Date

Sept. 3

I. Introduction (Text: Chapter 1, pp. 1-9)

A. Statistics - There are two definitions. The two definitions require different verb tenses.

1. Descriptors - Facts or information of a numeric type. (Statistics are . . . )
2. Field of study or body of knowledge - This course! (Statistics is . . .)

B. Two Kinds of Statistics:

1. Descriptive: methods or procedures used to describe data. Tables, charts, graphs and numeric measures.

2. Inferential: sample data are used to draw a conclusion about the population from which the sample was drawn.

Sept. 5

I. Introduction - Continued (Chapter 1, pp: 1-37)

B. Two Kinds of Statistics:

1. Descriptive: methods or procedures used to describe data. Tables, charts, graphs and numeric measures.

2. Inferential: sample data are used to draw a conclusion about the population from which the sample was drawn.

C. Data Collection

1. Census: collecting data from all members of a population.

2. Sampling: selecting a subset of the population from which you gather data. Discussed several different methods of drawing samples.

Problems for Sampling:
Biases and Errors

Sept. 8

3. Experiments: an alternative means of collecting data. Key elements: control, randomization, replication.

II. Descriptive Statistics

A. Organizing Data (Chapter 2)

1. Variables and Data:(pp. 40-46)

Distinguished between variables and data; discussed different types of variables and data.

Sept. 10

A. Organizing Data (Chapter 2)

1. Variables and Data (pp. 40 - 46): PRS questions about variables and data. Finished discussing variables and data - the hierarchy of data.

2. Grouping Data (pp. 46 - 60): data arrays (sorting); grouped data tables; histograms.

Handout: 1997 Used Honda Accord data

Sept. 12

2. Grouping Data (pp. 46 - 60): Created a grouped data table for the 1997 Used Honda Accord data.

3. Graphs and Charts (pp. 58 - 72)

• Histograms: used for continuous quantitative data - the bars touch.
• Bar Charts: discrete data, nominal or qualitative data - the bars don't touch.

Sept. 15

• Bar Charts: discrete data, nominal or qualitative data - the bars don't touch.
• Shapes of distributions: (pp. 72-79) describing distributions - center, variation and shape. Symmetric and skewed distributions.
• Other Graphs and Charts: (pp. 58-72) Pie Charts, DotPlots, Stem and Leaf, Line Graphs.

Handout: Dotplots and Stem and Leaf Diagrams

4. Misleading Graphs: (79-83) issues with scale and the vertical axis.

B. Descriptive Measures - More Descriptive Stats.

1. Measures of Center (Chapter 3: Sections 3.1 and 3.2)

• Mean, Median and Mode: brief definitions and discussion of center; appropriate measures of center; population vs. sample.

Sept. 19

• The Mean - summation notation.
• Measures of Center, and Shape.

2. Variation: (Chapter 3, Section 3.3 and the first part of 3.5)

• Range
• Standard Deviation and Variance

Focus our discussion on measures of variation that are used with the sample mean and population mean: range, variance and standard deviation.

Sept. 22

2. Variation:
Final words; looked at the short-cut formulas for population and sample standard deviation.

3. Intervals: Combining Center and Variation. (Chapter 3, sections 3.3 and 3.5)
Intervals using Chebychev's Rule, the Empirical Rule.

In constructing these intervals we use the characteristics of the distributions, the mean and standard deviation. Another way to learn about or illustrate features of data distributions.

Sept. 24

4. 5-Number Summary (Chapter 3, Section 3.4)
Minimum, Q1, Q2, Q3 and the Maximum.
Discussed also the IQR and Outliers, both Potential and Probable.

Sept. 26

Stats Live - estimate the population means and standard deviations for ResEc Male and Female student heights.

4. 5-Number Summary:

More on Outliers. Minitab approach using boxplots. Shapes of distributions determined from boxplots.

We'll be finished with Chapter 3.

C. Regression (Chapter 4: read sections 4.1 and 4.2)

1. Introduction - univariate stats vs. bivariate stats.
2. Linear Equations - equations for a straight line, intercept, slope, x-values and y-values.
3. Scatter Diagrams - plot of numeric data in XY space.
4. Regression - a regression relationship, errors, the least squares criterion.

Oct. 1

4. Regression - finish regression. Least squares review, meaning of intercept and slope estimates, examples.
5. Correlation - association between two variables, measures strength of association.

Exam 1
Thompson 102, 104, 106
6:00 - 8:00 PM

Oct. 5

III. Probability, Random Variables, Normal Distribution and Sampling Distribution.

A. Probability (Chapter 5).

1. Basic Probability Concepts: defined concepts, build vocabulary. Probability will be discussed in terms of experiments, outcomes, sample space and events. Defined probability - discussed the classical view and the frequentists' view. Moved on to more complex events and talked about complements and mutually exclusive events.

Oct. 10

1. Basic Probability Concepts: more on complements, mutually exclusive events and independent events. We also introduced joint frequency distributions and talked a bit about joint probabilities, eg. P(A & B).
2. Rules of Probability: Started on the 10 rules.

Oct. 12

2. Rules of Probability: First 4 are straightforward. More time on the addition rules, conditional probability and multiplication rules. Discussed joint, marginal, conditional probabilities.

Oct. 15

Completed Rules of Probability and reviewed: Marginal, Joint and Conditional Probabilities. Introduced tree diagrams as a tool.

Oct. 17

B. Random Variables (Chapter 5: 5.4 and 5.5)

1. Discrete Random Variables

• Definition
• Distributions
• Use of Tree Diagrams
• Measures of Center and Variation

Oct. 19

Stats Live.
Fun with M&Ms

Estimation, repeated sampling.
Discrete Random Variable - Number of Blue M&Ms drawn from a bag: tree diagrams (dependent trials), probability distributions, mean or expected values, and standard deviation.

Oct. 22

Binomial Discrete Random Variables (Chapter 5, Section 5.6)

• Bernoulli Trials (4 conditions)
• Theoretical model (a mathematical expression for probabilities)
• Mean and Standard Deviation
• Examples.

Oct. 24

Binomial Discrete Random Variables (Chapter 5, Section 5.6)

• Examples.
• Shapes of Distributions
• Probability Distributions as Histograms: Probabilities equal areas of bars.

C. Continuous Random Variables. (Chapter 6)

1. Introduction.
2. The Normal Distribution: center and shape depend on just two parameters. More Empirical Rule.

3. The Standard Normal Distribution:
   • Properties, characteristics

Oct. 29

C. Continuous Random Variables. (Chapter 6)

3. The Standard Normal Distribution:
   • Properties, characteristics
   • Determining probabilities: 4 Cases
   
   Using the Z-table: Instructions.

Oct. 31

4. Determining Probabilities for any Normal
5. Determining Z-values given P(.)
6. Determining X-values given a Z-score or P(.)

Nov. 2

6. Determining X-values given a Z-score or P(.)

Nov. 5

D. Sampling Distribution for the Sample Mean

1. Sampling Error - difference between estimate and true population parameter value.
• Experiment - generated a bit of a sampling distributions for n=4 and n=8.
• Bigger sample size implies less sampling error - on average.
2. Sampling Distribution for the Sample Mean
   • What it is.
   • Why is the sample mean a random variable?

Nov. 7

D. Sampling Distribution for the Sample Mean

1. Sampling Error - difference between estimate and true population parameter value.
• Experiment - generated a bit of a sampling distributions for n=4 and n=8.
• Bigger sample size implies less sampling error - on average.
2. Sampling Distribution for the Sample Mean
   • What it is.
   • Why is the sample mean a random variable?
3. Probabilities for Sampling Distributions

Exam 2
6:00 - 8:00 PM
Thompson 102, 104 or 106

Nov. 9

IV. Inference

A. Confidence Intervals for Population Mean
(Chapter 8)

1. Point and Interval Estimation
2. CI for Population Mean (Sigma-X is known.)

Nov. 14

IV. Inference

A. Confidence Intervals for Population Mean
(Chapter 8)

1. Point and Interval Estimation
2. CI for Population Mean (Sigma-X is known.)
3. Margin of Error and Sample Size - discussed the margin of error; given margin of error and confidence level, we can solve for the appropriate sample size.
4. CI for Population Mean (Sigma-X not known)

Nov. 16

IV. Inference

A. Confidence Intervals for Population Mean
(Chapter 8)

1. Point and Interval Estimation
2. CI for Population Mean (Sigma-X is known.)
3. Margin of Error and Sample Size
4. CI for Population Mean (Sigma-X not known) - finish confidence intervals, create t-intervals.

B. Hypothesis Tests for Population Mean
(Chapter 9)

1. Basics of Hypothesis Tests
2. Terms, Errors, Conclusions.

Nov. 21

NO CLASS : Thanksgiving Break

B. Hypothesis Tests for Population Mean
(Chapter 9)

1. Basics of Hypothesis Tests
2. Terms, Errors, Conclusions.

Nov. 28

2. Terms, Errors, Conclusions

3. Hypothesis Tests - Pop. St. Deviation Known

Nov. 30

3. Hypothesis Tests - Pop. St. Deviation Known. We did a complete test, start to finish.

4. P-Values. Hypothesis Tests - Pop. St. Dev. Known.

 

Dec. 3

No class - snow :(

Dec. 5

5. Hypothesis tests - Pop. Standard Deviation is not known. We need to do a t-test. Estimate both the sample mean and the sample standard deviation.

C. Inference for Proportions (Chapter 11)

1. Sampling Distribution for Sample Proportion.
2. Confidence Intervals for Population Proportion.
3. Hypothesis Tests for Population Proportion.

Dec. 7

2. Confidence Intervals for Population Proportion.

Examples: Confidence Intervals for US Obseity Rates.

3. Hypothesis Tests for Population Proportion. Completed a hypothesis test for US Male Obesity Rates - assumed a single sample test with a "claim" that was equal to the 2003/4 rate.

4. Two Sample Tests of Population Proportions. If we know that the 2003/4 rate was an estimate, it affects our inference. Standard errors for both p1 and p2 (the sample proportions) are included.

US Obesity Hypothesis Tests

Dec. 12

4. Two Sample Tests of Population Proportions. Finish the test. Quick summary.

Review and Discuss an Old Topic: Type I vs. Type II Error and Power of the Test.