BIOL 300: Biostatistics

1
BIOL 300 Biostatistics
2
Statistical quotations

• There are three kinds of lies lies, damn lies,
  and statistics.
• Benjamin Disraeli / Mark Twain

3
(No Transcript)
4
Statistical quotations

• There are three kinds of lies lies, damn lies,
  and statistics.
• Benjamin Disraeli / Mark Twain
• It is easy to lie with statistics, but easier to
  lie without them.
• Frederick Mosteller

5
ProfessorDr. Luke HarmonDepartment of Zoology
Office 1370 BiosciencesOffice Hours 2 - 4 pm
Mondays(or after class)e-mail
harmon_at_zoology.ubc.ca
6
Course website

• http//www.zoology.ubc.ca/bio300/
• Lecture notes
• Textbook and Lab Manual
• Assignments and answers
• Contact information

7
(No Transcript)
8
(No Transcript)
9
Textbook

• Whitlock and Schluter, The analysis of biological
  data
• Available in two installments at CopieSmart, UBC
  Village
• Also available online

10
(No Transcript)
11
JMP

• Optional statistical software
• Used in labs
• Available in bookstore
• 60-day trial version on web
• www.jmp.com

12
Evaluation

• Final 50
• Mid-term 30
• Assignments (homework) 10
• Lab exam (final week of term) 10

13
Examinations

• Midterm Thursday October 19 in class
• Final exam TBA
• Old exams will be posted on the website

14
Assignments

• Available on course web-page, announced in class
• Due on Fridays at noon, at your TAs office
• (eight days after they are assigned)
• Bonus points for in-class quizzes and activities

15
Lab

• Begins third week of term
• (September 18- 22)
• Biol. Sci. room 2434
• Lab exam during final week of classes
• Book available at Copiesmart in the village and
  online

16
(No Transcript)
17
Class Forum

• There will be a forum for discussion on the web
• Discussion of lectures, labs, and homework
• More details available next week

18
STATISTICS PAIRINGS

• Credit given for only one of BIOL 300, FRST 231,
  STAT 200, PSYC 218 or 366.
• These are paired with BIOL 300, but do not count
  as requirements for Biology majors and pre-reqs

19
Introduction to statistics

• Statistics - technology used to describe and
  measure aspects of nature from samples
• Statistics lets us quantify the uncertainty of
  these measures

20
http//www.pbs.org/wgbh/evolution/library/01/5/ima
ge_pop/l_015_04.html
21
http//www.rit.edu/rhrsbi/GalapagosPages/DarwinFi
nch.html
22
The history of statistics has its roots in biology
23
Sir Francis Galton
Inventor of fingerprints, study of heredity of
quantitative traits Regression
correlation Also efficacy of prayer,
attractiveness as function of distance from
London
24
Karl Pearson
Polymath- Studied genetics Correlation
coefficient c2 test Standard deviation
25
Sir Ronald Fisher
The Genetical Theory of Natural
Selection Founder of population
genetics Analysis of variance likelihood
P-value randomized experiments multiple
regression etc., etc., etc.
26
Goals of statistics

• Estimation
• Infer an unknown quantity of a population using
  sample data
• Hypothesis testing
• Differences among groups
• Relationships among variables

27
Statistics is also about good scientific practice
28
Introductory Puzzle

• How to protect bombers flying over enemy
  territory?
• British Air Ministry - WWII
• Looked at distribution of bullet holes in
  airplanes returning from bombing runs

29
http//digitalroam.typepad.com/digital_roam/2006/0
3/the_hole_story_.html
30
Results

• Where should more armor be added to the
  airplanes?
• Explain your conclusion

31
(No Transcript)
32
(No Transcript)
33
Variable

• A variable is a characteristic measured on
  individuals drawn from a population under study.
• Data are measurements of one or more variables
  made on a collection of individuals.

34
Explanatory and response variables

• We try to predict or explain a response variable
  from an explanatory variable.

35
Mortality on the Titanic, as predicted by sex
36
Populations and samples
37
Populations lt-gt ParametersSamples lt-gt Estimates
38
Nomenclature
39
(No Transcript)
40
Properties of a good sample

• Independent selection of individuals
• Random selection of individuals
• Sufficiently large

41
In a random sample, each member of a population
has an equal and independent chance of being
selected.
42
Bias is a systematic discrepancy between
estimates and the true population characteristic.

43
A sample of convenience is a collection of
individuals that happen to be available at the
time.
44
Sampling error

• The difference between the estimate and average
  value of the estimate

45
Population parameters are constants whereas
estimates are random variables, changing from one
random sample to the next from the same
population.
46
Larger samples on average will have smaller
sampling error
47
Read Chapters 1 2