Download presentation

Presentation is loading. Please wait.

Published byDevan Perrow Modified over 3 years ago

1
The challenge of statistically identifying species-resource relationships on an uncooperative landscape Or… Facts, true facts, and statistics: a lesson in numeracy Barry D. Smith & Kathy Martin Canadian Wildlife Service, Pacific Wildlife Research Centre Delta, B.C., Canada Delta, B.C., Canada Clive Goodinson Vancouver, B.C., Canada Free Agent,Vancouver, B.C., Canada

2
Species-Habitat Associations += Objective: To incorporate habitat suitability predictions into a stand-level forest ecosystem model

3
Can we show statistically that the relative quantity of a resource on the landscape predicts the presence of a species such as Northern Flicker?

4
0 1 01 Predicted Observed Logistic regression model output 12316 974 01 Predicted

5
Observed Groups and Predicted Probabilities 20 + 1 + I 1 I F I 1 1 I R 15 + 1 1 + E I 1 1 1 1 I Q I 1 1 1 111 1 1 I U I 11 11 11 111 1 11 I E 10 + 1 11111 11 11111 11 1 + N I 1 1 10111101 11111111 1 I C I 011110011001110101111 1 1 I Y I 01110000100111000111111 1 I 5 + 00 001100000000110000001111111 11 + I 001000100000000000000001111101 1 11 I I 0 00000000000000000000000010001000110 11 I I 0 1 000000000000000000000000001000000000011011 11 1 I Predicted --------------+--------------+--------------+--------------- Prob: 0.25.5.75 1 Group: 000000000000000000000000000000111111111111111111111111111111 Logistic regression model 0 = Absent1 = Present

6
Sampling intensity is too low; birds occur within good habitat but sampling does not capture all occurrences. Habitat is not 100% saturated; there are areas of good habitat which are unoccupied. Habitat is over 100% saturated; birds occur in areas of poor habitat. 0 1 01 Predicted Observed Spatial variability is too low or spatial periodicity of key habitat attributes is too high, given sampling intensity. The playback tape pulls in individuals from outside the point-count radius.

7
So, can we expect be successful in detecting species-habitat associations when they exist? We use simulations where: we generated a landscape, then we generated a landscape, then populated that landscape with a (territorial) species, then populated that landscape with a (territorial) species, then sampled the species and landscape repeatedly to assess our ability to detect a known association sampled the species and landscape repeatedly to assess our ability to detect a known association

8
Sample Simulation > Sample Sim’on

9
To be as realistic as possible we need to make decisions concerning… The characteristics of the landscape (resources)The characteristics of the landscape (resources) The species’ distribution on thelandscapeThe species’ distribution on thelandscape The sampling method The sampling method The statistical model(s) The statistical model(s)

10
Spatial contrast is essential for, but doesn’t guarantee, success

11
High Landscape Spatial Periodicity (SP)

12
Medium Landscape Spatial Periodicity (SP)

13
Low Landscape Spatial Periodicity (SP)

14
It might help to conceptualize required resources by consolidating them into four fundamental suites: Shelter (e.g., sleeping, breeding) Shelter (e.g., sleeping, breeding) Food (self, provisioning) Food (self, provisioning) Comfort (e.g. weather, temperature) Comfort (e.g. weather, temperature) Safety (predation risk) Safety (predation risk)

15
To be as realistic as possible we had to make decisions concerning: The characteristics of the landscapeThe characteristics of the landscape The species’ distribution on thelandscapeThe species’ distribution on thelandscape The sampling method The sampling method The statistical model(s) The statistical model(s)

16
Territory establishment can be… Resource centred Species centred …but in either case sufficient resources must be accumulated for an individual to establish a territory

17
If territory establishment is… Species centred …then the ‘Position function” sets the parameters for territory establishment

18
Territory establishment Saturation Half-saturation

19
Territory densities may be… Low …so realistic simulations must be calibrated to the real world High

20
To be as realistic as possible we had to make decisions concerning: The characteristics of the landscapeThe characteristics of the landscape The species’ distribution on thelandscapeThe species’ distribution on thelandscape The sampling method The sampling method The statistical model(s) The statistical model(s)

22
Detection Function Point-count radius Vegetation plot radius

23
To be as realistic as possible we had to make decisions concerning: The characteristics of the landscapeThe characteristics of the landscape The species’ distribution on thelandscapeThe species’ distribution on thelandscape The sampling method The sampling method The statistical model(s) The statistical model(s)

24
The statistical model Deterministic model structureDeterministic model structure Multiple regression, Logistic Model errorModel error Normal, Poisson, Binomial Model selectionModel selection Parsimony (AIC), Bonferroni’s alpha, Statistical significance

25
The deterministic model Multiple regression (with 2 resources)Multiple regression (with 2 resources) Y i = B 0 + B 1 X 1i + B 2 X 2i + B 12 X 1i X 2i + ε i or Y i = f(X) + ε i Y i = detection (0,1,2,…) Xi = resource value

26
The deterministic model Logarithmic:Logarithmic: Y i = e f(X) + ε i Y i = detection (0,1,2,...) Xi = resource value

27
The deterministic model Logistic:Logistic: Y i = Ae f(X) /(1+ e f(X) ) + ε i Y i = detection (0,1,2,…) Xi = resource value

28
Choosing the correct model form

29
Linear model: 1 to 4 resources 1 Resource: Y i = B 0 + B 1 X 1i + ε i 4 Resources: Y i = B 0 + B 1 X 1i + B 2 X 2i + B 3 X 3i + B 4 X 4i + B 12 X 1i X 2i + B 13 X 1i X 3i + B 14 X 1i X 4i + B 23 X 2i X 3i + B 24 X 2i X 4i + B 34 X 3i X 4i + B 23 X 2i X 3i + B 24 X 2i X 4i + B 34 X 3i X 4i + B 123 X 1i X 2i X 3i + B 124 X 1i X 2i X 4i + B 134 X 1i X 3i X 4i + B 234 X 2i X 3i X 4i + B 1234 X 1i X 2i X 3i X 4i + ε i Number of parameters requiredfor… 1 Resource = 2 2 Resource = 4 3 Resource = 8 4 Resource = 16

30
The statistical model Deterministic model structureDeterministic model structure Multiple regression, Logistic Model errorModel error Normal, Poisson, Binomial Model selectionModel selection Parsimony (AIC), Bonferroni’s alpha, Statistical significance

31
Poisson error Repeated samples of individuals randomly dispersed are Poisson- distributed

32
Poisson error

33
Negative-binomial error

34
Normal error

35
Binomial error

36
The statistical model Deterministic model structureDeterministic model structure Multiple regression, Logistic Model errorModel error Normal, Poisson, Binomial Model selectionModel selection Parsimony (AIC), Bonferroni’s alpha, Statistical significance

37
Model Selection Use AIC to judge the best of several trial modelsUse AIC to judge the best of several trial models The ‘best’ model must be statistically significant from the ‘null’ model to be acceptedThe ‘best’ model must be statistically significant from the ‘null’ model to be accepted If =0.05, then Bonferroni’s adjusted is: 1 Resource = 0.0500 2 Resource =.0169 3 Resource = 0.0073 4 Resource = 0.0034

38
True, Valid and Misleading Models If the ‘True’ model is: Y i = B 0 + B 123 X 1i X 2i X 3iIf the ‘True’ model is: Y i = B 0 + B 123 X 1i X 2i X 3i Then:Then: Y i = B 0 + B 3 X 3i is a ‘Valid’ modelY i = B 0 + B 3 X 3i is a ‘Valid’ model Y i = B 0 + B 12 X 1i X 2i is a ‘Valid’ modelY i = B 0 + B 12 X 1i X 2i is a ‘Valid’ model Y i = B 0 + B 4 X 4i is a ‘Misleading’ modelY i = B 0 + B 4 X 4i is a ‘Misleading’ model Y i = B 0 + B 14 X 1i X 4i is a ‘Misleading’ modelY i = B 0 + B 14 X 1i X 4i is a ‘Misleading’ model

39
1 Resource Required - 1 Resource Queried Logistic-Poisson Multiple Regression - Normal Success identifying ‘True’ Model

40
1 Resource Required - 1 Resource Queried Logistic-PoissonLogistic-Binomial Success identifying ‘True’ Model

41
4 Resources Required - 4 Resources Queried TrueValid Medium SP - Resources uncorrelated – 100% detection - Full Misleading

42
4 Resources Required - 4 Resources Queried TrueValid High SP - Resources uncorrelated – 100% detection - Full Misleading

43
4 Resources Required - 4 Resources Queried TrueValidMisleading Low SP - Resources uncorrelated – 100% detection - Full

44
1 Resources Required - 4 Resources Queried True / Valid Misleading Medium SP - Resources uncorrelated – 100% detection - Full

45
1 Resources Required - 4 Resources Queried Misleading High SP - Resources uncorrelated – 100% detection - Full True / Valid

46
1 Resources Required - 4 Resources Queried Misleading Low SP - Resources uncorrelated – 100% detection - Full True / Valid

47
1 Resources Required - 4 Resources Queried Misleading Medium SP - Resources 50% correlated – 100% detection - Full True / Valid

48
1 Resources Required - 4 Resources Queried Misleading Medium SP - Resources 50% correlated – 25% detection - Full True / Valid

49
1 Resources Required - 4 Resources Queried Misleading Medium SP - Resources 50% correlated - 25% detection - 50% Full True / Valid

50
1 Resources Required - 4 Resources Queried Misleading High SP - Resources 50% correlated – 25% detection – 50% Full True / Valid

51
1 Resources Required - 4 Resources Queried Misleading Medium SP - Resources 95% correlated – 25% detection - Full True / Valid

52
Technical Conclusions A-priori hypotheses concerning species-habitat associations are essential Required resources should be amalgamated by suite Resource contrast is essential and should be planned: Ratio of ‘between-point:within-point’ variability must be increased for both resources and species-of-interest Point-count method must be designed with spatial period considerations in mind

53
At best: Affirmative conclusions about the importance of ‘critical resources’ based on statistical correlations alone are not justified! Key Conservation Conclusion At worst: Affirmative conclusions about the importance of ‘critical resources’ based on statistical correlations alone, and without documenting the spatial characteristics of the landscape etc., are completely indefensible!

Similar presentations

OK

On Comparing Classifiers : Pitfalls to Avoid and Recommended Approach

On Comparing Classifiers : Pitfalls to Avoid and Recommended Approach

© 2018 SlidePlayer.com Inc.

All rights reserved.

To make this website work, we log user data and share it with processors. To use this website, you must agree to our Privacy Policy, including cookie policy.

Ads by Google

Ppt on central limit theorem for dummies Ppt on polynomials in maths games Ppt on biodegradable and non biodegradable bins Ppt on microsoft sharepoint 2010 Ppt on channels of distribution definition Ppt on bookkeeping and accounting Full ppt on electron beam machining Ppt on algebraic expressions and identities for class 8 Download ppt on nationalism in indochina Ppt on power system harmonics calculation