Instructor: Dr. F. Pan Shu
(Internet Web site: www.geocities.com/shufp)
(Office: Dunn 224)
Office Hours: TTh 100-230PM (Dunn 224)
Other Hours By Appointment
Textbook:
Course Description:
The course discusses statistical procedures used for examining and interpreting business and economic data. It covers near-real-life business practices and economics analysis. Hands-on exercises requiring use of the Microsoft Excel are included. Topics to be discussed will include: the descriptive statistics; various probability distributions including normal distribution, student-t distribution, F distribution, Chi-squared distribution, Binomial distribution, and Poisson distribution; central limit theorem; parametric and non-parametric sampling distribution theorems; graphic data scatter plot and regression fitting; covariance, statistical independence, correlation and regression; simple CLRM assumptions and the regression analysis; regression model selection; parametric and non-parametric statistical inferences; and time series forecast.
Prerequisite: STA100, or ECON105/305, or ECON110/310. ECON305 is used as ECON105 for the prerequisite, and ECON310 is used as ECON110 for the prerequisite.
Grading Policy:
Student’s grade in the course is evaluated based on his/her performance in class attendance and participation, two mid-term and one final exams (with each exam including both an in-class and a take-home parts), and pop-up quizzes.
Student is advised to regularly attend class and actively participate in class discussion.
The course teaching is divided into three blocks. At the end of each teaching block, an exam will be given. Together, there are two mid-term and one final exams. In-class part of the exams will be given in class, with books and notes requested being closed during the test time. However, during the in-class exam hour, student is allowed to use formulas and notes organized in writing registered on a 8"*11" cheat sheet. Take-home part of the exams will be collected on each scheduled exam date. Student is allowed to freely use any content of the books and the notes prior to its submission to find answer to all the questions of the take-home parts of the exams. To find out the scheduled exam dates, click and go to Course Outline of the syllabus.
NO MAKE-UP WILL BE GIVEN should any in-class exam be missed due to legitimate reasons. When an in-class exam is missed for legitimate reasons, that part of the exam will be given as take-home exercise. The next in-class exam may receive double counts when this take-home exercise is completed by due date, perfectly scored. Generally speaking, this due date will be the very first date that student is regarded recovered from the excuse led to the absence.
Please refer to Take-Home Exams to find questions assigned to each of the take-home exams.
Table 1 below gives A Summary of the Final Grade Score Distribution by Grading Items .
Table 1. Final Grade Score Distribution by Grading Items
| Grading Items |
Final Grade Score Weights (out of
a total of 100%) |
| Exams |
25% each for the First and the Second
Mid-Term Exams
|
| Quizzes |
Read
Preparation for Pop-up Quizzes
for details regarding how to be prepared for the quizzes.
10 quizzes, with each counted 2.5%, are planned given during the entire
semester. |
Grading Formula:
Total final grade score will be coded into the Potsdam College final grade points following the translating formula given here. A total final grade score of 90 and above will be coded as 4.0. A total final grade score between 85 to 89 will be coded as 3.5. Final grade scores between 80 to 85 will be coded as 3.0; whereas final grade scores between 75 to 79 coded as 2.5. Next, final grade scores between 70 to 74 will be coded as 2.0; final grade scores between 65 to 69 coded as 1.5; final grade scores of 60 to 64 coded as 1.0; and scores below 60 coded as 0.
Preparation for Pop-up Quizzes:
Altogether, 10 pop-up quizzes will be given during the entire semester.
On average, this means that one pop-up quiz will be given each one
and half a weeks. To be well prepared for quizzes, student is advised
remained well reviewed of the course materials discussed and studied for
the most recent past one and half a weeks and remained well prepared in advance
for the next subject planned discussed in class. To find out subjects
planned covered in future classes, refer to Course
Outline
of the syllabus.
Listed below are take-home part of the three exams. The section numbers, page numbers, and question numbers refer to those of Siegel's. Answer to questions listed in the Take-Home Exam are required submitted when due. Refer to Course Outline of the syllabus for the Take-Home Exam due dates.
Chapter 1
- Summarize content of section 1.3.
- Summarize content of the Example "Statistical Quality Control".
Chapter 2
Chapter 3
- Summarize content of section 2.1.
- Summarize content of section 2.4.
- Duplicate the internet source exercise illustrated in Example "Searching the Internet for Government Data on Consumer Prices". Discuss content of your findings on Government Data on Consumer Prices.
Chapter 4
- Duplicate, as an exercise, the "Microsoft Excel>>Tool>>Chart>>Histogram" work illustrated in the Example "Mortgage Interest Rates". Write a report on the Histogram result.
- Summarize content of section 3.3.
- Summarize content of section 3.4.
- Summarize content of section 3.5. Discuss how is a bimodal distribution discovered from Histogram of a data set.
- Discuss the meaning of the outliers.
- Discuss content of the Histogram illustrated in Figure 3.7.1 and that of the Stem-and-leaf chart of p. 64, Siegel. Discuss your views about whether Histogram displays the information of a data better, or the stem-and-leaf chart does it better.
- Use Microsoft Excel operators to help solve answer fro Problem # 23, p, 74, Siegel.
Chapter 5
- Carefully review the landmark summaries discussed in chapter 4, Siegel. These summaries include the mean, the weighted average, the median, the mode, percentile-th summaries (such as the five number summery) found using a data's cumulative distribution, and meaning of the cumulative distribution.
- Solve Problem # 1, p. 109, Siegel, first by manual computation, then using operators of the Microsoft Excel. (Hint: When using the Microsoft Excel, first register in column A the raw data. Then, give "one" as the frequency value for each data value point. Third, compute using function operators of the Microsoft Excel for the relative and the cumulative frequency distribution of the data. Last, display Histograms based on the information given by the relative frequency distribution as well as the cumulative frequency distribution.)
- Summarize the content of "Which Summary Should You Use?", pp. 95-96.
Chapter 6
- Summarize types and meanings of the statistics useful for measuring and interpreting the variability of a data.
- Write down the standard deviation formula for sample data. Repeatedly learn this formula until you can use arithmetic operators of the Microsoft Excel to compute this statistic without using the Microsoft Excel Data Analysis Tool. An exercise as this is shown as the content of Table 5.1.2.
- Apply the Microsoft Excel>>Tool>>Data Analysis>>Descriptive Statistics operator to data discussed by Table 5.1.2. Report the descriptive statistics and then indicate whether summary statistics produced in this computation procedure contain a population or a sample standard deviation.
- Discuss content of the "Interpreting the Standard Deviation", pp.126-136, Siegel.
- Discuss differences between the formulas "the standard deviation for a sample" and "the standard deviation for a population", p. 137, Siegel. When a standard deviation is computed and directly quoted from the Microsoft Excel>>Tool>>Data Analysis>>Descriptive Statistics operator procedure, what would you need to do to report accurate population standard deviation if the data entered is the population data?
- Explain the following terms--coefficient of variation for a sample; coefficient of variation for a population; uncertainty shown in a data's performance; standardization; and data rescaling.
- Solve Problem #14, using either the arithmetic or the descriptive statistics operator of the Microsoft Excel.
- Conduct case analysis to Case, pp. 158-159, Siegel. This work is allowed for being two-authored. For a co-authored submission, clearly mark down names of the two authors contributing to the work.
Chapter 7
- Discuss the following terms--random experimental design; sample space; events; complement events; mutually exclusive events; the union of events; the joint of events; independent events; probability; odds; law of large numbers; theoretical probability; conditional probability; joint probability ; a probability tree; and Venn diagrams.
- Duplicate as exercises works that are illustrated in all the examples of section 6.5. Together, work is needed done for four examples illustrated.
- What is a generic joint probability table? How are marginal probabilities computed in this kind of the probability table? (Reading: pp. 194-5, Siegel.)
- Conduct case analysis using Case, pp.206-207, Siegel. This is a one-authored case work.
Chapter 8
- How are summary statistics expressed in the expected value terms? (For the topic regarding the discrete random variable, read pp. 210-212, Siegel. To understand the topic regarding the discrete binomial distribution, read pp. 214-223, Siegel.)
- Duplicate as exercises works that are illustrated by all the examples given in pp. 214-233, Siegel. Compute the binomial frequency using the Microsoft Excel like those illustrated in p. 221, Siegel.
- Discuss elements required of being made clear for what is the normal distribution and for what is the standard normal distribution. Familiarize yourself with the Microsoft Excel normal probability operator and its use for the identifying of an exact normal probability (To find an example, see page 231, Siegel.)
- Solve Problems # 1, p. 245, Siegel.
- Solve Problems # 3, 5, and 9 of pp. 246-247, Siegel by following the procedure illustrated in box "Mean and Standard Deviation For A Binomial Distribution", p. 218, Siegel.
- Read box "Computing Probabilities for A Normal Distribution", p. 231, Siegel, and use the Standard Normal Probability Table of pp. 226-227, Siegel, when appropriate, to solve Problems # 20, 21, and 22, p. 249.
- Summarize content of section 7.4 and duplicate as exercises of works illustrated by examples given in this section.
- Summarize content of box "Using the Normal Approximation to the Binomial", p. 234, Siegel.
- Discuss elements required of being made clear for what is the Poisson distribution and for what is the Exponential distribution. Refer to section 7.5 for your discussion. Duplicate as exercises works that are illustrated by all the examples given in section 7.5.
- Discuss what is the sampling distribution of the sample mean. Also discuss what is the central limit theorem. (Read content of sections 8.2 and 8.3.)
- Discuss elements required of being made clear for what is the sampling distribution of sample sum.
- Also, discuss what is the sampling distribution of the sample proportion.
- Summarize content of this chapter, especially, relate information learned to topics listed below--random experimental design, the relationship between parameters and statistics, and the relationship between the population standard deviation, the sample standard deviation, and the standard error (of the average, of the sum, or just the sample standard error).
- Explain the finite population correction factor for the adjusted standard error of the average.
- Summarize the Binomial standard deviation, the Binomial standard error for number of occurrences, and the Binomial standard error for proportion.
- Duplicate as exercises works illustrated by all the examples given in pp. 256-285, Siegel.
Chapter 9
- Explain what is the confidence interval and how is the interval estimated.
- Discuss how is the knowledge of the sampling distribution used for the confidence interval estimation. (Refer to content of section 9.1, Siegel for information.)
- Duplicate as exercises works that are illustrated by all the examples given in section 9.1, Siegel.
- Summarize content of the remaining sections of Chapter 9, Siegel. Indicate what elements are confusing and what are not.
Chapter 10
- Discuss two-sided hypothesis testing procedure, based on content of Table 10.2.4, Siegel, for population mean first and for population proportion next.
- Discuss one-sided hypothesis testing procedure, based on content of section 10.4, Siegel..
- Discuss when would be the time that a z-test and when would that of a t-test be more appropriately as tool used in the hypothesis testing procedure?
- Explain what is the Type-I error and what is the Type-II error encountered in the hypothesis testing procedure? Are Type-I and Type-II errors generally known to a data analyst? Explain why or why not.
- Explain the meaning of the significance level. Also, explain the relationship between the Type-I error and the significance level.
- Summarize content of section 10. 5, Siegel.
- Discuss content of section 10.7, Siegel.
- Duplicate as exercises works that are illustrated by all the examples given in this chapter.
Chapter 11
Chapter 12-13
- Explain all the formulas used in this chapter--this includes those used for sample correlation coefficient, least-squares slope and intercept, predicted value Y, residual, standard error of the regression, R2 or the coefficient of determination, true linear regression model, standard error of the regression coefficient, standard error of the intercept term, and standard error of a new observation of Y given X 0.
- Duplicate as exercise works that are illustrated by all the examples given in this chapter.
Chapter 14
- Be familiar with content of Table 12.1.2--"Results of A Multiple Regression Analysis", p. 471, Siegel. Use elements of this table content to help get familiar with the multiple regression computer results, like those displayed by Tables 12.1.4 (p.473, Siegel), 12.2.3 (p.497, Siegel), 12.2.7 (p.499, Siegel), 12.2.11 (p.507, Siegel), 12.2.12 (p.508, Siegel), and the interpretations about these contents.
- Be familiar with the hypothesis test on the significance of the entire model based on F-statistic. Refer to "Is the Model Significant? The F test or R2 test", pp. 480-488, Siegel.
- Duplicate as exercises works displayed by examples given in pp. 488-491, Siegel for confidence interval estimation and hypothesis testing of the jth coefficient of a multiple linear regression model.
- Summarize content of section 12.2, Siegel.
- Summarize content of section 12.3, Siegel.
- Summarize content of section 12.4, Siegel.
- Summarize content of Chapter 13, Siegel.
- Summarize content of chapter 14, Siegel. Discuss the following terms: trend-seasonal analysis, MA (moving average) methods, seasonal adjustments, Box-Jenkins ARIMA (autoregressive integrated moving-average) process, parsimonious modeling, random noise process, AR (autoregressive) process, MA (moving average) process, and ARMA (autoregressive moving average) process.
- Discuss the importance of data scatter plot to the understanding of the time series process.
Chapter 15
Chapter 16
- Summarize the meaning and the testing procedure involved with the one-way, the two-way, and the three-way ANOVA.
- Give a couple of examples where you see each of the ANOVA procedure could be useful for identifying elements that are vital in making the difference for a bahavior.
- Duplicate as exercises works that are displayed by all the examples given in this chapter. Altogether, there are three ANOVA analysis examples.
Chapter 17
- Summarize content of the chapter on "Nonparametrics".
- Duplicate as exercises works that are displayed by all the examples given in the chapter.
Chapter 18
- Summarize content of the chapter on "Chi-Squared Analysis".
- Duplicate as exercises works that are displayed by all the examples given in the chapter.
- Summarize content of the chapter on "Quality Control".
- Duplicate as exercises works that are displayed by all the examples given in the chapter.
|
|
|
| August 28-- Sept. 20 |
Chapters 1-8, Siegel Descriptive Statistics, Data Structures, Histograms, Landmark Summaries, Variability, Probability, Random Variables, and Random Sampling (Normal Distribution, Binomial Distribution, Student-t Distribution, Poisson Distribution; F distribution; and Chi-squared Distribution are intended discussed. Covariance, Statistical Independence, Correlation and Regression, materials of chapter 11, Siegel are intended covered when they become relevant to the content of teaching materials of this teaching block.) |
| September 25 |
First Mid-Term Exam (In-Class exam given using the class lecture hour; Take-home due 400PM to Dunn 224.) |
| Sept. 27 -- Oct. 25 |
Chapters 9-14, Siegel Confidence Interval, Hypothesis Testing, Correlation and Regression, Multiple Regression, Report Writing, and Time Series |
| October 30 |
Second Mid-Term Exam (In-Class exam given using the class lecture hour; Take-home due 400PM to Dunn 224.) |
| Nov. 1 -- Dec. 6 |
Chapters 15-18, Siegel ANOVA; Nonparametrics; Chi-Squared Analysis; Quality Control |
| Dec. 4 |
Take-Home Final Exam due 400PM to Dunn
224. Graded Take-Home Final will be returned in class December 6. |
| Dec. 10 |
In-Class Final Exam (The exam is scheduled given 700-900PM in Dunn 200.) |
|
Copyrights are observed for all the original materials included in
this web site. Copyrighted by Dr. F. Pan Shu and the ASSI Publishing Co. (August 22, 2001) |
Link to Dr. F. Pan Shu Index Page