geography f764 - skills

HideShow resource information

Methods of Sampling

SAMPLING FRAME 

SPATIAL - where that location will be (river study)

NON SPATIAL - who to ask (questionnaire)

METHODS 

  • Random 
  • Stratified 
  • Systematic 
  • Pragmatic 
1 of 39

1. Random

DESCRIPTION 

  • random number tables to select sample point with every idividual variable having equal chance of being picked 

ADVANTAGES 

  • stat. tests 
  • no bias 

DISADVANTAGES 

  • may not be representative of total statistical population (miss points)
  • takes a long time 
2 of 39

2. Stratified

DESCRIPTION 

  • underlying subdivisions in total stat. population are taken into account 
  • propotinally sampled 

ADVANTAGES 

  • no points missed or overepresented 

DISADVANTAGES 

  • possible bias - invalidate inferences made from statistical tests 
  • possibly no stat test 
  • need to get info of underlying patterns
  • groups under / over represented in proportional sampling  
3 of 39

3. Systematic

DESCRIPTION 

  • points are selected at regular intervals 
  • spatial (where) + non-spatial (who)

ADVANTAGES 

  • easy and quick 
  • allows even coverage to test hypothesis 

DISADVANTAGES 

  • bias 
  • interval may coincide with data / location 
  • possibly no stat 
  • missed vatiations + regularities not typical 
4 of 39

4. Pragmatic

DESCRIPTION 

  • where you can get access to 
  • and where changes can be observed 

ADVANTAGES 

  • realistic 
  • risk assessment based

DISADVANTAGES 

  • bias 
  • possibly no stat test 
5 of 39

Units of Sampling

Point

  • number of individual points  

Grid 

  • Quadrat used at indivial points 

Line 

  • transect - measurements along a line 

Belt transect 

  • wider transect 
6 of 39

Accuracy

DESCRIPTION 

  • level at which data is exact and free from error 

ERRORS

measurement error -

  • repeating increases room for error 

operator error -

  • idividual / equipment / climatic 
7 of 39

Reliability

DESCRIPTION

  • extent to which sample data reflect the greater whole statistical population 

ERRORS

sampling- 

  • inappropriate sampling frame 
  • small sample size 
8 of 39

Risk assessment

IDENTIFY RISK 

EVALUATE SEVERITY (1-5)

CONTROL MEASURES

RE-EVALUATE SEVERITY (is it acceptable with control?)

9 of 39

Pilot study

DESCRIPTION 

  • a small scale preliminary study used to evaluate successes / weaknesses and improvements to study design prior to performance of a full scale research project 

ADVANTAGES 

  • identify improvements 
  • if given time is acheivable 
  • if location is appropriate 
  • effectivenesss of sample method - representative, accurate, reliable 
  • risk assessment 
  • equipment effectiveness

DISADVANTAGES 

  • takes time 
10 of 39

Techniques of Presenting

TRENDS to be represented 

SPATIAL - patterns between areas 

TEMPORAL - patterns overtime 

TECHNIQUES 

  • maps (QUAL/QUANT)
  • graphs (QUANT)
  • diagrams (QUAL/QUANT)
  • annotated field sketches / photos (QUAL)
11 of 39

Maps (spatial)

1. Chloropleth 

2. Dot 

3. Proportional Symbols 

4. Isoline / Isopleth 

5. Flow line 

12 of 39

1. Chloropleth Maps

DESCRIPTION 

  • ratio values expressed as densities or percentages 
  • use of area 

METHOD 

  • standardized values (%)
  • divide into classes 
  • class sizes (fixed / mathematical calc / dispersion in data)
  • colour shading system 
  • title, key, scale, direction

ADVANTAGES 

  • easy + useful for area census data / good visual patterns 

DISADVANTAGES 

  • conceal variations in areas / abrupt changes at bounday / large units dominate / broad boundaries 
13 of 39

2. Dot Maps

DESCRIPTION 

  • ratio data 
  • areas

METHODS 

  • find base map with boundaries 
  • decide on dot value (represent low values) + size (just touch in high density areas)
  • place on maps 
  • key, title, scale, direction 

ADVANTAGES 

  • only one which provides info within wards 
  • visual + spatial patterns + not interupption at area boundaries 
  • statistical ananlysis 

DISADVANTAGES

  • high densities dots merge 
14 of 39

3. Proportional Symbols

DESCRIPTION 

  • ratio data in specific location / or absolute 

METHODS 

  • suitable scale base map 
  • choose symbol + scale 
  • calculate size / area of symbol 
  • plot in central of area 
  • add key, title, scale and direction 

ADVANTAGES 

  • good visual + spatial 
  • data can be recovered and can show whole range of values 

DISADVANTAGES 

  • hard scale to decide upon / larger symbols misread / difficult to place on small maps 
15 of 39

4. Isoline / Isopleth

DESCRIPTION 

  • ratio data
  • uses points 

METHOD 

  • suitable scale base map 
  • decide on number and value of isolines 
  • draw by interpolation 
  • number isolines 
  • add key, title, scale, direction 

ADVANTAGES 

  • clear spatial patterns / shows gradual changes / guess of values between data 

DISADVANTAGES 

  • need a lot of points / assuming constant change / only used if variable changes with space
16 of 39

5. flow line

DESCRIPTION 

  • ratio data 
  • uses lines to show flow paths (routed/ actual pathways or non-routed/ straightlines) 

METHOD 

  • suitable scale where flow lines can be recorded 
  • number of classes + scale of line (width)
  • key, title, scale, direction 

ADVANTAGES 

  • visually shows patterns of movements + quick/easy 
  • can show different variables of direction 

DISADVANTAGES 

  • very generalised + hard to stat. test 
  • carefully chose width scale 
17 of 39

Graphs (non-spatial)

Tables 

Charts 

  • Bar Charts 
  • Divided/Stacked Bar Charts 
  • Pie Charts 
  • Rose/Star Charts 

Graphs 

  • Line Graphs 
  • Scattergraph 
  • Triangular Graphs 
  • Lorenz Curves 
  • Kite Diagrams 
18 of 39

Tables

DESCRIPTION 

  • nominal data (presence or abscence) in form of parish names 
  • interval/numerical data in form of % of arable 
  • freq. distribution - values grouped into numerical values 
  • used to construct histogram 

ADVANTAGES 

  • backbone for then contructing futher presentation techniques 
  • clearly group data into individual classes
  • statistical tests 

DISADVANTAGES 

  • no spatial pattern / visual represenatation 
19 of 39

Bar Charts

DESCRIPTION 

  • interval and discrete data used 
  • quantities to be compared 
  • width constant and legth varies 

ADVANTAGES 

  • visual with temporal/spatial 
  • stat. tested + comparable 

DISADVANTAGES 

  • non-continuous data cant be used 
20 of 39

Stacked/Divided Bar Chart

DESCRIPTION 

  • quatity that can be divided into component parts 
  • absolute values or porportions 

ADVANTAGES 

  • easy to draw / interpret 
  • visual pattern identified 
  • stat. test 

DISADVANTAGES 

  • too many divisions will confuse 
21 of 39

Pie Charts

DESCRIPTION 

  • uses % data 
  • circular chart divided into segments of a whole sample

ADVANTAGES

  • visual and easily comparable 
  • precise % allowing stat. tests

DISADVANTAGES 

  • not always exact % 
  • too many divisions confuse + no temporal change can be shown
  • when comparing, order of division has to be standardised 
22 of 39

Rose/Star Charts

DESCRIPTION 

  • used to show direction 
  • length/width of bars show frequency 

ADVANTAGES 

  • clearly show direction and spatial changes 
  • visual pattern represented 
  • can recover stat. if accurrate + to scale 

DISADVANTAGES 

  • width/length scale hard to produce 
  • may not be able to state exact direction 
23 of 39

Line Graph

DESCRIPTION 

  • variations in absolute or % 
  • X axis independent and Y dependent 
  • X influences Y 

ADVANTAGES 

  • trends, patterns and anomalies highlighted 

DISADVANTAGES 

  • only continuous 
24 of 39

Scatter Graph

DESCRIPTION 

  • show an overall trend, not just a line of points 
  • simplest way of looking at relationship betweek 2 variables 
  • first stage in stat analysis 
  • closer points in straight line = stronger relationship 

ADVANTAGES 

  • correlation suggested (line of best fit) 
  • spearman's rank 
  • spread of values 
  • anomalies 

DISADVANTAGES 

  • few points can skew data 
  • too many confuse 
  • only between 2 variables 
25 of 39

Triangular Graph

DESCRIPTION 

  • visually represents 3 variables 
  • must add up to 100% on each side of equilateral triangle 
  • spatial and temporal

ADVANTAGES 

  • 3 variables can be visually compared 

DISADVANTAGES 

  • only % 
  • can be difficult to read 
  • can be difficult to construct 
26 of 39

Lorenz Curve

DESCRIPTION 

  • line graphs that show inequalities in distribution of a phenomena 
  • cumulative frequency curves 
  • striaght line shows even distribution 
  • Lorenz curve shows actual distribution and how much it deviated from even 
  • more concave = greater inequality 
  • 'gini' coeffiecient calculated to show degree of inequality 

ADVANTAGES

  • viual patterns identified 
  • plot more than 1 distribution 
  • gini coefficient calculated 

DISADVANTAGES 

  • time conuming to calculate cumulative freq. 
  • no exact quantative measure of degree of inequality 
27 of 39

Kite Diagram

DESCRIPTION 

  • shows how a phenomena's occurence changes over distance 
  • e.g bradshaw's model 

ADVANTAGES 

  • visually effective 
  • recove stat. tests 
  • relative phenomena compared 

DISADVANTAGES 

  • only show % change, not absolute values (Bradshaw - no values) 
28 of 39

Sketch Map

DESCRIPTION 

  • box to keep in area sketching 
  • add only essential infromation (locational reference points)
  • add an approximate scale 
  • add title and orientation 

ADVANTAGES 

  • simple and easy to interpret 

DISADVANTAGES 

  • to be effective needs scale, key, labels, direction 
29 of 39

comparing maps and photos

MAPS 

  • plan view indicating scale + direction 
  • shows what exists in area (characteristics / economic activity ...)
  • flexible scales 
  • GIS - shows layering 
  • sometimes dated - doesnt show present 
  • shows scales + spatial data 

PHOTOS 

  • aerial, oblique, ground level, satellite views 
  • capture at instant in time 
  • shows what is there at that time 
  • shows variety of data - colours, veg... 
30 of 39

GIS (geographical information system)

AEGIS 3 software used in connect with pilot study 

  • data stored, organised, combined with other data and then displayed 

ADVANTAGES 

  • cope with large amount of data 
  • cope with large variety 
  • easily change scale 
  • dynamic - cope with change 
  • allows spatial data to be investigated to show patterns / trends 
  • information tied to places 

USES 

1. collecting / recording data - (primary / weather  + secondary / census data) 

2. presenting data - (area / line / point / symbols / colours / overlayed / compared) 

3. analysing / interpreting - (investigate + answer questions)

31 of 39

Types of data

PRIMARY 

  • unprocessed 
  • not analysed or interpreted 
  • geogrpaher has direct control 

SECONDARY 

  • dervived from published documents that has been anlysed/ interpreted 
  • includes processed census data, research papers, published maps, textbooks

QUALITY 

Nominallowest quality (0 or 1) / only stat tests are Mode + Chi Squared 

Ordinal - rank ordering / only stat tests are Spearman's rank, median, percentiles 

Interval - discrete scale + allows magnitude / stat tests include mean, SD, Spearmans, regression

32 of 39

Stat. tests 1.

Mean - includes anomalous data 

Median 

Mode 

Standard deviation - measures central tendancy around mean 

Kurtosis - the taller/steeper the curve the lower the standard deviation 

Distribution - normal (bell shaped curve) +Ve skew (mean greater than mode) -Ve skew (mode greater than mean)

33 of 39

Stat. tests 2 - Spearman's

Spearman's Rank Correlation Coefficient 

DESCRIPTION 

  • doesnt have to be normally distributed data 

POSITIVES 

  • easy and simple 
  • doesnt have to be normally distributed (test other variables)

NEGATIVES

  • a poor statistical test 
  • no magnitude 
  • no explanation for causes of strength of relationship 

 

34 of 39

Spearman's significance testing

DESCRIPTION 

  • degree of freedom (N-2)
  • standard significance level 0.05 (95%)

ADVANTAGES

  • can say whether results are respresentative of total stat. population 
  • whether they are significant 
  • reduces problem of BIAS / due to CHANCE 
  • whether we can be 95% sure of this 
35 of 39

hypothesis

NULL H1

  • relationship found in sample is not representative of total stat. population 
  • testing for no relationship

ALTERNATIVE 

  • relationship in sample does accurately reflect total statistical population 
36 of 39

Stat. tests 3 - Pearson's

Pearson's product moment correlation coefficient 

DESCRIPTION 

  • have to have each individual point normally distributed 

ADVANTAGES

  • statistically better
  • more specific 
  • gives magnitude 

DISADVANTAGES

  • can only use normally distributed interval data 
  • harder to construct 
  • doesnt give reason for relationship 
37 of 39

Stat. tests 4 - Chi squared

DESCRIPTION (e.g. corrie orientation)

  • observe differences between comparable sets of data (manufacture set from averages)
  • null hypothesis put forward - random distibution 
  • data collected so can be grouped into classes
  • compare to significance test to confirm whether any deviation from random in observed data is by chance 
  • if > critical value then we can reject the null hypothesis 

 

38 of 39

Stat. tests 5 - nearest neighbour analysis

DESCRIPTION 

  • allows us to statistically describe the distribution of settlements 
  • use 'central place theory' to test this 
  • whether they are clustered / random / regular 

0 = CLUSTERED (H1)

1 = RANDOM (H0)

2.15 = REGULAR (H1)

  • can be due to many different factors 
  • e.g settlement distributions 
  • whether you measure as crow flies or along roads 
  • SERVICES affect location 
39 of 39

Comments

No comments have yet been made

Similar Geography resources:

See all Geography resources »See all Geographical skills and fieldwork resources »