Business Statistics: Exam I
Wednesday, January 30, 2013
7:00 pm
You will need a calculator for this exam.
I will provide a list of useful equations and a copy of the normal
table.
I. Introduction
A. Using statistics
1. meaning, context, definition
2. methodology
3. descriptive statistics,
uncertainty, estimation
B. Reporting statistics
1. publication bias
a. "positive" results
b. sponsor
2. conclusions may not reflect
statistical results
3. results may not be statistically
significant
- is a confidence level or margin of
error reported?
4. results may not have real world
significance
5. biased samples or biased surveys
will give meaningless results
- is methodology reported?
II. Describing Data
A. Graphs
1. qualitative variables
a. pie charts
b. bar charts
2. quantitative variables
a. histograms
b. boxplots
B. Measures of central tendency
1. mean
2. median
3. mode
C. Measures of dispersion
1. variance
2. standard deviation
3. range
4. quartiles, quintiles,
percentiles
5. coefficient
of variation
D. Summarizing distributions
1. mean, standard deviation
2. five-number summary
3. boxplot
E. Descriptive Statistics and probability
1. Chebyshev's theorem
2. The Empirical rule (for
normal distributions)
III. Relations between variables
1. scatterplots
2. covariance
3. correlation
a. positive, negative, or zero
correlation
b. strong or weak correlation
4. regression
5. correlation does not imply
causality
a. X may cause Y
b. Y may cause X
c. X and Y may interact
d. a third variable may cause
both X and Y
e. the correlation might be spurious
6. Ordinary Least Squares regression estimates
a. Y= a+bX
i.
positive, negative, or no relation (slope)
ii. Predicting value of Y
given value of X
iii. Testing theories
b. best, linear, unbiased
estimate
c. computer estimation
7. Regression issues
a. regression does not show causality
b. Data collection must be methodologically sound
i. random
sample, representative of population
ii. avoid
bias in survey questions
iii. results
are sensitive to extreme values (outliers)
iv. model
must be correctly specified
- missing
variables
- spurious
relations
IV. Data Collection
A. Samples must be random and representative
1. sampling
design
a. random
sample
b.
systematic sample
c.
stratified sample
d. cluster
sample
2. response
rates
3. Sample bias
a. good samples are representative of
population
b. biased samples-- meaningless results
B. Survey Methods
1. write questions carefully
i. avoid bias
a. leading questions
b. confusing questions
c. over reliance on
memory
ii. group like
questions together
2. test survey
3. revise
V. Estimation
1. sample statistics are imperfect
estimates of population parameters
2. variability
a. sampling error
b. larger samples reduce variability
4. standard error
a. sample mean
b. proportion
5. Working with inferential statistics
a. interval estimates may be
preferable
b. issues of statistical
significance
c. hypothesis testing
VI. Probability distributions
1. overview.
2. the normal distribution
a.
characteristics
b. the
standard normal
i. transforming to standard normal form
ii. Using the normal tables
Business Statistics class
page