cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Try the Materials Informatics Toolkit, which is designed to easily handle SMILES data. This and other helpful add-ins are available in the JMP® Marketplace
%3CLINGO-SUB%20id%3D%22lingo-sub-666094%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3EC%C3%B3mo%20comparar%20varios%20conjuntos%20de%20datos%20modelados%20por%20modelos%20log%C3%ADsticos%20de%203%20par%C3%A1metros%3C%2FLINGO-SUB%3E%3CLINGO-BODY%20id%3D%22lingo-body-666094%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3E%3CP%3EHola%2C%3CBR%20%2F%3E%3CBR%20%2F%3E%20No%20he%20podido%20encontrar%20muchos%20recursos%20para%20este%20problema%20en%20particular.%3CBR%20%2F%3E%3CBR%20%2F%3E%20Contexto%3A%3CBR%20%2F%3E%20Estoy%20trabajando%20en%20la%20emergencia%20de%20insectos%20(despu%C3%A9s%20de%20la%20metamorfosis).%20Estamos%20registrando%20la%20proporci%C3%B3n%20de%20la%20poblaci%C3%B3n%20inicial%20que%20emerge%20con%20el%20tiempo.%3CBR%20%2F%3E%20Para%20un%20grupo%20de%20individuos%2C%20este%20fen%C3%B3meno%20siempre%20sigue%20un%20modelo%20log%C3%ADstico%20de%203%20par%C3%A1metros%2C%20pero%20diferentes%20grupos%20tendr%C3%A1n%20diferentes%20par%C3%A1metros.%3CBR%20%2F%3E%3CBR%20%2F%3E%20Estamos%20tratando%20de%20determinar%20si%20un%20tratamiento%20cambiar%C3%A1%20los%20par%C3%A1metros%20de%20la%20curva%20de%20emergencia.%20Cualquier%20cambio%20significativo%20en%20uno%20o%20varios%20de%20los%20par%C3%A1metros%20es%20relevante%3CBR%20%2F%3E%3CBR%20%2F%3E%20Ej%3A%20si%20cambio%20la%20humedad%20ambiental%20en%20mi%20espacio%20de%20crianza%2C%20%C2%BFla%20emergencia%20ser%C3%A1%20m%C3%A1s%20r%C3%A1pida%20(impacto%20en%20el%20punto%20de%20inflexi%C3%B3n%2C%20tasa%20de%20crecimiento)%3F%20%C2%BFTendr%C3%A1%20un%20costo%20para%20los%20individuos%20(impacto%20en%20la%20as%C3%ADntota)%3F%3CBR%20%2F%3E%3CBR%20%2F%3E%20Para%20responder%20a%20esta%20pregunta%2C%20estamos%20realizando%20experimentos%20en%20los%20que%20n-1%20grupos%20reciben%20los%20niveles%20n-1%20de%20un%20tratamiento%20y%20un%20grupo%20es%20un%20control.%20Generamos%20n%20%22curvas%20de%20emergencia%22%2C%20siendo%20cada%20una%20descrita%20por%20su%20vector%20de%203%20par%C3%A1metros.%3CBR%20%2F%3E%20Como%20sabemos%20que%20podemos%20tener%20efectos%20de%20cohorte%20o%20ambientales%2C%20el%20experimento%20se%20replica%20m%20veces.%20Dentro%20de%20un%20experimento%20(curvas%20nxm%20generadas)%2C%20cada%20curva%20se%20modela%20a%20partir%20de%20un%20tama%C3%B1o%20de%20muestra%20fijo%20(generalmente%20alrededor%20de%20400%20individuos).%20m%20es%20relativamente%20peque%C3%B1o%20(%26lt%3B10)%3C%2FP%3E%3CP%3E%26nbsp%3B%3C%2FP%3E%3CP%3E%C2%BFC%C3%B3mo%20podemos%20concluir%20que%20el%20factor%20tiene%20efecto%20sobre%20uno%20o%20varios%20par%C3%A1metros%20de%20las%20curvas%3F%3CBR%20%2F%3E%3CBR%20%2F%3E%20-%20Una%20opci%C3%B3n%20ser%C3%ADa%20utilizar%20las%20%22pruebas%20de%20equivalencia%22%20(paralelismo)%20que%20ya%20est%C3%A1n%20incluidas%20en%20JMP%2C%20pero%20que%20solo%20permiten%20comparar%20dos%20curvas%20a%20la%20vez.%20Se%20describen%20como%20pruebas%20heredadas%20y%20parecen%20algo%20criticadas.%3CBR%20%2F%3E%20-%20%C2%BFAnalizar%20cada%20factor%20por%20separado%20(ANOVA%20y%20equivalentes%20no%20param%C3%A9tricos)%3F%20Hay%20algunas%20correlaciones%20entre%20los%20par%C3%A1metros%20de%20las%20curvas%20(probado%20con%20la%20correlaci%C3%B3n%20de%20Pearson%2C%202%20por%202)%3CBR%20%2F%3E%20-%20%C2%BFUsando%20un%20enfoque%20Manova%3F%20Realmente%20no%20estoy%20familiarizado%20con%20Manova%2C%20as%C3%AD%20que%20me%20gustar%C3%ADa%20saber%20si%20ser%C3%ADa%20un%20enfoque%20v%C3%A1lido%20antes%20de%20profundizar%20en%20el%20tema.%3CBR%20%2F%3E%20-%20%C2%BFOtras%20sugerencias%3F%3CBR%20%2F%3E%3CBR%20%2F%3E%20Puedo%20compartir%20algunos%20datos%20de%20muestra%20si%20es%20necesario%20(datos%20de%20emergencia%20sin%20procesar%20o%20una%20tabla%20con%20par%C3%A1metros)%3C%2FP%3E%3C%2FLINGO-BODY%3E%3CLINGO-LABS%20id%3D%22lingo-labs-666094%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3E%3CLINGO-LABEL%3EModelado%20Estad%C3%ADstico%20Avanzado%3C%2FLINGO-LABEL%3E%3CLINGO-LABEL%3EAn%C3%A1lisis%20y%20modelado%20de%20datos%20b%C3%A1sicos%3C%2FLINGO-LABEL%3E%3C%2FLINGO-LABS%3E%3CLINGO-SUB%20id%3D%22lingo-sub-666102%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3ERe%3A%20C%C3%B3mo%20comparar%20varios%20conjuntos%20de%20datos%20modelados%20por%20modelos%20log%C3%ADsticos%20de%203%20par%C3%A1metros%3C%2FLINGO-SUB%3E%3CLINGO-BODY%20id%3D%22lingo-body-666102%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3E%3CP%3E%22analizar%20cada%20factor%20por%20separado%22%20deber%C3%ADa%20ser%20%22analizar%20cada%20par%C3%A1metro%20por%20separado%22%3C%2FP%3E%3C%2FLINGO-BODY%3E
Choose Language Hide Translation Bar
Alexa_Guigue
Level I

How to compare several sets of data modeled by a 3-parameter logistic models

Hi, 

I haven't been able to find a lot of resources for this particular issue.

Context:
I am working on insect emergence (after metamorphosis). We are recording the proportion of the initial population emerging over time.
For a group of individuals, this phenomenon always follows a 3-parameter logistic model, but different groups will have different parameters.

We're trying to determine if a treatment will change the parameters of the emergence curve. Any significant changes in one or several of the parameters are relevant

Ex: if I change the ambiant humidity in my rearing space, will the emergence be quicker (impact on inflexion point, growth rate)? Will it come to a cost to the individuals (impact on asymptote)?

To answer this question, we are conducting experiments where n-1 groups receive the n-1 levels of a treatment, and one group is a control. We generate n "emergence curves", each one being described by its 3-parameter vector.
Since we know that we may have cohort or environmental effects, the experiment is replicated m times. Within an experiment (nxm curves generated), each curve is modelled from a fixed sample size (usually about 400 individuals). m is relatively small (<10)

 

How can we conclude that the factor has an effect on one or several parameters of the curves?

- One option would be to use the "equivalence tests" (parallelism) that are already included in JMP, but they only allow the comparison of two curves at a time. They are described as legacy tests and seem somewhat decried 
- Analysing each factor separately (ANOVAs and non-parametric equivalents)? There are some correlations between the parameters of the curves (tested with Pearson's correlation, 2 by 2)
- Using a Manova approach? I'm really not familiar with Manova, so I'd like to know if it would be a valid approach before taking a deep dive in the subject
- Other suggestions?

I can share some sample data if needed (raw emergence data, or a table with parameters) 

1 REPLY 1
Alexa_Guigue
Level I

Re: How to compare several sets of data modeled by a 3-parameter logistic models

"analysing each factor separately" should be "analysing each parameter separately"