ARCH 21266126

1
ARCH 2126/6126 BIAN 3010/6510

• Co-ordinator for both these 3-unit honours
  preparation classes-
• Robert Attenborough

2
How these courses link

• They are distinct courses but occupy the same
  time slot on Wednesday am
• ARCH 2126 runs 9am 11am in this lecture room
• BIAN 3010 runs 9 am12 noon (max) see separate
  handout for full details
• ARCH 2126 runs in first 6 weeks, July-August,
  BIAN 3010 after that

3
Techniques in Biological Anthropology

• Two kinds of techniques will be the particular
  focus phylogenetic analysis chronometric
  techniques
• Assessable work may but need not focus on these
  particular techniques

4
Analytical Methods for Anthropology Archaeology

• ARCH 2126/6126
• Session 1a
• Introduction

5
for Anthropology Archaeology

• Basically, though not exclusively, an Honours
  preparation course for the anthropological
  disciplines (incl. arch.)
• How many here intending Honours in ?
  Social/cultural anthropology?? Biological
  anthropology?? Archaeology?
• Anyone else?

6
Analytical Methods

• Analysis in the anthropological disciplines can
  be of many kinds verbal, linguistic,
  intellectual etc.
• For this course, the focus is on analysis through
  the use of numbers
• Lets be blunt statistics
• The textbooks already give this away

7
(No Transcript)
8
Textbooks

• Main textbook Robert Drennan (1996) Statistics
  for Archaeologists a Commonsense Approach.
  Plenum, NY.
• Also recommended Lorena Madrigal (1998)
  Statistics for Anthropology. Cambridge University
  Press.
• Important difference between Drennan Madrigal
  is more in their approach than in their
  discipline or their merit

9
Historically

• Historically, Statistics is no more than State
  Arithmetic It has been used indeed still is
  used to enable rulers to know how far they may
  safely go in picking the pockets of their
  subjects Taxation and military service were
  the earliest fields for the use of Statistics.
  For this reason was the Domesday book compiled.
  M.J. Moroney 1956

10
Various senses of the word

• National statistics as in Australian Bureau of
  Statistics, cf. Moroney
• Statistics is also a branch of the mathematical
  sciences probability
• Statisticians are not necessarily enthusiasts for
  calculation
• Nor do they necessarily always share the same
  opinions on statistics

11
Why should anthropologists archaeologists study
statistics?

• I assume that, for most of you, it is not sheer
  love of it that brings you here
• Anyone taken a statistics course?
• Anyone afraid of statistics or convinced they are
  incapable of it? proudly innumerate?
• Anyone feel statistical analysis is a badge of
  academic respectability rather than a truly
  necessary step in the research process?
• Or that if figures show it, it must be true?

12
So why are numerical analyses so common in our
disciplines?

• After all, we (mostly) became anthropologists/arch
  aeologists out of curiosity excitement about
  human beings, societies, cultures, biology not
  numbers
• Lets accept for the moment that numbers are
  helpful to us will return to the reasons later

13
The purpose of this course

• You could have attended a formal statistics
  course run by a statistician
• Here you do not get a statistician, but you get
  someone more familiar with the uses you have for
  numerical analysis
• I aim for us to break down barriers to
  comprehension, develop confidence competence,
  encourage thought in terms of probability
  quantity, practise a few basic methods of data
  presentation analysis
• We do not become statisticians

14
Assessment two items

• Take-home open-book test week 7
• Results interpretation exerciseweek 8
• Weighting 5050
• For postgrads only, a third item review of
  selected academic paperweek 9 (weighting
  1/31/31/3)

15
Structure of the course

• Six 2-hour sessions (lab not practical)
• These will be better if they are interactive we
  will have a break during them
• Please draw my attention to good/bad uses of
  numerical data that you see in the media or in
  your academic reading
• Self-paced STEPS tutorials
• Adjunct ILP Excel SPSS sessions

16
A little history the role of computers

• Classical statistical theory and many of the
  tests in common use to this day were developed in
  the 1920s 1930s
• Choices made then were guided in part by need to
  keep calculations within feasible tolerable
  limits
• Since then especially since 1970s computers
  have become able to do massive amounts of tedious
  arithmetic

17
Hands on

• This growth in computing power has implications
  for us at several levels
• Practical statistics no longer involves facility
  with calculation rather, ability to use
  computers to run packages
• We have a laboratory at our disposal AD Hope
  LG29, with 3 computers we have priority use of
  it for self-paced work throughout Wednesdays

18
Analytical Methods for Anthropology Archaeology

• ARCH 2126/6126
• Session 1b
• Variation

19
Gathering data in the anthropological disciplines

• Empirical research in any of these disciplines
  involves data gathering at times though in very
  different styles
• A socio-cultural anthropologist may collect a
  myth or a genealogy, observe a conversation or a
  ceremony, interview an informant, map and census
  a village or suburb

20
And

• An archaeologist may photograph or survey a site,
  draw a section, reconstruct a pot or a stone
  artefact, sieve soil, collect pollen or
  phytoliths, interview a traditional land owner,
  make qualitative descriptions of sites
• Even a biological anthropologist may categorise
  blood or fingerprints
• Thus not all data are quantitative

21
But quantitative or not, the essence is variation

• Almost always empirical research describes
  attributes of a society or culture, a site or
  artefact, an individual or population, which vary
  (or might vary) this is intrinsic to our
  interest
• Single entities may vary within a set sets of
  entities may differ on average
• How to capture this variation?

22
Characterizing variation

• Where variation is described in words or images,
  analysis may be likewise verbal or visual, and
  relatively informal
• But even where entities are simply categorized,
  they can be counted
• And where they are measured, the methods
  available for summarizing variation are
  inherently quantitative

23
The analytical methods we shall focus on are
numerical

• Why? The world is complex there are few
  absolutes in the biological and social sciences
  we need to be able to detect trends, patterns,
  relationships (e.g. smoking cancer) which may
  not be simple or obvious, may have
  counter-examples this is where good statistics
  can help
• So the discipline of statistics

24
The purpose of statistics

• To provide insight into situations and problems
  by means of numbers
• How is this provided?
• Numerical data are available or are collected
• Data are organized, summarized, analysed and
  results presented
• Conclusions are drawn, in context
• Whole process is often guided by critical
  appraisal of similar work already done

25
Data, variables and values

• What are data? (Singular datum Plural data)
• Givens fixed points which constrain possible
  interpretations
• Variation can be more formally seen in terms of
  variables e.g. stature
• In a particular case, the variable attains a
  particular value, e.g. stature of a particular
  person may be 178 cm

26
Kinds of variables

• Variables that can be analysed numerically are of
  several different sorts
• Categorical/qualitative/nominal variables
• Ranked/ordered/ordinal variables
• Numerical/quantitative/metric variables
• Different kinds of variables allow different
  kinds of numerical analysis
• This applies to the method of description or
  measurement, not the basic property

27
Categorical/qualitative/nominal

• E.g. female/male, A/B/AB/O blood groups, marital
  or employment status, artefact types
• You can assign code numbers to these values if it
  helps you to do so e.g. in SPSS you might code
  female as 1, male as 2, missing data as 9
• But in that case it is arbitrary what numbers you
  assign, you could have assigned reversed or
  different ones, and there is no implication of a
  mathematical relationship between the values
• You might summarize by reporting the modal (most
  common) category there is no average
• All cases should normally be placed in one and
  only one category

28
Ranked/ordered/ordinal

• Any numbers assigned indicate an ordered
  relationship between the values, but not
  necessarily any more than that
• E.g. many sociological psychological
  questionnaires have an ordered range of answers
  primatologists infer dominance amongst monkeys
  these can be coded the codes indicate relative
  rank only
• Results can be reported as modes or as medians
  (middle values of a distribution)

29
Numerical/quantitative/metric

• The case most familiar to scientists, where
  numbers have a true mathematical meaning the
  variable varies along an ordered scale of equal
  units 3 is as far from 4 as 4 is from 5
• E.g. the weight of a person, the length of a
  stone artefact, the volume of a pottery vessel,
  the area of a village
• It is meaningful to calculate a mean (average) as
  well as a median or mode

30
Numerical variables may have either interval or
ratio scales

• Both have an ordered scale of equal units
• Interval scales have equal units but do not make
  multiplicative sense or have a mathematically
  meaningful zero, e.g. ºC
• Ratio scales make multiplicative sense, e.g. a 66
  kg person is twice as heavy as a 33 kg person
  and zero is meaningful
• We shall generally not need to distinguish
  between interval and ratio subtypes of numerical
  variables

31
Numerical variables may be continuous or
discontinuous

• Continuous variables are in principle infinite
  and values may fall anywhere along the scale,
  between as well as on integers e.g. weights,
  volumes, areas, angles, linear measurements
• Discontinuous variables are essentially counts
  can only be integers e.g. no. of household
  members, fingerprint ridge counts, no. of teeth
  in a mandible or artefacts in a spit
• Means can be calculated for either

32
More terminology about variables

• Frequency of any value of a variable is the
  number of times that value is found i.e. it is a
  count, an absolute number
• Relative frequency of any value is its frequency,
  expressed as a proportion of all observations
  (often a percent)

33
More terminology about variables

• Ratio the size of a number relative to another
  number
• Proportion a ratio in which the second number
  includes the first
• Percentage a proportion multiplied by 100
• Rate a ratio of the number of events to the
  number of cases at risk of experiencing that event

34
Data sets

• Usually data do not come singly they come in,
  or are collected in, sets
• We collect them because we want to test some idea
  against them
• E.g. we might want to test whether the stone
  artefacts from one site differ in size from stone
  artefacts from another
• For this, we measure artefact sizes
  systematically consistently

35
Examples of presentation

• Even the simplest forms of stating findings
  percentages, averages and the simplest
  graphical presentations emphasize selected
  aspects
• This can be legitimate can also be misleading
  much depends on honesty clarity with which
  procedure is described
• What as a percentage of what?
• Does the graph have linear scales? A zero?
• Please bring in examples yourselves