Showing posts with label RES600. Show all posts
Showing posts with label RES600. Show all posts
Tuesday, October 4, 2011
Sunday, September 25, 2011
RES600 complete! Awaiting final score.
My RES600 course is done. I'm just waiting for my final grade.
Here are my results for the rest of my course:
Module 4
Case - Grade A
Professor comments:
Overall you did a good job with this Alex, you put forth a good effort at trying to bring some order to this assignment and I appreciate your hard work with this.
Dr. C
SLP - Grade A
Professor comments:
Good work here as well. You seem to understand what hypotheses are all about and the basics of hypothesis testing and did a good job overall.
Dr. C
Discussion question:
Scatterplots provide graphical indication of relationships, whether they be linear, non-linear or nonexistent. Correlations are numerical summary measures that indicate the strength of relationships between pairs of variables. A correlation is very useful, but it has an important limitation. Do you know what this limitation is and why this limitation exist?
Guess what are the rho values (correlation coefficients) for the following plots? Possible values for these plots are 0, +/- 0.4, +/- 0.6, +/- 0.8, +/- 0.99.
Discussion answer (Grade A):
Do you know what this limitation is and why this limitation exist?The limitation of correlation is that it depends both of the variables to be random as well as observation independent. The variable will need a normal distribution in the test of the null hypothesis (H0). "Both correlation and regression assume that the relationship between the two variables is linear." (Bewick, et al, 2003)
Ref: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC374386/
Guess what are the rho values (correlation coefficients) for the following plots? Possible values for these plots are 0, +/- 0.4, +/- 0.6, +/- 0.8, +/- 0.99.
a. p=1
b. p=-1
c. p=.4
d. p=-.8
e. p=.8
f. p=.-8
g. p=.4
h. p=0 (Wikipedia, 2011)
Ref: http://en.wikipedia.org/wiki/File:Correlation_examples2.svg
Module 5
Case - Grade A-
Professor comments:
In this assignment you were asked to take a look at the ‘Howie’s bakery’ data and to explore descriptive statistics and draw some scatter plots. You were also asked to run a multiple regression and to consider the t-statistics, coefficients and r-square and to discuss whether the regression was successful. You were also asked comment on ways to improve the regression and to consider exploring time-series.
I think in this assignment there was hope you would perform a multiple regression analysis rather than just a simple regression but overall you seem to have a grasp on the fundamental concepts.
Dr. C
SLP - Grade A
Professor comments:
In this assignment you were asked to comment on several scenarios. One involved the lack of correlation between Abraham Lincoln’s educational background vs. typical backgrounds of past presidents. You were also asked to comment on the hypothesis “When political instability increases, the price of quality increases.” In the Toxic Shock Syndrome case you were asked to comment on causal implications. Finally, you were asked to comment on the ethics of running a bivariate regression between absenteeism and a series of Likert scale items, and you were asked to present the assumptions underlying regression.
In the case of Lincoln’s situation, it’s pretty obvious that he was a rather exceptional, self educated individual and thus, an outlier when compared to other presidents who typically have exceptional academic credentials. With regards to the ‘political instability’ hypothesis, there may be a correlation, but it seems to me there would be a number of intervening variables that would explain the relationship. As far as the TSS case, we’re looking at a pretty small sample here and there also may be a concern regarding the cause/effect relationship given that we are looking at cross sectional data. Finally, I don’t see an ethical problem playing with data post-hoc, and frequently bivariate data is used in regression even if it is not ‘normal’ per se. However, post-hoc findings do have to be reported as such.
You made some good observations in your discussion Alex!
Dr. C
Discussion question:
Three prisoners, A, B, and C, have applied for parole. The parole board has decided to release two of the three, and the prisoners know this but not which two. Prisoner A realizes that it would be unethical to ask the warden if he, A, is to be released, but thinks of asking for the name of one prisoner other than himself who is to be released. He thinks that if the warden says “B will be released,” his own chances have now gone down from 2/3 to 1/2, because either A and B or B and C are to be released. And so, A decides not to reduce his chances by asking. Explain why A is mistaken in his calculations.
Discussion answer (Grade A):
This is almost the same type of question as the "what's behind door number ..." in module 2 with the exception that the prisoner may be too scared to find out the answer as to ruin their chances of being released. The reasoning is that if they ask, the warden may consider this an act of misconduct versus if they stay silent, they may get released. There is also a chance that the reverse may occur if they ask and the prisoner will get the answer they are looking for. So there are morality issues that come to play as well.
The reason that the prisoner is wrong is because of the following:
"The incorrect solution, and the source of the prisoner’s “paradox”: Three possible pairs of prisoners may be released, with each of the three pairs equally likely: (A & B), (A & C), (B & C). Knowledge of B’s release eliminates the option (A & C), and the conditional probability that A will be paroled becomes P(A paroled|B paroled) = 1/3 / 1/3+1/3 = 1/2"
The correct answer comes from 4 possible solutions:
"(B&C, B) 1/6
(B&C, C) 1/6
(A&B, B) 1/3
(A&C, C) 1/3"
Overall, the door question and the prisoner question both have the same probability initially, however, the prisoner has not considered the warden's motives or choice in the decision.
Source: http://www.amstat.org/publications/jse/v13n2/carlton.html
Professor comments:
You made some very well thought out contributions to the thread this session Alex!! Best of luck in your future endeavors!!!
And that ends RES600.
I am transferring out of Trident University (TUIU) to go to University of Phoenix now because I do not feel that TUIU is for me. The school was good for my masters but for my phd, I feel that I need a more thorough understanding of what I am learning. At the moment, I feel that I am moreso learning a crash course in statistics. It's a pain so hopefully UoP will be more thorough so that I can get an actual understanding of what I am learning in school.
Here are my results for the rest of my course:
Module 4
Case - Grade A
Professor comments:
Overall you did a good job with this Alex, you put forth a good effort at trying to bring some order to this assignment and I appreciate your hard work with this.
Dr. C
SLP - Grade A
Professor comments:
Good work here as well. You seem to understand what hypotheses are all about and the basics of hypothesis testing and did a good job overall.
Dr. C
Discussion question:
Scatterplots provide graphical indication of relationships, whether they be linear, non-linear or nonexistent. Correlations are numerical summary measures that indicate the strength of relationships between pairs of variables. A correlation is very useful, but it has an important limitation. Do you know what this limitation is and why this limitation exist?
Guess what are the rho values (correlation coefficients) for the following plots? Possible values for these plots are 0, +/- 0.4, +/- 0.6, +/- 0.8, +/- 0.99.
Discussion answer (Grade A):
Do you know what this limitation is and why this limitation exist?The limitation of correlation is that it depends both of the variables to be random as well as observation independent. The variable will need a normal distribution in the test of the null hypothesis (H0). "Both correlation and regression assume that the relationship between the two variables is linear." (Bewick, et al, 2003)
Ref: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC374386/
Guess what are the rho values (correlation coefficients) for the following plots? Possible values for these plots are 0, +/- 0.4, +/- 0.6, +/- 0.8, +/- 0.99.
a. p=1
b. p=-1
c. p=.4
d. p=-.8
e. p=.8
f. p=.-8
g. p=.4
h. p=0 (Wikipedia, 2011)
Ref: http://en.wikipedia.org/wiki/File:Correlation_examples2.svg
Module 5
Case - Grade A-
Professor comments:
In this assignment you were asked to take a look at the ‘Howie’s bakery’ data and to explore descriptive statistics and draw some scatter plots. You were also asked to run a multiple regression and to consider the t-statistics, coefficients and r-square and to discuss whether the regression was successful. You were also asked comment on ways to improve the regression and to consider exploring time-series.
I think in this assignment there was hope you would perform a multiple regression analysis rather than just a simple regression but overall you seem to have a grasp on the fundamental concepts.
Dr. C
SLP - Grade A
Professor comments:
In this assignment you were asked to comment on several scenarios. One involved the lack of correlation between Abraham Lincoln’s educational background vs. typical backgrounds of past presidents. You were also asked to comment on the hypothesis “When political instability increases, the price of quality increases.” In the Toxic Shock Syndrome case you were asked to comment on causal implications. Finally, you were asked to comment on the ethics of running a bivariate regression between absenteeism and a series of Likert scale items, and you were asked to present the assumptions underlying regression.
In the case of Lincoln’s situation, it’s pretty obvious that he was a rather exceptional, self educated individual and thus, an outlier when compared to other presidents who typically have exceptional academic credentials. With regards to the ‘political instability’ hypothesis, there may be a correlation, but it seems to me there would be a number of intervening variables that would explain the relationship. As far as the TSS case, we’re looking at a pretty small sample here and there also may be a concern regarding the cause/effect relationship given that we are looking at cross sectional data. Finally, I don’t see an ethical problem playing with data post-hoc, and frequently bivariate data is used in regression even if it is not ‘normal’ per se. However, post-hoc findings do have to be reported as such.
You made some good observations in your discussion Alex!
Dr. C
Discussion question:
Three prisoners, A, B, and C, have applied for parole. The parole board has decided to release two of the three, and the prisoners know this but not which two. Prisoner A realizes that it would be unethical to ask the warden if he, A, is to be released, but thinks of asking for the name of one prisoner other than himself who is to be released. He thinks that if the warden says “B will be released,” his own chances have now gone down from 2/3 to 1/2, because either A and B or B and C are to be released. And so, A decides not to reduce his chances by asking. Explain why A is mistaken in his calculations.
Discussion answer (Grade A):
This is almost the same type of question as the "what's behind door number ..." in module 2 with the exception that the prisoner may be too scared to find out the answer as to ruin their chances of being released. The reasoning is that if they ask, the warden may consider this an act of misconduct versus if they stay silent, they may get released. There is also a chance that the reverse may occur if they ask and the prisoner will get the answer they are looking for. So there are morality issues that come to play as well.
The reason that the prisoner is wrong is because of the following:
"The incorrect solution, and the source of the prisoner’s “paradox”: Three possible pairs of prisoners may be released, with each of the three pairs equally likely: (A & B), (A & C), (B & C). Knowledge of B’s release eliminates the option (A & C), and the conditional probability that A will be paroled becomes P(A paroled|B paroled) = 1/3 / 1/3+1/3 = 1/2"
The correct answer comes from 4 possible solutions:
"(B&C, B) 1/6
(B&C, C) 1/6
(A&B, B) 1/3
(A&C, C) 1/3"
Overall, the door question and the prisoner question both have the same probability initially, however, the prisoner has not considered the warden's motives or choice in the decision.
Source: http://www.amstat.org/publications/jse/v13n2/carlton.html
Professor comments:
You made some very well thought out contributions to the thread this session Alex!! Best of luck in your future endeavors!!!
And that ends RES600.
I am transferring out of Trident University (TUIU) to go to University of Phoenix now because I do not feel that TUIU is for me. The school was good for my masters but for my phd, I feel that I need a more thorough understanding of what I am learning. At the moment, I feel that I am moreso learning a crash course in statistics. It's a pain so hopefully UoP will be more thorough so that I can get an actual understanding of what I am learning in school.
Saturday, September 3, 2011
BUS504: Modules 1-5; RES600: Modules 1-3
I am actually surprised that people have been reading my blog... I have not updated it in a while but I will do my best to allow others to see what I have written so far.
For my BUS504 course, here are my essays:
Module 1:
Case
SLP
Module 2:
Case
SLP
Module 3:
Case
SLP
Module 4:
Case
SLP
Module 5:
Case
SLP
Unfortunately I do not recall what grade I received for each assignment, however, the overall grade for the BUS504 course was a B+.
I am currently taking RES600 - Introductory Data Analysis. This will be my last course at TUIU as I am transferring back over to University of Phoenix.
Module 1:
Grade A: Case
Professor comments:
Alexandria,
In this assignment you were asked to identify the key research question in the study presented, distinguish between types of variables, and provide relevant descriptive statistics to include frequency tables, box plots and other relevant statistics. You were also directed to give a go at using the cross tabs function. You were also asked to comment on these various findings in relation to the variables considered most and least important to kids in relation to defining popularity …and you were asked to provide some other observations.
Overall I like what you did. I did not see where you clearly and specifically pointed out the key research question, though you did allude to it. Also, you might want to spend some time pondering if Grade might be better construed as Interval data. From the start of one grade to the start of another is one year. Thus, there is a constant distinction or interval between grades. At the same time, there is no zero value in K-12.
Still, you seem to understand the fundamental concepts presented in the assignment and I appreciate your hard work.
Dr. C
Grade B+: SLP
Professor comments:
In this assignment you were asked to identify the data type for a series of variables. You were then presented with a coding scheme for categorizing income data and asked to comment on it. Finally, you were asked to provide a frequency table and calculate the mean, median and mode for speed limits in various countries.
Overall you did a good job with this assignment. I think, however, that for the nominal data categories such as marital status and whether a person has been unemployed, the mean has very little meaning. Here it seems that frequencies, proportions and the mode would be the appropriate descriptive statistic. Also, I was hoping for a bit more comment on question 2. At the doctoral level your response to any given question should be quite in-depth.
Keep up the good work!!
Dr. C
Discussion forum: Grade A
Academic/Scientific research What is Academic/Scientific research? Bring your multidisciplinary viewpoints to support your arguments.
Academic/Scientific research consists of data analysis and formulas. This data analysis looks to prove or disprove hypotheses. The main objective is to learn, discover, and investigate the integrity of the data. What academic/scientific research can bring to society, science, individuals, etc. is proven information that people can learn from or expand upon.
Module 2:
Grade B+: Case
Professor comments:
Alexandria,
In this assignment you were asked to put together a simulation mimicking 500 series to determine using a simulation experiment what the likelihood is of World Series sweeps. You were asked to discuss this in terms of probability and statistics and to provide your result and some basic graphical analysis.
There were two ways to do this with SPSS. One involved the use of a syntax editor and the second way to handle this was provided in a wave file tutorial.
You used an Excel statistical product, which is fine.
Overall you appear to have done what you were asked to do except I did not see the pie chart of your outcome, and I think it would have been good to provide some explanation regarding the differences in calculated probabilities and actual series outcomes. For instance, clearly teams are not always evenly matched. There are also other potentially spurious variables such as home team advantage among others. Also, I did not see where you extrapolated to additional series outcomes such as a series going 5, 6 or 7 games. Regardless, you did demonstrate some critical thinking and a grasp of the fundamental concepts presented in this module.
Dr. C
Grade A-: SLP
Professor comments:
Alexandria,
In this assignment you were asked to identify the appropriate distributions for various data types, distinguish between a few terms related to sampling, and to show how to calculate World Series probabilities for winning games 5, 6 and 7.
In short, the information provided for assigning distributions was a bit vague in most accounts and required a little ‘qualifying’ of the information to be able to intelligently argue for one type of distribution or another. I think it would have been good for you to describe why you thought the distributions you selected would fit the data set described. Also, a number of students selected to use an abbreviation for a binomial expression in their probability calculations. I don’t really have a problem using this approach and I noted you used this approach as well. You did a good job with this part of the assignment.
Dr. C
Discussion forum: Grade B+
Interesting Probability Question Let us look at a very interesting probability question here: In a certain televising game show, a valuable prize is hidden behind one of three doors. You, the contestant, pick one of the three doors. Before opening it, the announcer opens one of the other two doors and you see that the prize isn't behind that door. The announcer offers you the chance to switch to the remaining door. Should you switch, or does it really matter? (Hint: you may use conditional probability)
You are welcome to share your thoughts and clues here and it can be a collaborate effort. The final answer may not matter as long as you show your logic reasoning here.
The initial probability of opening the correct door is 1/3 or 33%, since there are 3 doors and you can only finalize one.
"...the announcer opens one of the other two doors and you see that the prize isn't behind that door..."
It doesn't really matter if the contestant switches or not because the odds of winning will always be slim.
If the contestant picks correctly (door 1), and door 2 or 3 is randomly opened and reveals that there is no prize, then there is a 1/2 chance between the contestant's choice and the announcer's choice and cannot open door 1 to open.
door 1 probability=0
door 2 probability=1/2
door 3 probability=1/2
If the contestant picks door 1 but door 2 has the prize, the announcer will pick door 3.
door 1=0
door 2=0
door 3=1
If the contestant picks door 1 but door 3 has the prize, the announcer will pick door 2 to open.
door 1=0
door 2=1
door 3=0
This is only if the announcer does not reveal the door with the prize.
There is a second set of probabilities if the announcer does show the prize if the contestant picks door 1.
door 1=0
door 2=1/2
door 3=1/2
Module 3:
Grade A: Case
Professor comments:
Alexandria,
You did a good job with this assignment. Your reasoning was easy to follow and you did a good job of following directions. I think the key point of this assignment is to give students some 'hands on' experience with sampling distributions. I like that your 'experiment' tended to demonstrate the Central Limit Theorem as well. Both concepta are important fundamentals of statistics.
You seem to have done everything that was required of you. Good work!
Dr. C
Grade B+: SLP
Bonus: SLP with comments from professor
Professor comments:
Alex,
Please see the attached feedback file...
Dr. C
Discussion forum: Grade N/A
Understanding Polls -- Confidence Interval Many newspapers, when reporting results of political polls, say that “with 95% confidence, the results are in error by no more than +/- 3 percentage points.” The typical sample size is about 1500. This allowance for error is intended to cover both sampling variability and the effect of small biases.
a) Assume that the poll (sample) indicates that just about 50% of likely voters favor a particular candidate. How large a +/- term is required for a 95% confidence interval for the population proportion.
b) Would the +/- term be much different if 40% of likely voters in the sample favored the candidate.
c) Why is the quoted +/- 0.03 larger than the +/- term you calculated in question a)?
Many newspapers, when reporting results of political polls, say that “with 95% confidence, the results are in error by no more than +/- 3 percentage points.” The typical sample size is about 1500. This allowance for error is intended to cover both sampling variability and the effect of small biases.
a) Assume that the poll (sample) indicates that just about 50% of likely voters favor a particular candidate.
P = 50% (or .5) of voters that favor the candidate
n = 1500 is the sample size
standard deviation sample proportion (p) = sqrt[P(1 – P) / n] (Stattrek.com, 2011)
p = sqrt[.5(1 - .5) / 1500] = sqrt[.25 / 1500] = sqrt.0001666 = 0.0129
Confidence Interval (z) = 1.96 (Bioconsulting.com, n.d.)
Confidence (C) = 95%
Confidence interval with level C (N) = (1-C)/2
N = (1-.95)/2 = .05/2 = .025
Margin of error (m) = z * p / sqrt N (Mackowaik, et al, 1992)
m = (1.96 * 0.0129 / .025)² = (.025284/.025)² = 1.01132² = 1.0228
b) Would the +/- term be much different if 40% of likely voters in the sample favored the candidate.
P = 40% (or .4) of voters that favor the candidate
p = sqrt [.4(1 - .4) / 1500] = sqrt [.24 / 1500] = sqrt.00016 = 0.0126
m = (1.96 * 0.0126 / .025)² = (.024696/.025)² = .98784² = .97582
c) Why is the quoted +/- 0.03 larger than the +/- term you calculated in question a)?
The quoted +/- 0.03 might have been larger than the +/- term I calculated because the quote may have come from different standard deviation calculations and may need more information, such as other samples to calculate the question more appropriately.
Stattrek.com (2011)
http://stattrek.com/ap-statistics-4/standard-error.aspx
Mackowiak, et al (1992)
http://www.stat.yale.edu/Courses/1997-98/101/confint.htm
Bioconsulting.com (n.d.)
http://www.bioconsulting.com/calculation_of_the_confidence_interval.htm
Module 4: in progress
I honestly felt that this was the hardest course I have had to take in a long time. I am really dreading taking any more statistical courses. I thank my professor for being very generous with his grading methods as I am very new to this type of course and mostly tech savvy.
For my BUS504 course, here are my essays:
Module 1:
Case
SLP
Module 2:
Case
SLP
Module 3:
Case
SLP
Module 4:
Case
SLP
Module 5:
Case
SLP
Unfortunately I do not recall what grade I received for each assignment, however, the overall grade for the BUS504 course was a B+.
I am currently taking RES600 - Introductory Data Analysis. This will be my last course at TUIU as I am transferring back over to University of Phoenix.
Module 1:
Grade A: Case
Professor comments:
Alexandria,
In this assignment you were asked to identify the key research question in the study presented, distinguish between types of variables, and provide relevant descriptive statistics to include frequency tables, box plots and other relevant statistics. You were also directed to give a go at using the cross tabs function. You were also asked to comment on these various findings in relation to the variables considered most and least important to kids in relation to defining popularity …and you were asked to provide some other observations.
Overall I like what you did. I did not see where you clearly and specifically pointed out the key research question, though you did allude to it. Also, you might want to spend some time pondering if Grade might be better construed as Interval data. From the start of one grade to the start of another is one year. Thus, there is a constant distinction or interval between grades. At the same time, there is no zero value in K-12.
Still, you seem to understand the fundamental concepts presented in the assignment and I appreciate your hard work.
Dr. C
Grade B+: SLP
Professor comments:
In this assignment you were asked to identify the data type for a series of variables. You were then presented with a coding scheme for categorizing income data and asked to comment on it. Finally, you were asked to provide a frequency table and calculate the mean, median and mode for speed limits in various countries.
Overall you did a good job with this assignment. I think, however, that for the nominal data categories such as marital status and whether a person has been unemployed, the mean has very little meaning. Here it seems that frequencies, proportions and the mode would be the appropriate descriptive statistic. Also, I was hoping for a bit more comment on question 2. At the doctoral level your response to any given question should be quite in-depth.
Keep up the good work!!
Dr. C
Discussion forum: Grade A
Academic/Scientific research What is Academic/Scientific research? Bring your multidisciplinary viewpoints to support your arguments.
Academic/Scientific research consists of data analysis and formulas. This data analysis looks to prove or disprove hypotheses. The main objective is to learn, discover, and investigate the integrity of the data. What academic/scientific research can bring to society, science, individuals, etc. is proven information that people can learn from or expand upon.
Module 2:
Grade B+: Case
Professor comments:
Alexandria,
In this assignment you were asked to put together a simulation mimicking 500 series to determine using a simulation experiment what the likelihood is of World Series sweeps. You were asked to discuss this in terms of probability and statistics and to provide your result and some basic graphical analysis.
There were two ways to do this with SPSS. One involved the use of a syntax editor and the second way to handle this was provided in a wave file tutorial.
You used an Excel statistical product, which is fine.
Overall you appear to have done what you were asked to do except I did not see the pie chart of your outcome, and I think it would have been good to provide some explanation regarding the differences in calculated probabilities and actual series outcomes. For instance, clearly teams are not always evenly matched. There are also other potentially spurious variables such as home team advantage among others. Also, I did not see where you extrapolated to additional series outcomes such as a series going 5, 6 or 7 games. Regardless, you did demonstrate some critical thinking and a grasp of the fundamental concepts presented in this module.
Dr. C
Grade A-: SLP
Professor comments:
Alexandria,
In this assignment you were asked to identify the appropriate distributions for various data types, distinguish between a few terms related to sampling, and to show how to calculate World Series probabilities for winning games 5, 6 and 7.
In short, the information provided for assigning distributions was a bit vague in most accounts and required a little ‘qualifying’ of the information to be able to intelligently argue for one type of distribution or another. I think it would have been good for you to describe why you thought the distributions you selected would fit the data set described. Also, a number of students selected to use an abbreviation for a binomial expression in their probability calculations. I don’t really have a problem using this approach and I noted you used this approach as well. You did a good job with this part of the assignment.
Dr. C
Discussion forum: Grade B+
Interesting Probability Question Let us look at a very interesting probability question here: In a certain televising game show, a valuable prize is hidden behind one of three doors. You, the contestant, pick one of the three doors. Before opening it, the announcer opens one of the other two doors and you see that the prize isn't behind that door. The announcer offers you the chance to switch to the remaining door. Should you switch, or does it really matter? (Hint: you may use conditional probability)
You are welcome to share your thoughts and clues here and it can be a collaborate effort. The final answer may not matter as long as you show your logic reasoning here.
The initial probability of opening the correct door is 1/3 or 33%, since there are 3 doors and you can only finalize one.
"...the announcer opens one of the other two doors and you see that the prize isn't behind that door..."
It doesn't really matter if the contestant switches or not because the odds of winning will always be slim.
If the contestant picks correctly (door 1), and door 2 or 3 is randomly opened and reveals that there is no prize, then there is a 1/2 chance between the contestant's choice and the announcer's choice and cannot open door 1 to open.
door 1 probability=0
door 2 probability=1/2
door 3 probability=1/2
If the contestant picks door 1 but door 2 has the prize, the announcer will pick door 3.
door 1=0
door 2=0
door 3=1
If the contestant picks door 1 but door 3 has the prize, the announcer will pick door 2 to open.
door 1=0
door 2=1
door 3=0
This is only if the announcer does not reveal the door with the prize.
There is a second set of probabilities if the announcer does show the prize if the contestant picks door 1.
door 1=0
door 2=1/2
door 3=1/2
Module 3:
Grade A: Case
Professor comments:
Alexandria,
You did a good job with this assignment. Your reasoning was easy to follow and you did a good job of following directions. I think the key point of this assignment is to give students some 'hands on' experience with sampling distributions. I like that your 'experiment' tended to demonstrate the Central Limit Theorem as well. Both concepta are important fundamentals of statistics.
You seem to have done everything that was required of you. Good work!
Dr. C
Grade B+: SLP
Bonus: SLP with comments from professor
Professor comments:
Alex,
Please see the attached feedback file...
Dr. C
Discussion forum: Grade N/A
Understanding Polls -- Confidence Interval Many newspapers, when reporting results of political polls, say that “with 95% confidence, the results are in error by no more than +/- 3 percentage points.” The typical sample size is about 1500. This allowance for error is intended to cover both sampling variability and the effect of small biases.
a) Assume that the poll (sample) indicates that just about 50% of likely voters favor a particular candidate. How large a +/- term is required for a 95% confidence interval for the population proportion.
b) Would the +/- term be much different if 40% of likely voters in the sample favored the candidate.
c) Why is the quoted +/- 0.03 larger than the +/- term you calculated in question a)?
Many newspapers, when reporting results of political polls, say that “with 95% confidence, the results are in error by no more than +/- 3 percentage points.” The typical sample size is about 1500. This allowance for error is intended to cover both sampling variability and the effect of small biases.
a) Assume that the poll (sample) indicates that just about 50% of likely voters favor a particular candidate.
P = 50% (or .5) of voters that favor the candidate
n = 1500 is the sample size
standard deviation sample proportion (p) = sqrt[P(1 – P) / n] (Stattrek.com, 2011)
p = sqrt[.5(1 - .5) / 1500] = sqrt[.25 / 1500] = sqrt.0001666 = 0.0129
Confidence Interval (z) = 1.96 (Bioconsulting.com, n.d.)
Confidence (C) = 95%
Confidence interval with level C (N) = (1-C)/2
N = (1-.95)/2 = .05/2 = .025
Margin of error (m) = z * p / sqrt N (Mackowaik, et al, 1992)
m = (1.96 * 0.0129 / .025)² = (.025284/.025)² = 1.01132² = 1.0228
b) Would the +/- term be much different if 40% of likely voters in the sample favored the candidate.
P = 40% (or .4) of voters that favor the candidate
p = sqrt [.4(1 - .4) / 1500] = sqrt [.24 / 1500] = sqrt.00016 = 0.0126
m = (1.96 * 0.0126 / .025)² = (.024696/.025)² = .98784² = .97582
c) Why is the quoted +/- 0.03 larger than the +/- term you calculated in question a)?
The quoted +/- 0.03 might have been larger than the +/- term I calculated because the quote may have come from different standard deviation calculations and may need more information, such as other samples to calculate the question more appropriately.
Stattrek.com (2011)
http://stattrek.com/ap-statistics-4/standard-error.aspx
Mackowiak, et al (1992)
http://www.stat.yale.edu/Courses/1997-98/101/confint.htm
Bioconsulting.com (n.d.)
http://www.bioconsulting.com/calculation_of_the_confidence_interval.htm
Module 4: in progress
I honestly felt that this was the hardest course I have had to take in a long time. I am really dreading taking any more statistical courses. I thank my professor for being very generous with his grading methods as I am very new to this type of course and mostly tech savvy.
Subscribe to:
Posts (Atom)