Transcript Statistic for the day: Price of a bullet proof mink coat from Zizzo Bullet

Apr. 9 Statistic for the day:
Number of times a Hummer H2
could be driven around the world
on the excess calories Americans
consume each year: 244
Source: Harper’s index
Assignment:
Review for Monday’s test using practice
problems, exercises from book, and lecture
notes
These slides were created by Tom Hettmansperger and in some cases
modified by David Hunter
You should read and review the difference between
•Categorical and measurement variables
•Continuous measurement variables and discrete
measurement variables
You should be able to distinguish among
•Validity of a measurement
•Reliability of a measurement
•Bias of a measurement
See pp40-43 of the text
Categorical, discrete measurement,
or continuous measurement?
(Cat)  Eye color
(CM)  Weight
(DM)  Number of siblings
(Cat)  Gender
(CM)  Time in 100-meter dash
(DM)  Number of cigarettes smoked in a day
(Cat)  Building where your first class occurs
Consider a clock that’s 5 minutes
fast.
Valid or invalid?
 Reliable or unreliable?
 Biased or unbiased?

Answer: valid, reliable and biased.
Consider a scale that is sometimes
several pounds too low, sometimes
several pounds too high
Valid or invalid?
 Reliable or unreliable?
 Biased or unbiased?

Answer: valid, unreliable and unbiased.
Confidence intervals
All confidence intervals look like this:
Estimate of population value ± (multiplier)(SD of estimate)
1. Know how to match up estimate with SD (three
possibilities)
2. Know how to find the multiplier on p. 137 if I
give you a confidence coefficient other than 95%
(for 95%, the multiplier is 2). By the way, p.
137 will be provided for you on the test (you
don’t need to copy it onto your sheet of notes).
How to create 95% CI’s for:
a)
A population proportion
Sample proportion ± 2(SD of sample proportion)
b)
A population mean
c)
The difference between two population means
(SE mean)
Sample mean ± 2(SD of sample mean)
Diff of sample means ± 2(SD of diff of sample means)
SD of sample proportion
The standard deviation of the sample proportion is
estimated by:
sample proportion  (1  sample proportion )
sample size
SD of sample mean (SE mean)
The standard deviation of the sample mean is estimated
by
sample standard deviation
sample size
This estimate of the SD is called the STANDARD
ERROR OF THE MEAN, or sometimes SE mean or
SEM.
SD of difference of sample means
The standard deviation of the difference between two
sample means is estimated by
(SEM #1)  (SEM #2)
2
2
(To remember this, think of the Pythagorean theorem.)
The logic of confidence intervals
What does a 95% confidence interval tell us? (What’s the
correct way to interpret it?)
IF (hypothetically) we were to repeat the
experiment many times, generating many 95%
CI’s in the same way, then 95% of these intervals
would contain the true population value.
Note: The population value does not move; the
hypothetical repeated confidence intervals do.