Test Construction - Science topic

Based on your description, it sounds like the transfected cells are experiencing cell cycle arrest or apoptosis due to toxicity from the transfection reagents and/or overexpression of the transfected plasmid.

You can try to:

- Reducing the amount of transfection reagent even further. Start with the manufacturer's recommended minimum and titrate down. Too much lipid can be quite toxic.

- Optimize the ratio of DNA:lipid. Test different ratios to find the sweet spot for your cell type.

- Try a different transfection reagent. Lipofectamine is quite harsh. You could try FuGENE or Polyjet which may be less toxic.

- Reduce the amount of plasmid DNA transfected. Overexpression can trigger apoptosis. Titrate down to find the minimum needed.

- Use a lower CMV or inducible promoter to reduce expression levels.

- Try transfecting plasmid expressing an inert reporter like GFP first to rule out plasmid toxicity.

- Let cells recover overnight in normal media before imaging.

- Check for apoptosis markers like cleaved caspase-3 in transfected cells.

- Monitor proliferation with labels like EdU or by quantifying cell numbers over time.

With some optimization of reagents and DNA amounts, you should be able to find conditions where transfected cells still divide.

If you found it, please share it with me as well

Mostly the psychological scale includes certain paragraphs that determine the individual's position on them to reveal the characteristics that characterize him

Through the TaT test. For two independent samples

You can check our papers if you find something useful there:

The discriminant validity is based on the correlation of latent variables (it is recommended that they be less than .70) and the factor loads of the exogenous variables in relation to each dependent variable (greater than .50).

Hi M.F. Marquetto

your model is extremely complex. So complex that you probably won't be able to fit it in one phase of a study. To show that, I re-generated your model with the browser software dagitty.net wich allows you to draw a path diagram and print the "testable implications" -- which are in total evaluated by the model chisquare test and described by the fit indices. The lower part of this post shows the list of these restrictions. The signs "⊥" mean "independence" (i.e., zero correlation) and the bar "|" is a "condition"-sign. For instance, your model assumes/predicts that A ⊥ H | G, which means that A does not correlate with H when you control G. The rules are simple path tracing, path blocking/d-separation (google for these terms).

Even leaving out the downstream part (G, H, I, J) would still imply a complex model, however, with some chance to get it done. But the relationships between C to F are still complex. Ideally, such a huge model could/would be developed and tested via successive steps of primary studies, each with some exploratory and confirmatory part. Perhaps starting with an upstream model, in which some of the mediators are collapsed/excluded could be a start.

I know that this is not what you wanted to hear. But if SEM gets often difficult then because IT IS difficult.

Best,

Holger

- - - - - - - - - - - - - - - - - - - - - -

Hi Nick,

Essentially,you have two issues here. 1) Is the power of your study enough to generalise/infer your findings from your sample to your target population? 2) Is the sample sufficient to compute factor analysis and produce robust construct validity results?

Well, both questions are related to calculating sample sizes but using different methods and purposes.

To answer qn.1, look up sample size calculation for your type of study and estimate how many minimum sample you need to achieve alpha > 0.8 or confidence of 95%. If you have collected your data, you can calculate this retrospectively, to identify whether you have reached power and precision to generalise your finding. If not, you just need to fess up and report in your limitation of study.

To answer qn.2, you are right, it may seem arbitrary but as a rule of thumb, a minimum of 10 samples per item/question/variable is necessary to avoid computational problems later. This depends on how many constructs and how many items per constructs you have. If you have one construct with about four observed variables, then even sample size of 60 is adequate. In any case, give your best to obtain as many sample as you can. Any sample size over 300 is considered adequate for factor analysis. You may also come across those recommending cut-off sample sizes: 50 is very poor, 100 is poor, 200 is fair, 300 is good and 500 is very good, and 1,000 or more is excellent.

You may also try linear discriminant analysis as alternative. Hope this helps!

I agree with the great comments above, and for the sake of completeness, I want to mention the "correlation with marker items (items that you highly trust) method", which I find very practical.

Focus groups are widely recommended for this kind of work because they give you insight into the diversity of views that get expressed. I generally recommended choosing your questions for these groups according to which of three levels meet your needs. First, you might be pursuing discovery, when you don't have any prior ideas about what to measure, so you need to be exploratory. Second, you might be pursuing development, when you have some ideas about what you want to measure, and you need to hear about questions that would match the concepts you have in mind. Third, you might be doing definition, where you want to determine the best wording for the questions you want to ask.

Or, if all you need is a list of types of violence, then studies have repeatedly shown that just having a handful of people give you their answers will do the best job of producing such a list, rather than doing a full-scale research project.

In any event, you have picked a very sensitive topic, so you need to do more than just select the methods. In addition, you need to establish a high level of trust to get people to engage in whatever method you choose.

Dear Tran Nguyen,

in the research model development, I agree with the previous comments. It is a common method to adopt, combine, and.or adapt the previous models for developing the new ones in the social computing studies. It may relate to the context of the human behavior change for using new technologies. However, of course, the adoption, combination, and/or adaptation have to be justified clearly based on a reasonable assumption. The assumption itself is developed for representing the research phenomenon using the basic concepts/theories.

In this case, my point of view is that you propose a brand loyalty model about branded mobile app by adopting and integrating the Alnawas's (2016) model and the Bhattacherjee's (2001) ECM model, and replacing (adapting) the "Perceived Usefulness" by the "4 benefits of using branded apps."

In the context of the adoption, combination, and the adaptation points, it may reasonable; but you have to able to describe clearly assumptions of the above-mentioned points in terms of the brand loyalty model about branded mobile app.

My suggestion are:

First; please, identify the used concepts/theories behind the Alnawas (2016) and Bhattacherjee's (2001) studies and then develop a logical map of the adoption, integration, and the adaptation following to the brand loyalty issue of the branded mobile app. This is for expressing reasonably the validity point of your proposed model, how the model represent the real phenomenon of the study.

Second; please, elucidate the model development process. The clear demonstration of the process may helpful people to see transparently the process. It is in regard to the trust point of the model development study. I believe, both validity and trust issues are essential in the model development studies (Eddy et al., 2012).

You can access:

1.

2.

3.

May help,

A'ang

Thank you for your response, Dr. Ortega. Will do that.

You can find an overview of various norms for test construction from this book chapter:

file:///C:/Users/MM/Downloads/9788132236290-c2.pdf

Please refer to attached document by Hinkin 1998. It is a complete guideline for instrument development and I highlighted some areas which could be more highly beneficial for you.

Good Luck

Recomiendo aplicar el enfoque de evaluación Autentica que consiste en focalizar una evaluación en el desempeño de los estudiantes es decir, evaluar en contextos reales .

<!-- /* Font Definitions */ @font-face {font-family:"Cambria Math"; panose-1:2 4 5 3 5 4 6 3 2 4; mso-font-charset:1; mso-generic-font-family:roman; mso-font-format:other; mso-font-pitch:variable; mso-font-signature:0 0 0 0 0 0;} @font-face {font-family:Garamond; panose-1:2 2 4 4 3 3 1 1 8 3; mso-font-charset:0; mso-generic-font-family:roman; mso-font-pitch:variable; mso-font-signature:647 0 0 0 159 0;} /* Style Definitions */ p.MsoNormal, li.MsoNormal, div.MsoNormal {mso-style-unhide:no; mso-style-qformat:yes; mso-style-parent:""; margin:0cm; margin-bottom:.0001pt; mso-pagination:widow-orphan; font-size:12.0pt; font-family:"Times New Roman","serif"; mso-fareast-font-family:"Times New Roman"; mso-ansi-language:ES; mso-fareast-language:ES;} .MsoChpDefault {mso-style-type:export-only; mso-default-props:yes; font-size:10.0pt; mso-ansi-font-size:10.0pt; mso-bidi-font-size:10.0pt;} @page WordSection1 {size:595.3pt 841.9pt; margin:70.85pt 3.0cm 70.85pt 3.0cm; mso-header-margin:35.4pt; mso-footer-margin:35.4pt; mso-paper-source:0;} div.WordSection1 {page:WordSection1;} -->

2 Características de una Evaluación Auténtica Vinculada con el mundo y las necesidades reales para el futuro desempeño ciudadano y profesional del estudiante. Intenta averiguar qué sabe o qué es capaz de hacer el estudiante, utilizando diferentes estrategias y procedimientos evaluativos. Incluye tareas complejas y contextualizadas enfatizando más la profundidad que la extensión.

3 Características de una Evaluación Auténtica Es una instancia de enseñanza, de sentido formativo, centrada más en procesos que en resultados. Los estudiantes deben demostrar su competencia en contextos cercanos a la realidad. Estimula el desarrollo de la meta cognición. Se realiza en un período de tiempo amplio.

4 Características de una Evaluación Auténtica Involucra múltiples formas de producción y desempeños del estudiante. Procura reflejar de manera completa el aprendizaje, la comprensión, logros, motivación y actitudes de los estudiantes. Utiliza variados procedimientos que demandan la elaboración reflexiva y justificada de respuestas o productos. Participación activa de los estudiantes.

5 La Evaluación Auténtica según Margalef (2005) Es: Holística, el proceso se antepone al resultado. Democrática, participan todos los que intervienen en el proceso. Una actividad ética que parte de una explicitación de los criterios de evaluación; remite a valores, intereses y expectativas. Una actividad política e ideológica. Un proceso que se guía por la búsqueda de la equidad y no de la objetividad

6 La Evaluación Auténtica según Margalef (2005) Es: Un proceso que reconoce su dimensión valorativa y la búsqueda de la justicia. Una oportunidad para practicar la autoevaluación y la co-evaluación. Una actividad crítica que genera aprendizaje tanto para los profesores como para los alumnos. Fuente de innovación y mejora de la propia práctica.

7 La Evaluación Auténtica según Margalef (2005) Es: Eminentemente “formativa” o educativa porque persigue la calidad de la enseñanza. Una posibilidad para asegurar el éxito de los alumnos porque su seguimiento es continuo. Es integradora, individualizada y personalizada. Una evaluación que tiene en cuenta al alumno y al contexto. Una actividad crítica de aprendizaje.

8 Procedimientos de Evaluación Auténtica Informes/ Ensayos Carpetas o Portafolios Posters Diarios Murales Discursos/Disertaciones Entrevistas

9 Procedimientos de Evaluación Auténtica Experimentos Proyectos Estudio de Casos Creaciones Artísticas: Plásticas, Musicales y Literarias Elaboración de Perfiles Personales

10 Criterios para la Construcción de Procedimientos Evaluativos Autenticidad: cercano a la realidad. Generalización: alta probabilidad de generalizar el desempeño a otras situaciones comparables. Focalización múltiple: posibilidad de evaluar diferentes resultados de aprendizaje. Potencial educativo: permite a los estudiantes ser más hábiles, diestros, analíticos, críticos.

11 Criterios para la Construcción de Procedimientos Evaluativos Equidad: evita sesgos derivados de género, NEE, nivel socioeconómico, procedencia étnica. Viabilidad: es factible de realizar con los recursos disponibles. Corregible: lo solicitado al alumno puede corregirse en forma confiable y precisa.

 Dear Sonam! Strongly speaking adaptation consists of the change of questions for the persons of the same age as it was at an original test (taking into account culture`s differences and so on). If you use the same factors as it was at an original test you can`t say that you have a deal with pure test construction. So you are between construction and adaptation. If you add or change one factor you will have the right to consider your test as constructed one. I think it is a better way for you in your situation. I wish you much success. Sincerely Ivan Voloshchuk

pBabe vectors don't do well with transient transfections at all. Whenever I've tried to do that in the past, it's extremely difficult to find a single cell that is transiently transfected. I would recommend testing constructs in pcDNA3.1 first for transient transfection, then moving it into pBabe and just go forward with stable cell line generation.

Thank you guys!

International Streptomyces Project (ISP). You can find yr need.

Mehraneh,

Define difficulty as the mean observed score for an item (in your example, between 1-4).  Higher mean = easier task.

Define discrimination as Pearson correlation between item score and total score.  If you want to be a bit more precise, subtract item score from the total score first (so-called corrected item-total correlation).  Classical discrimination indices are all some variation on how well item scores relate to some larger criterion (e.g., total score).

You can, of course, use Qasim's approach, but that requires an extra step of first computing total scores for all respondents, then disaggregating cases into 'high' and 'low' scoring groups.

Hi there,

actually, I could never really understand why some specific fields (its only a small number of fields) place so much value in alpha and AVE.

My 2 c:

CR is a nice measure (much better than alpha as it does not assume essential tau-equivalence, that is, equal loadings) to evaluate the *validity* of a set of measures *given the correctness of the factor model*. Why it is not reliabilty? Because the measurement error is not only random error but the error term of the indicator (comprising all other systematic and non-systematic influences on the item response). Thus the error variance is the "non-factor-relevant" (i.e., invalid) part of the variance and the loadings are the "factor-relevant" (i.e., valid) part of the variance.  

If the model fits, than even indicators with a low CR can work well because measurement error is taken into account (thats why we use latent variables and SEM, isn't it?). Therefore, the CR is a nice evaluation criterion for the indicators but it does not signify that one can or cannot use the indicators. 

Much more important is the i) fit of the model (supporting the structure of the factor model and thus basis of any validity issues) and ii) the individual loadings which give some hints about the meaning of the latent variable. The first issue is relevant to the question if the arrow pointing from the latent variable to the indicator has some meaning (this is THE most important issue when addressing validity). The second issus concerns the question if the latent variable has the meaning one thinks it has.

The question, thus, is: is a low effect/loading in accordance with YOUR understanding of the meaning of the latent variable? The basis for validity (see the brilliant paper by Borsboom et al. below) a) does the latent variable exists and b) does it have an effect of the indicator (or turned arround: does the indicator measures what it intends to measure?

Like the usual fit indices, things like CR and AVE have been invented because people tend to avoid to rigidly test their (causal) models and they need some substitutes.

I hope I do not annoy anyone. I just want to present a different perspective 

Best,

Holger

Borsboom, D., Mellenbergh, G. J., & van Heerden, J. (2004). The concept of validity. Psychological Review, 111(4), 1061–1071.

my advice is yes (you should do it). You can perform a confirmatory factor analysis or an exploratory factor analysis.

If you intend to use PCA as an extraction method for EFA would actually be not only insufficient but probably wrong for adapting a psychometric instrument's translation. PCA is sensitive to the actual variables you feed it and the original researchers ended up with the particular set of items from a a larger pool. Thus using the refined scale items as a new pool will lead to misleading results. I would say go to CFA without any PCA before. Draw your model structure from the references of the original instrument.

[Furthermore, and as a general note on PCA, Overall's simulation has shown that PCA does not reveal the true structure behind a set of observed variables - it is rather a good summary of the correlations. PCA components are good for prediction purposes, but not for theoretical understanding].

The ISO standard 12572 (2001) can for example be used if you mean moisture as water vapour. It uses the dry cup or wet cup method.