1. What is Statistics?
Discover how this complex discipline is relied upon to get
to the heart the of great quantities of information. Historical
anecdotes and brief profiles of contemporary applications provide
an overview of statistics. (28:51 minutes)
|
2. Picturing Distributions
Are patterns perfect predictors? Construct stemplots,
frequency tables and histograms, and understand the importance of pattern
deviations, including gaps and outliers, in examples drawn from meteorology,
traffic control and television programming. (28:46 minutes)
|
3. Describing Distributions: Numerical Descriptions
A few good numbers can be worth a thousand words. Examines
the difference between mean and median and learn of quartiles, boxplots,
interquartile range, and standard deviation. Also discussed is the
advantage of back-to-back stemplots. An example of pay
inequity illustrates the principles. (28:49 minutes)
|
4. Normal Distributions
How do studies on batting averages in baseball and age changes
in population find expression in density curves? A series of simplifications
shows the progression from histogram to a single normal curve for standardized
measurement. Included are mean, median and percentiles for density
curves, and the 68-95-99.7 rule. (28:46 minutes)
|
5. Normal Calculations
Vehicle emission standards and medical studies of cholesterol
give practical examples of normal calculations at work. Covered are
the standardization and calculation of normal relative frequencies from
tables, assessing normality by normal quintile plots. (28:42 minutes)
|
6. Time Series
Discover how statistics can help identify patterns over time,
answering questions about stability and change. Trends in the stock
market and studies of sleep cycles illustrate these concepts. Topics
include statistical control; inspecting time series for trend, seasonal
variation, cycles; and smoothing by averaging. (28:54 minutes)
|
7. Models for Growth
Topics include linear growth, with review of the geometry of
straight lines; an introduction to the least squares idea; exponential
growth, and straightening an exponential growth curve by logarithms; prediction
and extrapolation. Studies of children's growth problems and of world
oil production provide examples. (28:57 minute)
|
8. Describing Relationships
Scatterplots and their variations are discussed in examples
drawn from weight-loss programs to manatee protection. Also covered
are smoothing scatterplots of response versus explanatory variables by
median trace; linear relationships, least squares regression lines, and
comment on outliers. (28:42 minutes)
|
9. Correlation
Find out how to derive the correlation coefficient and to interpret
it, using the relationship between a baseball player's salary and his home-run
statistics as one example. A study of identical twins further illustrate
correlation concepts. (28:52 minutes)
|
10. Multidimensional Data Analysis
The program recaps the presentation of data analysis by showing
the use of computing technology and a case study at Bell Communications
Research. A study on environmental stresses in the Chesapeake Bay
demonstrates the value of statistical principles. (28:46
minutes)
|
11. The Question of Causation
Observed association may or may not represent causation.
The relationship between smoking and lung cancer is examined. A study
of admissions data illustrates Simpson's paradox. (28:52 minutes)
|
12. Experimental Design
Distinguish between observational studies and experiments and
learn the basic principles of design including comparison, randomization,
and replication. Case material for heart disease study shows the
advantages of a double-blind experiment. (28:46 minutes)
|
13. Blocking and Sampling: Experiments and Samples
Understand random sampling and the difference between single-factor
and multi-factor experiments and the kinds of questions each can answer.
A study of agriculturalists' efforts to find improved varieties of strawberries
demonstrates randomized block design. (28:37 minutes)
|
14. Samples and Surveys: Sampling and Sampling Distributions
Can small samples give accurate information? Stratified
random sampling is explained. A 1936 Gallup election yields important
information about the concept of undercoverage and the importance of careful
use of sampling. See how a survey is designed to ensure randomness
and avoid bias. (28:51 minutes)
|
15. What is Probability?
Distinguish between deterministic and random phenomena, and
understand sample space, events, outcomes and probability models.
Examples include the work of statistician Persi Diaconis on probability
and randomness and a computer that models traffic scenarios. (28:49
minutes)
|
16. Random Variables
How does a statistician calculate the probability of a space
shuttle accident? How do geologists use statistics to predict earthquakes?
Learn about the idea of independence; the multiplication rule for independent
events; and discrete and continuous random variables. (28:47 minutes)
|
17. Binomial Distributions
Find out how to calculate the mean and standard deviation of
binomial distributions, and see how the quincunx, a randomizing device
at the Boston Museum of Science, illustrates concepts. Addition rules
for the means and variance of random variables are defined in an example
predicting sick cell anemia. (28:46 minutes)
|
18. The Sample Mean and Control Charts
Roulette and the manufacturing industry offer real-life demonstrations
of the use of the central limit theorem, control chart monitoring of random
variation, creation of x-bar charts and definitions of control limits and
out-of-control monitoring. (28:42 minutes)
|
19. Confidence Intervals
Understand the two aspects of confidence intervals--the interval
and the confidence level--and see how they are used in blood pressure studies,
political and population surveys, and primate research. Included are z
intervals for the mean of a normal distribution and behavior of confidence
intervals. (28:53 minutes)
|
20. Significance Tests
A hiring discrimination case and a study of Shakespearean authorship
illustrate the basic reasoning behind tests of significance. The strengths
and weaknesses of significance tests are assessed. Defined are null
and alternative hypotheses and p-values. (28:44 minutes)
|
21. Inference for One Mean
Discover an improved technique for statistical problems that
involve a population mean: the t-statistic for use when s
is not known. Paired samples are emphasized as the most important
practical use of these procedures. The t-confidence interval and
t-test and "robustness of t-procedures" are defined. (28:52
minutes)
|
22. Comparing Two Means
Learn how to recognize a two-sample problem and to distinguish
such samples from one-sample and paired-sample situations. Give a
confidence interval for the difference between two means. Demonstrate
the two-sample t-test with conservative degrees of freedom.
(28:50 minutes)
|
23. Inference for Proportions
How do federal government statisticians estimate how many people
are unemployed? What size sample can give accurate results?
Discover confidence intervals and tests for single proportion and for comparing
proportions based on paired and independent samples. (28:51
minutes)
|
24. Inference for Two-Way Tables
A two-way table can show the relationship between two categorical
variables in a single population or compare the distributions of a single
categorical variable in several populations. The chi-square test
for independence/equal distributions in two-way tables is covered.
(28:52 minutes)
|
25. Inference for Relationships
See how statistical principles come together in a case study
that illustrates planning the data collection, collecting and picturing
the data, drawing inferences from the data, and deciding how confident
to be about the conclusions. (28:54 minutes)
|
26. Case Study
See how statistical principles come together in a case study
the illustrates planning the data collection, collecting and picturing
the data, drawing inferences from the data, and deciding how confident
to be about the conclusions. (28:51 minutes)
|
