The Dictionary of Human Geography

Comp. by: VPugazhenthi Stage : Revises1 ChapterID: 9781405132879_4_S Date:1/4/
09 Time:15:23:35 Filepath:H:/00_Blackwell/00_3B2/Gregory-9781405132879/appln/3B2/
revises/9781405132879_4_S.3d

by setting demanding probability levels in

confirmatory data analysis. Type II errors

• that is, having insufficient information to be
  able to detect a genuine effect – are managed
  by conducting a power analysis during the
  design phase. Conversely, collecting too much
  information is not only wasteful of resources
  but can be seen as an unethical intrusion.
  Statistical power is increased when there is
  little ‘noise’ in the system; the effect is sub-
  stantial when probability levels are set leni-
  ently and when the sample size is large, and
  according to which statistical test is used
  (parametric procedures being more powerful).
  Consequently, researchers should choose
  settings/contexts that maximize the ‘signal’ and
  not as in a study of the effect of size of house
  on price, sample areas where all the properties
  are three-bedroomed ones. Power formulas
  and software (such as GPower) are available
  but require an estimate of the size of the effect.
  Cohen (1988) has defined small, medium and
  large effects as the ratio of an effect to variation
  for a very large range of statistical procedures
  (e.g. at-test in a multipleregressionmodel).
  Thus, to be able to detect asmalldifference
  of 0.25 of a standard deviation between two
  sample means with 80 per cent power and 5
  per cent significance (both these percentages
  being the most commonly used conventions)
  requires 2253 observations in the total
  sample; while to be able to detect alargedif-
  ference of 1.0 standard deviation requires only
  2 *17 observations. Unfortunately, academic
  research has paid too little attention to statis-
  tical power with, for example, Sedlmeier and
  Gigerenzer (1989) finding that even in a
  reputed journal statistical power hovered around
  50 per cent. If all these studies were replicated,
  only half would result in an identifiable effect.
  The problem is actually even more widespread
  due to the use of non-probabilistic samples.
  The way forward is to use simulationto
  judge effectiveness and efficiency, as pioneered
  by Snijders (1992) for snowball sampling.
  Indeed, simulation is a general strategy that
  permits great flexibility, not only allowing the
  assessment of power as sample size increases
  but also catering for missing data, non-
  linearity, unequal variances and other specifi-
  cations of an underlying model. kj

Suggested reading

Barnett (2002); Dixon and Leach (1977); Kish

(1995); Lenth (2001); Sudman (1976). G*Power

for power calculations is available from http://

http://www.psycho.uni-duesseldorf.de/aap/projects/

gpower/index.html

satisficing behaviour Behaviour that meets

an actor’s minimum criteria for success. The

concept was developed by Herbert Simon

(1916–2001: see Simon, 1956) as an alterna-

tive to the presumed optimization of

rational choice theory, in which actors

always seek to make the best-possible choice

• for example, to maximize profits. Satisficing
  behaviour may be appropriate either when it is
  impossible to calculate the maximal outcome
  or when actors are unprepared to make the
  investment necessary to identify and/or pursue
  that outcome (as argued by Pred, 1967, 1969).
  Actors will then set their own criteria that will
  represent a satisfactory return on their invest-
  ment. (See alsobehavioural geography.)rj

Suggested reading

Gigerenzer and Selten (2001).

scale ‘Scale’ has no single definition, and

in recent years has been the object of much

theorizing (Howitt, 2003). The traditional

definition incartographyrefers tomapreso-

lution. All maps represent the world by redu-

cing the size and diversity of its component

spaces for visual display, digitally or on paper.

Cartographic scale expresses the mathematical

relationship between the map and the Earth,

usually denoted as a representative fraction.

For example, the small fraction, 1:500,000,

indicates that one unit of distance on the

map represents 500,000 units of Earth space.

Such a map would show large expanses of

terrain – much more than say, the larger frac-

tion of 1:24,000. Hence the common confu-

sion between large-scale (or large-fraction)

maps that show less space but typically more

detail, andsmall-scalemaps that show more

space, but with less detail. Each type of social

and environmental diversity has its own ‘best

resolution’ in terms of cartographicrepresen-

tation; thus, the choice of cartographic scale

depends on the problem at hand. To visualize

US state variation in the enforcement of envir-

onmental policies, we need the familiar small-

scale map of the country with state borders,

while determining whether point source

pollutionreleased into a river caused down-

stream lymphomas requires a large-scale map.

The second major definition is operational

ormethodological. This is the scale or reso-

lution of data collection, with the familiar cas-

cade from micro (body) to macro (globe).

Tied to this type of scale are various analytical

complexities, including the claims that:

(a) social patterns and processes can be sorted

according to their scale of operation and, as

Gregory / The Dictionary of Human Geography 9781405132879_4_S Final Proof page 664 1.4.2009 3:23pm

SATISFICING BEHAVIOUR