Class Notes (1,100,000)
US (490,000)
UC-Davis (10,000)
PHI (60)
PHI 31 (20)
Lecture 10

PHI 31 Lecture 10: PHI 31 Lecture 10 and 11


Department
Philosophy
Course Code
PHI 31
Professor
Griesemer James
Lecture
10

This preview shows half of the first page. to view the full 2 pages of the document.
LECTURE 10: 10/19
SAMPLING AND ESTIMATION
Sampling Processes
Each and every sample will look a little different from the next
Each test is a trial
Sample: produces a sequence of trials
Probability of a Sequence: combined probability of getting a result on the first trial and a
result on the second trial and a result on the third trial...
Sequences have probabilities, just as trials do
Random Sampling
2 Key Points:
1) In a very large hypothetical set of sequences of 2 trials, if the
proportion of red in each trial is equal to the proportion in the population
2) There is no correlations between trials
The LARGER the sample…
The less likely your sample will have the exact frequency of Red that is the true
proportion in the population
The closer to P(R), your sample frequency of red, f(R), will get
Close to 50%, the closer to sample size
Use combination rules, OR, to add up the area under the curve
AND is if the probabilities were to be stacked up vertically on curve
Probability Density
Standard deviation measures how close Y=f(R) is as an estimate of P(R) in a
way that is independent of sample size
of the probability density is within 1 standard deviation from the most probable
Y
95% of the probability density is within 2 standard deviations from the most
probably Y
LECTURE 11: 10/22
ESTIMATION AND EVALUATION
You're Reading a Preview

Unlock to view full version