Sampling design

1
Sampling design
2
Representativeness
3
What does a sampling design consist of ?

• The number of samples
• Identify particular samples (geographic
  locations, time points)
• Explanation and justification for the number and
  the positions/timings of the samples

4
Probabilistic vs judgmental sampling design

• Probabilistic sampling designs apply sampling
  theory and involve random selection of sampling
  units.
• Judgmental sampling designs involve the selection
  of sampling units on the basis of expert
  knowledge or professional judgment.

5
(No Transcript)
6
Probabilistic vs judgmental sampling design
7
Sampling designs
8
Example of a Map Showing Random Sampling Locations
9
Stratified sampling

• Prior information about the population is used to
  determine groups (called strata) that are sampled
  independently.
• Each possible sampling unit or population member
  belongs to exactly one stratum.

10
(No Transcript)
11
Systematic/grid sampling
Temporal (periodic) design
12
Map of an Area to Be Sampled Using a Triangular
Sampling Grid
13
Ranked set sampling

• it combines simple random sampling with the field
  investigators professional knowledge and
  judgment to pick places to collect samples.

14
Ranked set sampling

• Use simple random sampling to randomly select 9
  locations on the property. Randomly divide the 9
  locations into 3 sets of size 3.
• Consider the 3 locations in Set 1. Make a
  measurement at each of those 3 locations and
  label locations 1, 2, and 3 to indicate the
  smallest, middle, and largest XRF measurement,
  respectively. Collect the first soil sample at
  location label 1 in Set 1 this location has the
  smallest XRF lead measurement in Set 1 (labeled
  1 in Figure)
• Consider the 3 locations in Set 2 and make an XRF
  measurement at each of those locations. Collect
  the second soil sample at label 2 in Set 2 this
  location has the second highest XRF measurement
  in Set 2 (labeled 2 in Figure).
• Consider the three locations in Set 3 and make an
  XRF measurement at each of the three locations in
  that set. Collect the third soil sample at label
  3 in Set 3 this location has the highest XRF
  measurement in Set 3 (labeled 3 in Figure).

15
Adaptive cluster sampling

• n samples are taken using simple random sampling,
  and additional samples are taken at locations
  where measurements exceed some threshold value.

16
(No Transcript)