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

From Sustainability Methods
Line 31: Line 31:
 
Relevant figures:  <br>
 
Relevant figures:  <br>
  
 +
Does you categorical dependent variables have 1-2 factor levels?
 +
 +
 +
Does you categorical dependent variables have more than 2 factor levels?
 +
 +
===[[Experiments#Analysis_of_Variance| Analysis of Variance]]<br>===
 +
R commands:  <br>
 +
Relevant figures:  <br>
 +
 +
<div id="Is your dependent variable normally distributed?">The dependent variable is normally distributed</div>
 +
 +
[[Data_distribution#The_normal_distribution|Dependent variable normally distributed]]<br>
 +
====[[Type II Anova|Type II Anova]]<br>====
 +
R commands:  <br>
 +
Relevant figures:  <br>
 +
 +
=====[[Poisson GLM|Dependent variable is count data]]=====
 +
R commands:  <br>
 +
Relevant figures:  <br>
 +
 +
=====[[Binomial GLM|Dependent variable is 0/1 or proportions]]=====
 +
R commands:  <br>
 +
Relevant figures:  <br>
 +
 +
====[[Linear mixed effect models|Random factors]]====
 +
R commands:  <br>
 +
Relevant figures:  <br>
 +
     
 +
[[Data_distribution#Non-normal_distributions|Dependent variable not normally distributed]]
 +
   
 +
====[[Type III Anova|Type III Anova]]====
 +
R commands:  <br>
 +
Relevant figures:  <br>
 +
 +
=====[[Poisson GLM|Dependent variable is count data]]=====
 +
R commands:  <br>
 +
Relevant figures:  <br>
 +
 +
=====[[Binomial GLM|Dependent variable is 0/1 or proportions]]=====
 +
R commands:  <br>
 +
Relevant figures:  <br>
 +
 +
====[[Generalised linear mixed effect models|Random factors]]====
 +
R commands:  <br>
 +
Relevant figures:  <br>
  
 
[[#Continuous variables|No, I have only continuous variables! (?)]] (?)<br>
 
[[#Continuous variables|No, I have only continuous variables! (?)]] (?)<br>
Line 61: Line 106:
 
<div id="Does your independent variable contain more than 2 groups?">Does your independent variable contain more than 2 groups?</div>
 
<div id="Does your independent variable contain more than 2 groups?">Does your independent variable contain more than 2 groups?</div>
  
===[[Experiments#Analysis_of_Variance| Analysis of Variance]]<br>===
+
 
  
 
[[#Is your dependent variable normally distributed?| Is your dependent variable normally distributed?]]<br>
 
[[#Is your dependent variable normally distributed?| Is your dependent variable normally distributed?]]<br>
 
[[#Is your dependent variable not normally distributed?|Is your dependent variable not normally distributed?]]<br>
 
[[#Is your dependent variable not normally distributed?|Is your dependent variable not normally distributed?]]<br>
  
<div id="Is your dependent variable normally distributed?">The dependent variable is normally distributed</div>
 
 
[[Data_distribution#The_normal_distribution|Dependent variable normally distributed]]<br>
 
====[[Type II Anova|Type II Anova]]<br>====
 
 
=====[[Poisson GLM|Dependent variable is count data]]=====
 
 
=====[[Binomial GLM|Dependent variable is 0/1 or proportions]]=====
 
 
====[[Linear mixed effect models|Random factors]]====
 
 
     
 
[[Data_distribution#Non-normal_distributions|Dependent variable not normally distributed]]
 
   
 
====[[Type III Anova|Type III Anova]]====
 
 
=====[[Poisson GLM|Dependent variable is count data]]=====
 
 
=====[[Binomial GLM|Dependent variable is 0/1 or proportions]]=====
 
  
====[[Generalised linear mixed effect models|Random factors]]====
 
  
  

Revision as of 20:55, 18 January 2021


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

Do you have several continuous variables without clear dependencies? (?)
Yes!
No!

R commands:
Relevant figures:

Univariate statistics

Does you data contain at least one categorical variable?
Yes, I have at least one categorical variable! (?) (?)
R commands:
Relevant figures:


Categorical and continuous data

Does your data consist of categorical and continuous variables? R commands:
Relevant figures:

Does your data consist only of categorical variables? R commands:
Relevant figures:

Categorical variables

Chi-Square test R commands:
Relevant figures:

Does you categorical dependent variables have 1-2 factor levels?


Does you categorical dependent variables have more than 2 factor levels?

Analysis of Variance

R commands:
Relevant figures:

The dependent variable is normally distributed

Dependent variable normally distributed

Type II Anova

R commands:
Relevant figures:

Dependent variable is count data

R commands:
Relevant figures:

Dependent variable is 0/1 or proportions

R commands:
Relevant figures:

Random factors

R commands:
Relevant figures:

Dependent variable not normally distributed

Type III Anova

R commands:
Relevant figures:

Dependent variable is count data

R commands:
Relevant figures:

Dependent variable is 0/1 or proportions

R commands:
Relevant figures:

Random factors

R commands:
Relevant figures:

No, I have only continuous variables! (?) (?)
R commands:
Relevant figures:


Multivariate statistics

Yes!





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?

t-test

My data consists only of categorical variables

Chi-Square test

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



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