Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

multivariate analysis > basic stuff > Flashcards

basic stuff Flashcards

1
Q

Direct, long gradient

A

CCA

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Direct, short gradient

A

RDA

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Constrained

A

CCA and RDA

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

unconstrained

A

CA and PCA, distance based approaches (mds and polar)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Indirect, long gradient

A

CA

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Indirect, short gradient

A

PCA

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Parametric (linear) distance based approach

A

Classical MDS

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Non-parametric (ranks) distance based approach

A

nonmetric MDS

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

when do you add environmental data afterwards?

A

indirect ordination

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

long gradient response?

A

unimodal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

short gradient response?

A

linear

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What do Log (1+x) and sqrt(x) transformations do?

A

Reduce the influence of large values

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What does the Hellinger transformation do?

A

computing sqrt of relative abundances per location

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What does the Wisconsin transformation do?

A

‘double standardization’: first computing relative
abundances per location, then normalizing values to max
value=1 per species

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

which distances are symmetric?

A

Manhattan and Euclidian

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

which distances are asymmetric?

A

chi-squared and Bray-Curtis

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

what is inertia for CCA/CA

A

Chi-square

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

what is inertia for RDA/PCA

A

Variance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

what distance is CA based on?

A

Chi-squared distance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

what is the average MDS by design?

A

0

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

when is stress level acceptable?

A

<0.05 is excellent, <0.1 is great, <0.2 is good/ok, <0.3 is poor

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

how are distances mapped in Non parametric MDS?

A

The ranks are mapped

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

is non paramteric MDS the same result every time you try?

A

No, it’s iterative (each run may have different results)

24
Q

how to check the quality of NMDS?

A

Inspecting stress value, Shepard diagram

25
Q

how to choose how many dimensions for NDMS?

A

The least amount of dimensions where the stress is still below 0.1 (more dimensions reduce stress but you want the least amount of dimensions)

26
Q

how to choose how many axis for PCA?

A

scree plot with broken stick method

27
Q

what is the total inertia for CA?

A

Average chi-squared distance among all sites, or sum of all eigenvalues

28
Q

what do eigenvalues represent for CA?

A

the chi-square value per axis

29
Q

what distance is PCA based on?

A

Linear species response based on Euclidian distance

30
Q

when is a gradient long or short?

A

first axis of a DCA (detrended) is 3 or <3 it is short. Also if there are many zeroes it is most likely long, and most species in most sites means short.

31
Q

how to know in output if a test was constrained (CCA/RDA) or not (CA/PCA)?

A

if output does not say ‘constrained’ it is unconstrained

32
Q

how to calculate proportion explained by an axis?

A

eigenvalue of axis / total inertia

33
Q

in a significance test for constrained ordination, what refers to restrained and unrestrained part?

A

residual= unrestrained. Model = restrained

34
Q

when is inertia chi-square?

A

for CA/CCA

35
Q

when is inertia variance?

A

PCA/RDA

36
Q

what is total inertia for PCA?

A

sum of the eigenvalues of all axes, or sum of all variance (since inertia = variance)

37
Q

what does it mean when the outcome of an unconstrained and constrained analysis are very different?

A

the enviornmental variables do not explain the variance well

38
Q

when can you use multivariate analysis

A

for anything that has multi-response data that allowes calculating dissimilarities

39
Q

in an constrained output how many axes are used?

A

the constrained + unconstrained ranks. constrained = amount of environmental variables

40
Q

when do you have to check for colinearity of explanatory variables?

A

with CCA and RDA because they are regression methods

41
Q

when is collinearity a problem?

A

vif >5 potentially, >10 definitetly

42
Q

what is conditioning?

A

removing the effect of gradients in a landscape for further testing

43
Q

what are canonical axes?

A

constrained axes

44
Q

what is a marginal effect?

A

the effect of a particular term when all other model terms are included in the model

45
Q

how are marginal terms tested?

A

by eliminating each term from the model containing all other terms

46
Q

are marginated effects dependent on order of the terms?

A

no, but correlated terms will get high P values

47
Q

does the order matter when testing terms?

A

yes, if there is correlation

48
Q

what is the P value in a permutation test?

A

the fraction of permutation values that are larger than the actual value

49
Q

how is p value calculated in permutation test?

A

the number of values that are higher than the actual value, divided by (the amount of permutations + 1)

50
Q

in an unconstrained ordination do the eigenvalues increase or decrease over the axes?

A

decrease

51
Q

when do you use chi-square distance

A

when long gradient and rare species are well sampled

52
Q

when do you use Euclidian or mannhattan distance

A

when there’s a short gradient

53
Q

when do you use bray-curtis disctance

A

long gradient and rare species not well sampled

54
Q

what to be careful of with Manhattan/euclidian distance?

A

Scaling, double zeroes, abundance paradox

55
Q

what to be careful of with Bray curtis distance?

A

Large values

56
Q

what to be careful of with Chi square distance?

A

rare species (that aren’t sampled well), distance between two sites is influenced by other sites

multivariate analysis (1 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions