Difference between revisions of "An initial path towards statistical analysis"

From Sustainability Methods
Line 37: Line 37:
  
 
==Categorical and continuous data==
 
==Categorical and continuous data==
<imagemap>Image:Statistics Flowchart - Categorical factor levels.png|650px|center|
+
<imagemap>Image:Statistics flowchart - Categorical factor levels.png|650px|center|
poly 320 376 -4 712 332 1000 632 700 632 700 [[https://sustainabilitymethods.org/index.php/An_initial_path_towards_statistical_analysis#One_or_two_factor_levels|One or two factor levels]]
+
poly 320 376 0 712 332 1000 632 700 632 700 [[An_initial_path_towards_statistical_analysis#One_or_two_factor_levels|One or two factor levels]]
poly 1064 372 736 696 1076 996 1376 696 [[https://sustainabilitymethods.org/index.php/An_initial_path_towards_statistical_analysis#More_than_two_factor_levels|More than two factor levels]]
+
poly 1064 372 736 696 1076 996 1376 696 [[An_initial_path_towards_statistical_analysis#More_than_two_factor_levels|More than two factor levels]]
 
</imagemap>
 
</imagemap>
  

Revision as of 08:11, 23 March 2021

Start here with your data! This is your first question.

Multivariate Statistics Univariate StatisticsStatistics Flowchart - First Step.png
About this image

How do I know?

  • Inspect your data with str or summary. Are there several variables?
  • What does the data show? Does the underlying logic of the data suggest dependencies between the variables?

Example: Inspecting the swiss dataset


Univariate statistics

Not only continuous variables Only continuous variablesStatistics Flowchart - Univariate Statistics.png
About this image

How do I know?

  • Check the entry on Data formats to understand the difference between categorical and numeric variables.
  • Investigate your data using str or summary. integer and numeric data is not categorical, while factorial and character data is.


Categorical variables

Chi Square Test Categorical and continuous dataStatistics Flowchart - Data Formats.png
About this image

How do I know?

  • Investigate your data using str or summary. integer and numeric data is not categorical, while factorial and character data is.


LINK LEFT TO CHI SQUARE TEST R EXAMPLE

Categorical and continuous data

One or two factor levels More than two factor levelsStatistics flowchart - Categorical factor levels.png
About this image

How do I know?

  • R commands: quantile(), str, summary
  • Investigate your categorical dependent variables using...
  • ADD MORE


One or two factor levels

More than two factor levels

t-test

R commands: t.test, t_test Relevant figures:

No, my categorical dependent variables more than 2 factor levels!


Analysis of Variance

R commands: aov, Anova, ezAnova, var.test(), lm
Relevant figures: boxplot()

Is your dependent variable normally distributed?

R commands: ks.test, shapiro.test, hist 

Yes, my dependent variable is normally distributed!
No, my dependent variable is binomial distributed!
No, my dependent variable is Poisson distributed!

Yes, my dependent variable is normally distributed!


Gaussian Anova

R commands: aov, lm
Relevant figures: boxplot


No, my dependent variable is not normally distributed!


Is your dependent variable binomial or Poisson

No, my dependent variable is Poisson distributed!


Dependent variable is count data

R commands: glm,
Relevant figures: plot

No, my dependent variable is binomial distributed!


Dependent variable is 0/1 or proportions

R commands:
Relevant figures:



Type III Anova

R commands: Anova(car)
Relevant figures: boxplot

Dependent variable not normally distributed

Dependent variable is count data

R commands: glm
Relevant figures: plot

Dependent variable is 0/1 or proportions

R commands: glm
Relevant figures:

Are there random factor variables?

Random factors

R commands: glmer, glmmPQL
Relevant figures:

Continuous variables

Non dependent relations?

Correlations

Clear dependent relations

Regression models

Dependent variable normally distributed

Linear Regression

Dependent variable not normally distributed

Generalised linear model

Dependent variable is count data

Dependent variable is 0/1 or proportions

R commands:
Relevant figures:

Yes, I have several continuous variables without clear dependencies!


Multivariate statistics

Statistics Flowchart - Clustering, Networks, Ordination.png
About this image

How do I know?

  • In an Ordination, you arrange your data alongside underlying gradients in the variables to see which variables most strongly define the data points. Check the entry on Ordinations (to be added) to learn more.
  • In a Cluster Analysis, you group your data points according to how similar they are, resulting in a tree structure. Check the entry on Clustering Methods to learn more.
  • In a Network Analysis, you arrange your data in a network structure to understand their connections and the distance between individual data points. Check the entry on Social Network Analysis to learn more.


Data is classified into groups

R commands:
Relevant figures:

Cluster analysis

DIFFERENCE BETWEEN SUPERVISED AND UNSUPERVISED?? DISTINCTION NOT MADE IN THE CLUSTERING ENTRY

Supervised Classification Unsupervised ClassificationStatistics Flowchart - Cluster Analysis.png
About this image

How do I know?


TAKE OUT LINK TO CLUSTERING METHODS ENTRY???

Supervised classification

R commands:
Relevant figures:

Unsupervised classification

R commands:
Relevant figures:

Network analysis

Big problems for later| Big problems for laterStatistics Flowchart - Network Analysis.png
About this image

How do I know?

  • Check your data using the R code ADD CODE

ADD MORE BELOW

Bipartite

If your data has two different kinds of nodes, your network is called a "bipartite" network.

R commands:

  • is_bipartite(graph)
  • make_bipartite_graph(types, edges, directed = FALSE)

Tripartite

R commands:
Relevant figures:

Ordinations

Euclidean distances Jaccard distancesStatistics Flowchart - Ordination.png
About this image

How do I know?

  • Check the entry on Data formats to learn more about the different data formats.
  • Investigate your data using str or summary. Abundance data is marked as FORMATNAME, and continuous data is marked as FORMATNAME.

MAKE THE STUFF BELOW CLEARER

Linear-based ordinations

Linear-based ordinations are... It uses Euclidean distances, which is... R commands:
Relevant figures:

Correspondance analysis

A correspondence analysis is... It uses Jaccard distances, which is... R commands:
Relevant figures:


More than 2 categorical variables


Is your dependent variable normally distributed?
Is your dependent variable not normally distributed?

My data consists only of categorical variables

Does your independent variable contain only 1 or 2 groups?
Does your independent variable contain more than 2 groups?

Does your independent variable contain more than 2 groups?


Is your dependent variable normally distributed?
Is your dependent variable not normally distributed?



Does your independent variable contain more only 1 or 2 groups?



My data consists only of categorical variables


Multivariate statistics



Resterampe

[[At least one continuous and one categorical variable| More than 2 groups Analysis of Variance
Dependent variable normally distributed
INSERT TYPE II
INSERT RANDOM FACTOR
INSERT LMM

Dependent variable not normally distributed

Type III Anova

Dependent variable is count data

Dependent variable is 0/1 or proportions

Random factors