; Data Set C was simply boxes split by the median because the min and LQ were equal, and the max and UQ were also equal. We then discussed how to match the given Standard Deviations to the data sets - S1 was found to be B because of the low variability in the data set; S2 was C because of the large variability in the data set; and S3 was found to be A because of the steady variability in the data set.
 * We then moved on (for just a little bit) to Task 4 on page 138. We went over how to find the five critical values (min, max, median, UQ, and LQ) without calculation or a data set - this problem is set up in table form using frequency of scores. We determined that the min=65; max=95; LQ=72.5; median=85; and UQ=90. We also went over how to come up with this info using Davey's method. There were 41 values - median would fall at 21st position (85), with 20 values left on each side. We repeated this for the UQ and LQ. We will be going back to this on Wednesday.
 * Moving on to Probabilities, we discussed the "likelihood continuum" and visual ways to show this to students. Some suggested ways were: weather, pets/animals, and getting dressed for school (can be dependent on weather, too!). We then worked on #2 on page 141 as a class, to get an idea of how the continuum works with questions.
 * Took Quiz #3 on measures of center and box and whisker plots.
 * AHE for 11/18:
 * Complete peer evals on Survey Project and return on Wed.
 * Read p. 142
 * Complete #1-4 on p. 142 and 143
 * Define "random" to yourself
 * read p. 144
 * any changes to your personal definition?
 * post your final definition on new wiki page "What does random mean?"

11/11/09
 * Today we started by reviewing the measures of center and box plots. We looked at problem 11 b which had 3 values of 12 14 and 15 given and 3 values to be determined. We needed to determine these three values so that the median and mean were 19 with a mode value greater than 15. We discussed about looking at the median first or the mean first and most of us thought it was best to start with the median. With knowing the median has to equal 19 and having 6 values we determined the median would be between the 3rd and 4th value. The 3rd value is 15 which is a distance of 4 away from the median which means the 4th value needs to be a distance of 4 away in the opposite direction. Because 15 is -4 away from 19 adding 4 to 19 gave us the 4th value of 23. From there we worked on figure out the other two values looking at the mean. One way of doing this is to take the mean of 19 and multiply it by the number of values in the set which is 6. This came out to be 114 and then we subtracted the values we knew (12,14,15,23) and had 50 left. With two values left to determine we divded the 50 by 2 making them 25. With the 3 values being 23 25 and 25 gave us the median 19, mean 19, and a mode of 25 which is greater than 15. Another way to find these values with the mean we discussed was finding the sum of the distances below the mean. 15 is -4 away, 14 is -5 away and 12 is -7 away making the total ditance below - 16. We know the 1st value above the mean is 23 which is 4 away so the sum of the distance of the two remaining values had to add up to 12 to make the total 16. Keeping in mind we needed a mode greater than 15 we determined the two values could be 23 and 27 because 23 is a distance of 4 from the mean and 27 is a distance of 8. The three values were 23 23 and 27 making the total distance above 19 equal to the total distance below 19. The mode in this case was 23 which fit a mode value greater than 15.
 * We discussed problem 1 on page 121. With the box plot we were able to give the percentages of presidents older than 78 when they died and percent of presidents older than 67 when they died. We found these by looking at the upper quartile and the meadian. 78 is the upper quartile and with the data spread being pretty evenly distributed we concluded that it would be 25% presidents died when they were older than 78. 67 was the median meaning half of the data is below and half above so we concluded that the percent of presidents that died when they were older than 67 to be 50%.
 * We discussed problem 7 on page 126 and Dr. B took class poles on matching the displays to the data sets. When matching the data sets we looked at the distribution, the measures of center, the measures of dispersion, and the outliers to determine which displays were of the same data sets.
 * We also talked about quartiles and the interquartile range is the difference between the upper and lower quartile.
 * We ended class with a short video about probability
 * Quiz on Monday over measures of center and box plots.
 * AHE: page 132 - page 134

11/9/09 > Complete p. 132-134 #2-8
 * We started today out by turning in our survey projects.
 * Dr. B asked us to take a quick poll regarding some of the mid-term reflections she had returned back to her. The first poll asked if we strongly disagreed, somewhat disagreed, was neutral, somewhat agreed or strongly agreed with the statement, "homework is pointless because it's not collected and graded" Most of the class disagreed saying that even though it isn't collected, it gives us practice for tests, the midterm and final. The next poll was, "there's too much time spent on homework discussion". Over half of the poll participants disagreed, but some students did still agree with that statement.
 * Next we went over a few homework problems from last week and started with p. 101 #4b. We talked about deciding what type of graph was appropraite for that problem, and we discussed that it was important to look at what type of variable was being displayed. Dr. B said that when dealing with statistics that it isn't always black and white, we can run into gray areas sometimes like we did today when discussing the graph. We came up with a few different answers for B, such as saying there were 30 students who received $4 or more and only 29 students who received less than $4 for allowance.
 * We then moved onto p. 107 when the little boy was talking to this mother about finding the middle number. He eventually came up with an equation to find the mean like this: 1---12 + 1 =13 /2 = 6.5 To find the mean of a set of numbers, you would take the number of values in the data set, in this case 12 and add one to it. After that you would divide by 2 and that gives you the (position of the) median. this is just an easier way than counting off each number from one side until you reach the middle value.
 * The next homework problem was p.103 questions c and d. We talked about how box-and-whisker plots are built upon the median, without the median it would be impossible to find the other 4 values. We also talked about **range** and how it is one way to measure variability and it's not a measure of center. The range is the spread of the data, to find it you take the maximum value and subtract the minimum value from it. While working on this problem we discussed whether it was important to count from the bottom of a column of data or if you could start at the top. We decided that it was important to remain consistent while counting so children wouldn't get confused, but counting from a bottom of a column is better because it is set in numerical order. While each column itself is the same number, it's better just to start at the bottom rather than the top.
 * On p. 128 there was a data set we used to start talking about deviations. Deviations are the differences from a certain value, and today we talked about deviations from the mean. In data set B we were asked how far is the minimum, lower quartile, median, upper quartile and maximum was from the mean. When we found the distance from the mean it was about 13.27, so from the mean which was 72, most of the data set lies from 59 (13 away from 72) and 85 (13 away from 72). Because some of these values would have been negative, these values are just absolute values so there are no negative numbers invovled. To make sure that there are no negatives, after finding the deviations, you must sqaure them. The table on p. 130 helps explain this better. After finding the mean of the squared deviations, you can find the standard deviations by finding the square root of this number. You can also find these values from your calculator, the directions for that are on p. 132.
 * AHE: Vote for George (p.99) and support your reasoning supporting or disagreeing with George's reasoning.

We started off the class with taking a quick poll to see what homework problem we wanted to do first. The class decided on p.108 number 7. Since the problem had to do with mean, we did an activty on our calculars to show that your mean is going to increase by any number (q) if it that same number is distributed to everyone. (every data value) The same is true if you are subtracting a number from every data value. We also proved this works for multiplication, if you are just multiplying every data value by 2, you mean will also double. We then started to talk about p.99 and the concept of just moving all of your Xs to the mean on a dot plot, but we will discuss it on Monday. The next problem we discussed was p. 116 # 19. This was a stem an leaf plot that had years duringwich the 50 states were settled. We decided that the data was numerical, because you are measuring time. When you take two of the data values, the difference between them has meaning. If we are dealing with the parking lots, then the data is categorical because we assigned a number to them. Also, the order doesn't matter because itwas random. When trying to the find the median of the data, you take the number of states and divide by 2 which is 25 states. However, since 50 is an even number you will have 2 medians. You take the halfway mark, 25.5 states, and find the middle from that. It would be between 1733 and 33. In order to get the upper and lower quartiles, you take half of the median which was numerially 25. 25/2 = 12.5. In this problem the lower quartile is the top half of the stem and leaf because those are the lowest numbers. If you count back 12.5 from the median you get 1660 as the lower quartile. You do the same for the upper quartile and get 1809. The last problem we looked at was a new concept, p 119. We used what we just learned about median, upper quartile, and lower quartiles to construct a box and whisker plot. You first find the medians of the two lists and they are both 73. Since there are 6 scores on each side of the median, you don't need to count the median. That way, you can easily find the upper and lower quartiles. When you make the box and whiker plot, the median is placed first. Then, the quartiles are placed on th number line. These three points then make a box. The "whiskers" part are the min and max of the data sets. We found that although the medians were the same, list B had a wider range of scores than list A. The AHE is activily read p. 117, do exploration # 1, p.121 # 1-8, and the handout on mean and median.
 * 11/04/09**

11/02/09 We looked at the average and all of its different meanings. We determined that "average" means the typical or representative value of a data set. We then examined what "mean" means. We came up with a form ula : the sum of x divided by n = the mean of the data set for all numerical data sets. We came up with and looked at the conceptual ideas of mean. The three ideas we came up with were Sharing fairly (a.k.a. Splitting up evenly), Redistributing and the Balance point. We took these theories to look at pg. 97 exploration 2.
 * We had two groups make a dot plot for the information on pg. 103. Then as a class we looked at the  displays made and discussed the difference between the two GRAPHS. We found the difference between the mean and median of the two data sets and what that meant.
 * Anyone want to write "what that meant"??? The median is the middle value of the data set. To find the median, you arrange all of the data in order first. Then you start at both ends and count in towards the center of the data until you reach the middle value. When you have an even number of data elements, you take the two middle values and find their mean. When the data is more evenly spread out, the mean and the median are similar. When the the data is unevenly distributed, or you have one or more points that sit far away from the rest of the data, the mean is sensitive to these extreme values and can significantly differ from the median.
 * We used the fulcrum balances to play with the meaning of mean and median. HOW DOES THE IDEA OF BALANCE CONNECT WITH THE MEDIAN??? SORRY COULDN'T CHANGE COLOR HERE. I don't think the idea of balance points connects with the median.  We received several different problems to experiment with on the scales. These problems asked us to place one weight on the scale to balance the two sides. SO HOW DID WE DETERMINE WHEN A SET OF DATA WAS BALANCED??? THAT MIGHT BE HELPFUL TO KNOW. We determined that the sum of the distances of the weights from the balance point on one side of the scale must be equal to the sum of the distances of the weights from the balance point on the other side of the scale.
 * Then we discussed mode which is the most often to occur in a data set.
 * All of these are considered to be a measures of center.
 *  AHE: pg 102. Actively read through explorations, pg 106 2-14,19 and do evaluations if you have not already

WE'RE MISSING 10/21 AND 10/26. IF YOU HAVEN'T POSTED BIG IDEAS, WHY NOT TAKE ONE OF THESE DATES AND FILL US IN?? 10/19/09 =10/12/09=
 * Today we spent a lot of time looking at p. 62f. In this question we had to look at the double ( should be back-to-back ) stem and leaf plot and compare it to the histogram on the same page. The differences between the two numerical representations is that the histogram is looking at the overall grouping of the groups because there is no exact measurements for each bar, they could range in size from 37.5-44.9, you don't know where any of the measurements actually fall in that span. Wait, we do have "exact measurements" for the interval length; we just don't know the specific measures that fall in that interval. You do say that later; I just want to make sure we all understand which "measurements" we don't have. Do you or can someone help me to know what are the lenght-interval for each value of the stem for the stem and leaf plot on p. 62? You need to read the key to determine what each stem represents. I see the "4" represents 40 by reading the key. With the point between the values on the stem, that splits each group of 10 in half so on the first line, the data goes from 40-44.4 and the next line goes from 45-49.4. In the stem-and-leaf plot they are grouped into intervals but they are easier to see where the range is. Like you know that 4/1=40.5-41.4 and there is one of those measurements, you know that there is one measurements in that range. It is a much smaller range and there isn't as much guessing of what the range is.
 * We looked at the graphs on page 68 as well today. In order to find out how many left eyed right thumbed people there are out of that sample size you must have the data, fractions, in order to show the percentages. Without having the fractions/measurements than you wont be able to properly show the relationship. With these graphs and data we can only tell what it tends to be, we can't give a definite because there are others that are different and the opposite from the normal, to be exact all the information would have to be the same.
 * Next we looked at p. 71 #4 and looked at making the contingency tables for the information provided. If you know the total and one other number out of the table than you would be able to figure out the rest of the information. You have to make sure make sure that all the information adds up at the end so that way you know that your information is correct. Having this information will help you construct contingency tables.
 * Finally, we looked at p. 75a and the graph that we constructed out of our height and arm span information. We noticed that our data is clustered around an imaginary line and has a moderately strong positive slope. We know that it is a positive slop because it trends upward on the graph and it is clustered all around that imaginary line. If we had a lot of different points that were way off the norm than it wouldn't tend to be a positive slope. Having those close together than that means they are tending toward each other.
 * AHE : p. 84 10-11, p 87-94 tasks 1-9 and read 94-95
 * ===== Remember Midterm October 28th! =====
 * We sent our height, armspan, and navel height data through Navigator. We renamed the lists the data were sent in so that we could continue to use L1, L2, and L3. We were reminded NOT to use the text editor to create the lists with numerical subscripts as those are different lists than the default lists stored in the calculator of L1-L6, even though it is very hard to see that in the list editor. Dr. B thought that took too long so she needs to work on how to help us send data more efficiently. Probably give better directions next time.
 * Some of us had to link our data as some glitches occurred so we were shown how to use the Link Apps on our calculator. There are just so many cool features of our calculators that we can use as learning tools when we teach young children!
 * We had a few AHE questions to discuss but Dr. B made us go back to page 48 & 49 to talk about line plots and stem and leaf plots. We described how the birth month data was distributed using key features we discussed last week: clumps, bumps, holes, mins, maxes, range, and overall shape.
 * We eventually got to histograms and spent some time on how to create a tabular frequency distribution from a histogram. We spent a lot of time focusing on what accuracy the right hand end-point could be when the data was rounded, but in the end, since the left-hand endpoint was not presented with the same accuracy, decided to keep the left- and right-hand endpoints at the same level of accuracy. So, for #2 on p 61, the tabular intervals would look like: 1.0-1.1; 1.2-1.3; 1.4-1.5 and so on. The frequencies for these intervals are 4, 10, 25 respectively.
 * For Wed, we need to have the back-to-back stem and leaf plot completed making sure we use 2 lines per stem. We will still use the data on p 31 for this plot vs our own class data. Also, we need to have 1g completed on p 59. Not enough had it finished today to ensure a good enough discussion.
 * We finished the table on p 67 and that was it. No new material was presented; such a bummer. So we'd better watch out on Wed! She'll probably start out on new material on Wed and hit the old AHE problems before the quiz.
 * AHE : Enter the data on p 81 #5 into 3 lists, male, fem and TV. Identify which pairs of questions would make sense when looking for cat/cat, cat/num, and num/num associations from our survey projects. Dr. B added later in an email to "try part c on p 67. Just make a sketch. In the first part of c you are comparing the percent of right-eyed people in the class to left-eyed people. Then you do the same for thumbedness. Also, if you could try #3 on p78, just walk through the manual-fit process, that would help in class by you raising specific trouble-spots. Realize that since you will use the data we entered today in class, your data will not look exactly like the screens on p 78-79. Read through the instructions carefully; you'll do fine."
 * Midterm Oct 28th


 * ==10/7/09==
 * We spent the first hour of class editing the pilot survey questions. We ended up deleting 2 of the questions and rewording some of the remaining questions. Dr. B will e-mail everyone a final draft of the project survey later today.
 * We did come to a realization: our survey questions all seem to focus on the single parking problem of not being able to find a parking spot. We aren't really looking at a variety of parking issues, which is what we set out to do in our original investigation question. We were sent home to ponder this over the weekend.
 * Dr. B reminded us to think about who we want to work with for this project. Ideally, we would work in pairs, but there could end up being groups of 3 due to the fact that some people may need to work alone. Dr. B encouraged us to begin working on the project by summarizing what we have done so far (i.e. how we chose our problem to investigate, the question we posed, how we chose and edited our survey question, and how we decided on our sample population). We were also reminded not to use convenience sampling when conducting our surveys.
 * Next, we reviewed what we discussed on Monday (10/5). First, we discussed organizing and displaying numerical data (histograms are more appropriate for displaying large sets of data, dot plots are more appropriate for displaying smaller sets of data, stem-and-leaf plots are more of an organizing tool rather than a display). Then we discussed describing data (the variability of the data and the shape of the data - symmetric, not symmetric, flat, skewed). Finally, we discussed reading the data: when using a histogram to display count data, you can identify a min. and max. value **only** if the length of the intervals is 1; if the interval lengths are greater than 1, you have multiple values represented by each bar.
 * We talked about the Mystery Balancers worksheet. As far as making an argument for our choices, what factors did we look at? age, the hobby of the population surveyed, the variability of the data. We discussed how we went beyond the data to **interpret** the results when making our choices about which population fit each set of data.
 * We began a discussion on how 1 variable affects another.
 * AHE: pg. 66-68 Exploration #1 using the data Dr. B gave us in class; everyone is to have 5 completed surveys by next Wed. (10/14) Dr. B has sent everyone a link to the spreadsheet on Google Docs, so make sure you input all of your data there. You can email Dr. B if you have any problems accessing the spreadsheet or entering your data.; our next quiz is Wed. (10/14).

> 10.3(desired production) – 4.2(current production) = 6.1(represents the whole) > 5.9(actual production) – 4.2(current production) = 1.7(represents part of the whole) > 1.7(Numerator)/6.1(Denominator) = 27.9 %. > A.H.E: Go to wikispaces.com and choose your top 10 survey questions, select five numerical and five categorical questions. Please list your questions from most interest to least interest and e-mail them to Dr. Brown. Reflective writing # 1 is due on Wednesday.
 * =**10/5/09**=
 * =====Today in class we asked the question "How can we organize numerical data?" We defined the two types of numerical data to refresh our memories. The first type is Count, which deals with whole numbers. An example of this is asking "how many classes do you have total?" or "On average, how many times do you park on campus in a single day?" The second type of numerical data is measurement, which deals with exact numbers, not always whole. An example question would be "What is your exact height in centimeters?"=====
 * =====We can organize these types of data in 3 different ways: Stem and Leaf Plot, Dot Plot, and Histogram=====
 * =====We took our data from our pulse rates and showed them using a dot plot. We then asked the question: What can we determine from this data?=====
 * 1) How many people were surveyed
 * 2) What are the "outliers?" (a data point(s) that sits farther away from most of the data or the clump)
 * 3) clump/hole/bump
 * 4) minimum, maximum, range (difference)
 * 5) shapes (symmetric design, bell curve, etc.)
 * We realized that the shapes could also be skewed. Depending on which side the tail is on, the skew will be different. For example, when looking at a bell curve design, if the tail (longer end) extends on the right side, it is skewed to the right.
 * Stem and Leaf plots force us to see the clumps differently, and the gaps are also not present. Therefore, this type of plot doesn't always work for/with the data provided. We came up with the following response to the question of why we didn't chose a bar graph as well: because the the bar graph represents categorical data and we have numerical data. Using that display, it looks like there are gaps in the data where there aren't. It groups the numerical data into categories so it doesn't show the exact shape of the data.
 * **AHE:** comeplete Mystery Balancers Worksheet, read pgs. 55-56 actively, complete pg. 56-57, 58-65 1-4. Also, complete the emailed survey by 10 pm Tuesday night and email the responses to the professor. (only survey 1 person regarding the parking problems) The map that is to be attached is posted outside of her door in Everett.
 * ==**9/30/09**==
 * **Today we started with homework and had some good class discussion over the problems. We looked further into reading tables and graphs and what we should be looking at to pull information from. ( key words, labeling, scale) We also talked about reading and interpreting the questions. How we can not assume information that is not stated in the problem and making sure we know/understand what the question is really asking. We went over how a problem may have multiple pieces of information given, and they might be talking about the same topic, but they may not be out of the same whole. (We went back to pg. 35, #2, and talked about how the % of contributions over the years is not out of the same whole total.)**
 * **We looked over our Class Pulse graphs and had two new ones introduced, Leaf and Stem, and Dot plot. They are both a way to visually organize your data.**
 * **We went over and edited survey questions in our groups.**
 * **AHE: Read pg. 41-45;****complete questions on pg. 48 1-6,8,9**
 * **9/28/09**
 * What were main ideas from the AHE? One of the ideas was to be able to determine which types of graphs are appropriate for displaying different types of data.
 * Today in class we started out by remembering what the 5 categorical displays are from least difficult to most difficult: Real graph,Picture Graph, Table, Stacked Bar Graph, Circle graph. We also discussed that we know of 3 different bar graphs: Standard bar graph, Multiple bar graph, and Back to Back bar graph. We emphasized on the part to whole concept when using percentages you cannot compare percents of different wholes. We all entered our pulse rate into our calculators from the PIQ and we then were given everyone elses pulse rate on our own calculators.
 * A.H.E: You need to create a graph that either 1-3rd grades or 4th-6th graders would create by using the information from the list on your calculator of the classes pulse rates.
 * We also counted off in class and what number you said meant that was the number on our survey questions that you need to edit and put up on the edited survey questions page.
 * **9/23/09**
 * Today in class we started off discussing in groups our homework. Then as a class we discussed our survey project. The questions that we all picked where put together for a pilot survey draft. As a class we looked over the questions and got rid of ones that were repeated or very similar and then added to a few of the questions to make them more understandable. We also talked about the bar graphs that we made for the m&ms. We cut out the bar graphs and made stacked bar graphs out of them. We then discussed as a class how the m&m data compared to others in the class an we found that even though the colors varied we all still had about the same about of m&ms in our bag. We talked about our homework issues. The final thing of the day was our first quiz.
 * what ideas came from the AHE? Any?
 * <span style="font-family: 'Times New Roman',Times,serif; font-size: 14px; line-height: 27px;">A.H.E: Complete problems 5-8 on pages 37-40. Plot survey: we need to take the survey, edit the questions and remove any questions that are not good enough. Also do the percent worksheet handed out in class.
 * ** 9/21/09 **
 * <span style="color: #000000; font-family: 'Times New Roman',Times,serif;">We were asked to name the type of display that children would like to create first to display data. As a class, we agreed that children would want to do real graphs to organize their data since real graphs use physical objects. We talked about our survey questions and were advised to avoid embedded questions or those that just keep going on and on. <span style="color: #ff00ff; font-family: 'Times New Roman',Times,serif;">Also, avoid leading questions. <span style="color: #000000; font-family: 'Times New Roman',Times,serif;">To avoid these types of questions, we should try to put our thoughts together and formulate one good question. We were also asked to think of what initially starts the process of statistical investigation, we concluded that it begins with a **//problem//** that we would investigate by formulating **//research//** **//questions,//** which would help us survey the **//population//** (a representative sample of it). We discussed problem 2, on pg # 10 and it was decided that (a) is the most appropriate plan for Ms. Lo’s students to select a sample of students to survey. Selection (a) represents **//systematic sampling//**: this method assure us what will happen. In this case, one student out of a group of four students will certainly be surveyed. There is no guesswork involved in this method. Selection (b) represents a **//rambling sampling//**: this method involves no selection, but rambling. <span style="color: #ff00ff; font-family: 'Times New Roman',Times,serif;">I think you mean __random__ sampling. <span style="color: #000000; font-family: 'Times New Roman',Times,serif;"> Selection (c) represents **//convenience sampling//**: this is a not good representative sample of the population, so it would be bias. In this case, if the students conduct the survey in their history class, then the sample would be only from history class. Not a good representative sample of the population. Section (c) represents a **//voluntary response//**. This method distributes surveys easily, but these may not all be returned. Also, we solved problem 4, on pg # 11 and decided that the answer for (a) was 28%. <span style="color: #ff00ff; font-family: 'Times New Roman',Times,serif;">Agreed to state answers to the tenths' place, so answer was 27.9% <span style="color: #000000; font-family: 'Times New Roman',Times,serif;">. Stalin wanted to increase production steel output from 4.2 million tons in 1928 to 10.3 million tons in 1933, but their actual production in 1933 was 5.9 million tons. This was solved in the following manner:
 * ** 9/16/09 **
 * We started off class by discussing within our groups any homework problems or concerns that we had. We also looked at our class question for our problem. We discussed the wording and who we wanted to include in our population. We made a final question and changed it on wiki. Our question is: What parking problems are students who have W parking permits, who have to park between 8am and 6pm on main campus experiencing most often. All students need to go to the Survey questions and add either a numerical or categorical question under our class question. These are to be questions that will be asked on the survey that will provide us with data to help answer our question. We discussed that questions cannot be biased. Some things to avoid when writing questions (to make sure they are not biased) are to make sure the question is not leading and to not use strong emotional words.
 * In addition to working on our class question and problem we discussed different ways of organizing data. We looked at the different graphs or charts that were made from the m&m investigation and their progression. Positives and negatives were discussed for the different types. So far this is the order (from simple to complex): sort by a variable (first with actual object, then with pictures), count how many for each category (the frequency), real graph, picture graph, bar graph, table and circle graph.
 * AHE: Read and Complete pg 32-24, Complete pg 35-40 #1-4, Writting assignment is due Wednesday the 23rd
 * Reminder: Monday we will have a short quiz over everything that was covered through class on the 16th. All homework problems are fair game!


 * =9/14/09:=
 * We first started off by voting on a problem (posted on the problem ideas) that we would be researching. The problem idea that was chosen was "Parking on Campus". We then talked about once we have a problem what will be our question that will be researched . We concluded that our Question would need to be broad enough to be able to come up with more questions in order to collect data to answer our problem. An example of a problem that we discussed was Achievement Levels in Math 2650. And some questions that were shown were How do the hours of studying correlate with the achievement levels? and What facors contribute to achievement levels in Math 2650? Some further questions that could be used to collect data would be "do the hours of sleep/day effect with the achievement levels" or "What is the interest levels in math of the students and their final grade". We also talked about what kind of population would be researched: specific (math 2650 wmu students either 1 year past or 2 years), not whole population would need to be researched (also called taking a sample). We also discussed when reviewing data, the frequency of something is not the data and variable and question can be used to have the same meaning.At the end of class we were given M&M's and were to think of Questions that relate to a specific grade level(s) that could be used to find out more information about the bag. At the end of the day we were to figure out "What is the relative amount to the whole of each color in each bag?" and to display the data graphically according to our grade levels given.
 * AHE: Read pp 13-20 actively. Include marginal thoughts. Complete Exploration p. 21 using OUR eye color data (not from p 31), and applications pp 22-29, #1-4. Use the data on p 30 when needed. Yes use the data on p 30 here since we have not collected the whole class M&M data yet.on page 28 I noted there were errors but didn't tell you what they were! The percents for the M&M data provided by M&M Mars company are in the wrong order for the colors as listed! So don't just copy those percents from the example on p 28; refer back to the percents on 19 to get them in the right order. Sorry about that. Eight people are providing the research questions by tonight, oh say by 10 pm. Everybody else gets to vote anytime on Tuesday using the number 1 as the symbol to cast your vote. (copied right from the e-mail she sent us)


 * =9/9/09:=
 * Today in class we discussed the question "What is Statistics?" We came up with a list of things that describe Statistics; such as gathering, organizing, analyzing and interpreting data. We also decided that there are sub categories to this big idea. "Charts and graphs" was subcategorized into Organizing. "Data" as in numerical and categorical data was subcategorized into gathering and "finding a pattern" was subcategorized into analyzing data. Then we as a class decide d that "telling a data story" deserved its own bullet as well as the "statistics nouns" like mean, median, mode, range and outlier. At the end of class we discussed how when we do a statistical investigation; the beginning is a problem that triggers us into the investigation. We as table groups came up with some possible problems to investigate. 2 table groups will be posting possible problems and the class will be voting for the problem that sparks interest to them.
 * AHE (vs big ideas) Probably not a bad idea to include this so everyone can stay on top of their work. Dr. B handed out sheets on the Survey Project that everyone must read over as well as reading over the syllabi for next class. Dr. B also handed out the Personal Information Questionnaire (PIQ) that everyone must complete by next meeting. For or A.H.E (homework) we are to read pages 1-4 in our book, and complete the applications on pages 10-12 #1(for PIQ only) and #s 2-5.