Science topics: Nested
Science topic

Nested - Science topic

Explore the latest questions and answers in Nested, and find Nested experts.
Questions related to Nested
  • asked a question related to Nested
Question
2 answers
Hi all,
I am doing an CFA analysis of categorical data with the WRMR estimation method in Mplus 7. I want to compare nested models and I was wondering whether there is an online tool which is doing a chi2 difference test for me based on this data/estimation method. As far as I can see most tools just provide this on the basis of maximum likelihood estimations. Any suggestions?
Thank in advance,
Gert
Relevant answer
Answer
Yes sure, I meant WLSMV not WRMR. Thanks for providing the URL.
  • asked a question related to Nested
Question
2 answers
I have 3 different PCR methods to compare,
all are different compositions and different volumes.
is it okay to unify the concentrations or amount of primers and template for the comparison?
2 PCR methods are nested and the other is qPCR trying to find the sensitivity between them.
Relevant answer
Answer
You should compare only well-optimized assays. Optimization w.r.t. sensitivity implies that you test series of decreasing template concentrations in each assay anyway.
  • asked a question related to Nested
Question
3 answers
I am needing to do a nested two way ANOVA with three fixed factors (Time (5 levels) and Site (4 levels ) nested within Condition( 2 levels), followed by a pairwise comparison post hoc test to identify interactions. I need to use SPSS as this is the software I have used throughout my thesis. So far I have been able to gain outputs for the nested ANOVA but I can’t figure out how to gain a post hoc test output. I use syntax to code but when I add code for post hoc it gives a warning saying it can’t recognise my fixed factors. Attached images below of codes I have tried. Any help would be appreciated!
Relevant answer
Answer
One more thing. The code in the original post showed that you included Time*Site(Condition) as the only term in the model. You need to include the lower order terms too.
  • asked a question related to Nested
Question
2 answers
Good morning Dear all
Please, can you provide me some reference where I can find a relationship between great apes' age (juveniles, adults mature,) or body size with their nest diameter. I have collected nests diameter of great apes in my study area and I would like to sort them in classes of diameter according to the age of the animal that constructed the nest.
Thank you in advance and good day
Relevant answer
Answer
Hi Dear Carl
Thanks you very much for this. With the reference I might find others.
  • asked a question related to Nested
Question
5 answers
Does anyone know of papers or data discussing the historical connection between the Syr Darya and the Tarim rivers? Loaches found in these two rivers' basins are nested on the same clade of the phylogenetic tree when studied molecularly. We speculate whether these two basins were previously connected.
Many thanks in advance!
Relevant answer
Answer
Interesting topic. The Norin tributary of the Syr Darya and the Aksu tributary of the Tarim River originate from almost the same place, the Petrov Glacier (Kyrgyzstan). I think that these two rivers have historically connected tributaries.
Do any of the Loach species you are researching occur in Issykkul Lake or Lake Paterbashik?
  • asked a question related to Nested
Question
5 answers
Dear experts,
I am working on a very large scale data (20k). the research is on data collected from different schools from different district and different states in India. How to give nested data command in AMOS. I want to CFA in AMOS and want to include effect of nested data for the model fit. please guide me. I am not able to find any videos or lectures that provide hands-on training on this topic.
Relevant answer
Answer
Maximum likelihood (ML) estimation is available in Mplus. In fact, it is the default estimation method for continuous outcome variables in that program. The lavaan package in R also supports ML estimation for CFA/SEM.
Mplus offers an option called TYPE = COMPLEX that allows you to obtain robust standard errors and fit statistics when dealing with multilevel (clustered) data and the number of clusters is too small to use actual multilevel CFA or SEM modeling.
  • asked a question related to Nested
Question
1 answer
I had a set of data with factor A (a), factor B nested in A (b), and replication (r) in each unit. Recommendations have explicitly told the details of how to deal with data with equal variance in R, from nested ANOVA test to corrected multiple comparison (e.g. lme/lmer, glht/lsmeans). But these processes require the homoskedastic data, otherwise the violated assumption about variance may brought about poor inference efficiency.
However, similar recommendations on heteroskedastic data are limited. One of them is the Permutation ANOVA, which calculate the similarity of centroids and dispersion of groups. But directly using welch's anova for data of different groups (e.g., x1=data$y[data$y=='A1'], x2=data$y[data$y=='A2'], t.test(x1,x2,var.equal=TURE) -> p, following a bonferroni corrected p<p^{H_0}/m calculation). Is the plausible process correct?
Another method is the log transformation, which could used to compare means directedly, but only for some data. The inverse standard deviation of the error term for weighted least square was also introduced, but could this weighted data applicable for direct t.test (bonferron or tukey corrected?).
Relevant answer
Answer
You might see the answer here. Russ Lenth can be trusted on this matter. Are you able to formulate a model that takes into account the heteroscedasticity ? https://stats.stackexchange.com/questions/500938/post-hoc-test-with-heteroscedasticity
  • asked a question related to Nested
Question
3 answers
Dear RG community members,
I hope you are well and helthy and ready for small discussion. My question is, can we efficiently increase the population of wetfowls in wetland areas by constracting and using artificial nests suitable for specific taxa? If you also have any reference on that issue, I would be grateful.
Thank you.
Zlatko
Relevant answer
Answer
Hello Zlatko; If you are interested in attracting birds to wetlands, the method will depend on which groups of birds you are targeting. In North America, wetland songbirds are attracted by developing waterside shrubs and small trees. Willows are particularly useful. For bluebirds which are hole-nesters, artificial nest boxes are used. For raptors like Ospreys, platforms on high poles are promptly occupied by the birds. You get the idea. Most of the techniques I'm aware of target particular species or particular nest types. Best regards, Jim Des Lauriers.
  • asked a question related to Nested
Question
3 answers
I investigated the extent and prevalence of physical activity during the school day and sedentary behavior during inactive screen time in youth and their effect on overweight and obesity. Participants were stratified by age (children - adolescents) and gender. Data were compared using t-test and ANOVA and the effect on overweight and obesity was studied using MLR. Are my data considered nested? If so, how do I calculate the ICC requested by the reviewer?
Relevant answer
Answer
Dear Sirs,
Thank you for the answers. I need a reasoned response to answer the reviewer. Sincerely,
  • asked a question related to Nested
Question
1 answer
I have a multi-stage stochastic programming model. I have 3 groups of variables: the first group takes values ​​at the beginning of the planning horizon before the first realization and does not change until the end of the planning horizon and has no t index (they are binary and continuous), the second option is “here and now” variables that before each realization Are taken value and are continuous, the third group are “wait and see” variables that take value after each realization (binary and continuous). The model is SMINLP. I converted it to SMILP through linearization and solved it by CPLEX solver with generating a small number of scenarios ... I want to consider a continuous distribution for the stochastic parameter and generate a large number of scenarios by sampling and run an algorithm for it. nested benders decomposition or progressive hedging algorithms are more efficient for this model?
If anyone has experience, thank you in advance for your help.
  • asked a question related to Nested
Question
18 answers
Dear colleagues,
we conducted an experiment with a dependent sample and two conditions (treatment A and treatment B), with a crossover design to control for sequential effects. Participants (level 1; n = 34) are nested within different therapists (level 2; n = 8). The therapists conducted both treatment A and treatment B. I was wandering, if multilevel analysis is a suitable alternative to a paired t-test in this case? Unfortunately, the design is unbalanced as each therapist conducted a different amount of treatments. Thank you!
Relevant answer
Answer
Sounds like a multi-level analysis would be perfect, especially considering the unbalanced design.
  • asked a question related to Nested
Question
3 answers
Ants in the genus Aphaenogaster is referred to as the "funnel ants" due to their conical-shaped nest structure. Some species serve as model organisms for studying of foraging pattern and tool-using in the world of insects. But the under-ground behaviors of these ants with impact on soil processes appeared to have seldom been investigated. Does anyone has knowledge about any aspects of nest-construction behaviors by Aphaenogaster ants please?
Relevant answer
Answer
Ran; Good luck with your project. I've never been successful with lab colonies of ants. I didn't pay enough attention...I seem to prefer being in the field.
Best regards, Jim Des Lauriers
  • asked a question related to Nested
Question
7 answers
Thank you for checking this post out!
I'll use the following example to discuss the challenge I'm facing:
My logistic-exposure model asks whether a study species' nest success (1/0) can be explained by the density of the overstory (a proportion) around each nest, and the distance (meters, continuous) from the nest to the edge of the habitat patch, i.e.:
NestSuccess ~ OverstoryDen + DisToEdge
The independent variables are scaled - mean subtracted, divided by standard deviation, using R function scale().
The model output gives me:
OverstoryDen estimate = 2.91
DisToEdge estimate = 0.87
I am interested in interpreting the output in real, useful terms, but I'm not sure I'm getting this right. This is what I've done:
Let's look at OverstoryDen first: Odds Ratio = e^2.91 = 18.36
So, this implies that the probability of a nest succeeding is 18.36 greater in areas where overstory density if one standard deviation greater, correct?
Now, here's the part that stumps me: The standard deviation of OverstoryDen is 0.146, and, recall, this parameter is a proportion, i.e. 0 - 1. So, can I say anything more general/relevant about the relationship between nest success and OverstoryDen? i.e. would it be prudent to divide 18.36 by 0.146 and say that for every 1% increase in density the probability of success increases by a factor of 2.26? Or is there a linearity issue here?
Similarly, for DisToEdge, the odds ratio = 2.39, sd of the variable = 14 meters, so would it be prudent to divide per meter and say that success increases by 17.1% with each added meter of distance?
Thanks so much for any help you can offer!
Relevant answer
Answer
First, you should not use the term "probability" as a synonym for "odds." Their numerical values will be similar only when very low (and identical only when both are zero). So an odds ratio of 18 does not say the PROBABILITY of nest success is 18 times greater for each one s.d. increase in overstory density. Rather, it says the ODDS are 18 times greater. Only the latter interpretation is always accurate, because the coefficients from your logit model are linear for the logit function (the log of the odds), not for the probabilities.
Second, if your objective is to interpret the effects in relation to the original units of the variables rather than in relation to their standard deviations, a much simpler approach would be to use the original, unscaled variables in your logit model. With DistToEdge scored in meters, its odds ratio would be directly interpretable as the multiplicative effect on the odds of nest success for each additional meter of distance. You could check to see if that gives you the same effect as the more round-about approach you suggest. If I'm understanding your approach correctly, I think it might, but your approach is not entirely clear to me.
For OverstoryDen, I think it would be handy to first convert it from a proportion to a percentage, by multiplying by 100. Then the odds ratio would be directly interpretable as the multiplicative effect on the odds of nest succes for each additional one percentage point in density. (That's another nuance of terminology worth paying attention to: a one percentage point change is not the same as a 1% change. For example, a one PERCENTAGE POINT change from 19 to 20 is roughly a 5 PER CENT increase.)
  • asked a question related to Nested
Question
2 answers
I have been getting a band in the second (nested) amplification of the negative from the initial PCR, but not in my negative control testing for contamination. Any ideas?
Information:
I am using a nested PCR for different Ehrlichia species in whole blood.
The initial PCR is an Ehrlichia screen using one set of primers. For 20 cycles.
The nested PCR's have specific primers based on the Ehrlichia species. For 30 cycles.
The initial negative controls have RNases free water, Taq polymerase, and the Ehrlichia screen primers.
When I run the nested, I take 1 uL from the initial negative (which is clean on the gel).
I've recently changed out my reagents, and the band is around 500 bp so not primer dimers.
Could be something specific in the initial primers but I only see it in the samples that should be negative and it's a pretty big piece to be related to the primers.
Thank you
Relevant answer
Answer
I thought I'd give an update:
Most of the time, diluting the initial PCR negative did remove the band in the nested product. However, it was random, and sometimes it was still present, although faint.
Next, diluting the PCR products would sometimes cause the bands to be very faint or not be visible.
So it could work for someone else who is having the same issue.
  • asked a question related to Nested
Question
1 answer
I'm making a nested, high resolution simulation (~300m*300m) of WRF in the polar region. The existing static sea ice data is of low resolution and I want to update this static data with a satellite based high resolution data. I need to update the static field only for the inner domain.
How can I do it?
What are the best tools for the same?
Anything in particular I should be careful about?
Thank you in advance.
Relevant answer
Answer
Hi, you need to assimilate the high resolution satellite data into the initial field of WRF run.
  • asked a question related to Nested
Question
17 answers
Researchers in the social sciences have to report some measure of reliability. Standard statistics packages provide functions to calculate (Cronbach's) Alpha or procedures to estimate (MacDonalds) Omega in straightforward way. However, things become a bit more complicated when your data have a nested structure. For instance, in experience sampling research (ESM) researchers usually have self-reports or observations nested in persons. In this case, Geldhof et al. (2014) suggest that reliability be estimated for each level of analysis separately. Albeit this is easy to do with commerical packages like MPlus, R users face some challenges. To the best of my knowledge most multilevel packages in R do not provide a function to estimate reliability at the within vs. the between person level of analysis (e.g., misty or multilevel).
So far, I have been using a tool created by Francis Huang (2016) which works fine for Alpha. However, more and more researchers prefer (MacDonalds) Omega instead (e.g., Hayes & Coutts, 2020).
After working with workarounds for years I accidentially found that the R package semTools provides a function to estimate multilevel Alpha, different variants of Omega, and average variance extracted for multilevel data. I would like to use this post to share this with anyone struggling with estimation of multilevel reliability in R.
I find this post helpful, feel free to let me know.
Oliver
Bliese, P. (o. J.). multilevel: Multilevel Functions. Comprehensive R Archive Network (CRAN). [Computer software]. https://CRAN.R-project.org/package=multilevel
Geldhof, G. J., Preacher, K. J., & Zyphur, M. J. (2014). Reliability estimation in a multilevel confirmatory factor analysis framework. Psychological Methods, 19(1), 72–91. https://doi.org/10.1037/a0032138
Huang, F. L. (2016). Conducting multilevel confirmatory factor analysis using R. http://faculty.missouri.edu/huangf/data/mcfa/MCFAinRHUANG.pdf
Hayes, A. F., & Coutts, J. J. (2020). Use Omega Rather than Cronbach’s Alpha for Estimating Reliability. But…. Communication Methods and Measures, 14(1), 1–24. https://doi.org/10.1080/19312458.2020.1718629
Yanagida, T. (2020). misty: Miscellaneous Functions „T. Yanagida“ (0.3.2) [Computer software]. https://CRAN.R-project.org/package=misty
Relevant answer
Answer
The R package semTools now has a new compRelSEM() function, that estimates composite reliability from estimated lavaan models. For multilevel measurement models, reliability indices defined by Lai (2021) are implemented, as well as Geldhof et al.'s (2014) less useful "hypothetical reliability" of level-specific latent components. Until version 0.5-6 is available on CRAN, the development version can be installed with syntax provided in my description here: https://github.com/simsem/semTools/issues/106
  • asked a question related to Nested
Question
3 answers
Dear colleagues,
I'm experiencing difficulties with running a mixed model in SPSS (version 26) so I'm reaching out to the ResearchGate community.
My experiment is a 2x2 factorial design in which we provide light and/or larvae to chickens. I have individual (continuous) measurements from behavior tests as outcome parameters. But since the chickens are housed in groups (pens), and the light and larvae are provided on pen level, these individual measurements within a pen are not independent. Therefore I need to run a linear mixed model with light, larvae and their interaction as fixed effects and pen as random effect.
However, SPSS gives me the following warning:
"The final Hessian matrix is not positive definite although all convergence criteria are satisfied. the MIXED procedure continues despite this warning. Validity of subsequent results cannot be ascertained."
It probably says so because the pens are linked to the light/larvae treatment. But it should be possible to run this analysis in some way, right? Can anyone help me find out what I'm doing wrong?
Thank you so much!
Relevant answer
Answer
I use SmartPLS or to run such. I recommend you try it. Its easy
  • asked a question related to Nested
Question
5 answers
Does vegetation structure (e.g. tree raminification pattern) affect bird nesting activity and nest abundance? Could you please recommend studies related to this topic? Thanks
Relevant answer
Answer
Thank you very much for the recommendations. In Moudrý et al. it is interesting to note that vegetation heterogeneity was strongly related to bird species richness, also that dead trees also provided shelters for nesting birds. Those were however somehow limited to the ground nesting/foraging species as the authors mentioned. How about tree-nesting species?
  • asked a question related to Nested
Question
3 answers
Hello everyone,
I have a question regarding a statistic test.
I will give you the background first.
I am testing different characteristics of microglial cells. I am testing the difference between WT and KO mice. I have a sample of n=6. In each row, each genotype represents a mouse. Each value represents 1 cell.
If it is important - parameters from each mouse were taken from 4 fields (both hemispheres were imaged from 2 slices = 4 fields).
In the added table, I used nested t-test, as a representative from Prism suggested.
Do you think nested t-test is the best test for my DATA?
Is it legitimate to use this test in this experiment?
Ela.
Relevant answer
Answer
Thank you both so much! Mewa Singh Dhanoa John Hardy Lockhart
  • asked a question related to Nested
Question
4 answers
Hello all,
I'd greatly appreciate any help to clear my confusion about two-way crossed and nested design!
I am counting the abundance of each common genera of microalgae from the mangroves and tidal flats of 2 different sites, 1 sandy and oligotrophic, and the other muddy and eutrophic. The data that I have collected look like this:
1. muddy site - mangrove (n=6)
2. muddy site - tidal flat (n=8)
3. sandy site - mangrove (n=6)
4. sandy site - tidal flat (n=8)
And each set of data is a genus-abundance matrix.
I have always thought that my design is two-way crossed, but was just made aware that it could be a nested design, since the data obtained from say, muddy-mangrove is dependent on it being in the muddy site...
Is this a nested design, afterall? I read that sample sizes must be equal for a nested ANOVA, is that also a requirement for ANOSIM?
Thanks a lot in advance!
Relevant answer
Answer
Yes, you have sampled both levels of each factor (sediment sandy/muddy, mangrove presence/absence) for both levels of the other, so it is a crossed design.
ANOSIM doesn't require a balanced design (though imbalance may lead to a loss of power).
Comparing the R values in a 2-way crossed ANOSIM will allow you to assess the relative strengths of the effects of sediment (removing effect of mangroves) vs the effect of mangrove (removing the effect of sediment).
  • asked a question related to Nested
Question
3 answers
In gsem of STATA we can test random-intercept and random-slope models (multilevel) (see example38g in the manual). STATA MULTILEVEL MIXED-EFFECTS "me" deals with multilevel mixed-models, in particular MIXED for continuous outcomes.
I asked myself: Do I get the same results if I use gsem or MIXED? For the moment my answer is yes and no.....
In MIXED we have several options: we can use ML or REML estimation method; we can define different residual variance structures,....
I ran a gsem 2-level random-intercept model (id defines level 2 and session_coded defines level 1 nested within level 2) using own data
gsem (rd <- mpa_level i.session_coded i.order M1[id])
I found out that I get exactly the same results with the following mixed model
mixed rd c.mpa_level i.session_coded i.order ||id:, ml cformat(%9.4f)
However, using reml is prefarable; furthermore, an heterogenous residual variance better fits the specific data rather than the default. So the "best" MIXED model I would use is
mixed rd i.session_coded c.mpa_level i.order ||id:, reml residuals(ind, by(session_coded)) cformat(%9.4f)
With this model, the results are quite different.
My question: is it possible to write in gsem a model that is equivalent to this latter "more sophisticated" mixed model? Do you have any readings to suggest?
Why am I asking this question? Because in a second stage I would like to run multilevel-mediation analyses using gsem but ideally I would like to keep the level of "sophistication" that I have with MIXED (reml, residual variance, etc.).
Best regards,
Relevant answer
Answer
The technical support of STATA wrote me:
Currently, we don't have a command to estimate generalized structural equation models via REML. Also, residuals in -gsem- are assumed to be i.i.d., there is not an option to change this.
  • asked a question related to Nested
Question
5 answers
Can someone share their syntax for how to set the nested fixed effect in SPSS for the repeated measure MANOVA?
Relevant answer
Answer
Hello Hannah,
Can you be a bit more specific as to what your variables include (between, and within on the IV side; the DVs as well)?
Good luck with your work.
  • asked a question related to Nested
Question
2 answers
Hello,
I would like to measure provisioning rates in Eurasian Blue tits. My plan is to color ring them, so that I can distinguish between male and female.
In my system they breed in nest boxes, however I do not have the possibility to place a camera within a nest box. PIT tags are also not an option for me. Visual surveys can have problems because If the bird does not land on the nest box hole, then it would be impossible to know if it was a male or female.
I need a camera that could film at least 6h (with batteries). I plan to film at least 30 nests and to move the cameras around, so I may need about 12 cameras.
Of course I have a quality vs quantity vs cost trade off.
Somebody suggested using a security camera, but the problem is that there is no screen to see what you are filming and no WIFI for me to connect the camera to my phone in the field.
Others have suggested camcorders, but their models are no longer being sold and they can get pretty expensive.
Any technical suggestions will be super helpful.
Sincerely,
Chase
Relevant answer
Answer
Well Done !!! interesting...
  • asked a question related to Nested
Question
2 answers
After the estimation of nested logit using mlogit in R, I need to estimate the marginal effect or elasticity for each alternative levels of the covariates against the reference. Pls I would appreciate if anyone can help with the code.
Relevant answer
Answer
Take a close look at the attached Google search. Best wishes David Booth
  • asked a question related to Nested
Question
4 answers
Hi researchers,
Is it possible to perform nested GLM models or nested ANOVA of GLM models with >2 categorical variables in R, or does it make sense?
Thank you
Relevant answer
Answer
ANOVA or GLM needs at least one quantitative variable. Depending on your objective, you can try a quantitative conversion of your categories by the "as.factor" function.
  • asked a question related to Nested
Question
4 answers
Hey!
I am looking at the finding out if there is a significant difference in the number of predation events by dogs, foxes, and crab for two different turtle species (G+L), across three locations (W,A,N) in R.
the question I am trying to answer is what are the main predators for each turtle species , whether it varies across location, and whether greens or loggers are predated more (My prediction is that species L are predated more because they lay shallower nests, and that location W Suffers the most predation, and that foxes are the most prominent)
Im struggling to find what statistical test to use, and how to set up the data. Do I do individual tests for each and compare those results, or is there one statistical that can do all?
many thanks!
Relevant answer
Answer
You can go for ANOVA, DMRT, box plots, correlation, regression, PCA etc. in Rstudio.
  • asked a question related to Nested
Question
6 answers
When we are working with two-level control say the primary and secondary level of the grid, I have four PID controllers, two at the primary section and two at the secondary section. Now, for tuning purposes what should be the order, and how we can tune each controller co-officiants?
Relevant answer
Answer
Dear Rinku Kumar,
A cascade regulation is made up of two nested loops, the internal loop must be much faster than the external loop. The system can be broken down into two subsystems linked by a measurable intermediate quantity. A first loop, the slave loop, has as regulated quantity; this magnitude is intermediate. The second loop, the master loop, has the set magnitude. The controlled variable of the cascade control controls the setpoint of the slave control.
For more information about this subject, please take a look at links on topic.
Best regards
  • asked a question related to Nested
Question
4 answers
I am having difficulty understanding random stratified sampling when there are nested categories within them. Take for instance a size of 1000, and you are interested in sampling gender and smoking. Lets assum there are 500 females, so does that mean you create a first gender stratum with 500 females and 500 males. Subseqeuntly you randomly select participants from each gender category, and then create a second strata within each gender categories for smoker vs. and non-smoker. Then you select a random sample from each of these cateogory. Is that how stratified random sampling works? Because that sounds like multi-stage sampling to me? Please help I'm trying to visualise how it all works.
Relevant answer
Answer
From your second post I suggest you consult a sampling expert or simplify things so each sample is a simple random sample. I still would not be comfortable that I could solve that problem in a finite amount of time
Best wishes David Booth
  • asked a question related to Nested
Question
5 answers
Can I do Multilevel nested model analysis on SPSS software when I don't have continuous variables?
Relevant answer
Answer
Yes.
If your DV is binomial, you can use GENLINMIXED command (https://www.ibm.com/docs/en/spss-statistics/24.0.0?topic=genlinmixed-examples-command)
If your IV is categorical and your DV is continuous, you can use MIXEED command. (https://www.ibm.com/docs/en/spss-statistics/24.0.0?topic=reference-mixed)
Note, once you enter these GENLINMIXED and MIXED function in SPSS, it is no longer a simple point-and-click, meaning you will have to write some codes. If that's the case, it might be beneficial if you learn R or Python.
  • asked a question related to Nested
Question
6 answers
Mammals ravage the nests of artificial nesting birds. There are probably modern methods that display data from burglary attempts, etc.
Relevant answer
Answer
You could also make nutritional analyes of the predators (feaces, stomach contents). And of course direct controls like Johannes Mayer mentioned or Thermo loggers Florian Straub mentioned. However , nest observation with Fototraps or even better with video observation is the most precise method but with the highest workload.
I have not the rights to upload the texts here, but see:
ZSCHILLE J, STIER N, ROTH M, MAYER R (2014): Feeding habits of invasive American mink (Neovison vison) in northern Germany—potential implications for fishery and waterfowl. Acta Theriologica 59 (1), 25-34. https://doi.org/10.1007/s13364-012-0126-5.
STIER N, ZSCHILLE J, ROTH M (2005): Untersuchung zu den gebietsfremden Raubsäugern Marderhund, Waschbär und Mink in Mecklenburg-Vorpommern mit Forschungsschwerpunkt Mink. Zwischenbericht. Institut für Forstbotanik und Forstzoologie, TU Dresden. 21 S.
VOIGT U, SIEBERT U (2016): Prädation Niederwild. Abschlussbericht für die Untersuchungsjahre 2011-2015 Niedersächsisches Ministerium für Ernährung, Landwirtschaft, Verbraucherschutz und Landesentwicklung. Institut für terrestrische und aquatische Wildtierforschung, TiHo Hannover, Hannover. S.
VOIGT U (2016): Prädation in der Kulturlandschaft. Abschlußbericht Niedersächsisches Ministerium für Ernährung, Landwirtschaft und Verbraucherschutz. Inst. f. Terrestrische und Aquatische Wildtierforschung, Hannover. S.
KÄSELAU S (2021): To what extent do stomach content analyses provide information on predation on ground-nesting birds? MSc. University of Veterinary Medicine Hannover. 31 S.
  • asked a question related to Nested
Question
4 answers
Hi,
I am trying to run WRF with three nested domains of resolutions 18km, 6km and 2km.
I need the extent of the outermost domain to be 80 degrees longitudinally, ie from east to west, and 55 degrees latitudinally.
Are there any constraints to be kept in mind while deciding the extents of the inner domains. For eg, should the extent be some ratio of the extent of the parent domain? For my case, since the domain ratio is 3, should my second domain have a longitudinal extent of at least 27 degrees?
Is there any constrain like that, or can we choose the sizes, ie, extents of our domains as per the location of our area of interest that we plan to study?
Are there any other things/ constraints/ rules we need to keep in mind while deciding the domain configuration?
Kindly help me out with these queries.
Thankyou!
Relevant answer
Answer
Vijayan Gv It is not mandatory to follow the same criteria but in case if you get an error try to do it Because the same error I have solved in minecase. https://meteo.unican.es/trac/wiki/WRF4GTutorial2
  • asked a question related to Nested
Question
1 answer
Many software that handles nested logit regression such as R(mlogit) , stata (nlogit), python (pylogit,biogeme) with the exception of Gauss does not have the option of marginal effect as a post estimation test. However, the marginal effect for similar model such as multinominal logit, ordered logit etc can be executed using margin in R and stata and statsmodel in python. Does this really implies that marginal effect is not a relevant post estimation test for nested logit and if this is, I would love to have suggestion on the preferred pre - estimation and post estimation test for nested logit with references and preferred software of estimation.
Relevant answer
Answer
It seems that nlogit sofware by W. Greene allows you to compute the marginal effects.
  • asked a question related to Nested
Question
3 answers
Dear scholars, can anyone recommend a python package that estimates nested logit together with the marginal effects of each covariates. I have been trying pylogit but I don't seem to see the function for nested logit marginal effects. Any another free and easy software is also welcomed.
Relevant answer
Answer
Thanks so much Prof @Mohialdeen Alotumi. But I'm not sure biogeme does marginal effect after nested logit.
Thanks a bunch Prof @David Eugene Booth, I have employed R but I seems to be getting issues using the effect function for marginal effects as it seems to be only good for multnominal logits. In the same vein, Gauss is a paid software and to free as indicated in my questions.
  • asked a question related to Nested
Question
3 answers
I have three patients and three controls and I need to calculate the number of biological experiments I must perform. Thank you.
Relevant answer
  • asked a question related to Nested
Question
5 answers
Hi everyone! I have a statistical problem that is puzzling me. I have a very nested paradigm and I don't know exactly what analysis to employ to test my hypothesis. Here's the situation.
I have three experiments differing in one slight change (Exp 1, Exp 2, and Exp 3). Each subject could only participate in one experiment. Each experiment involves 3 lists of within-subjects trials (List A, B, and C), namely, the participants assigned to Exp 1 were presented with all the three lists. Subsequently, each list presented three subsets of within-subjects trials (let's call these subsets LEVEL, being I, II, and III).
The dependent variable is the response time (RT) and, strangely enough, is normally distributed (Kolmogorov–Smirnov test's p = .26).
My hypothesis is that no matter the experiment and the list, the effect of this last within-subjects variable (i.e., LEVEL) is significant. In the terms of the attached image, the effect of the LEVEL (I-II-III) is significant net of the effect of the Experiment and Lists.
Crucial info:
- the trials are made of the exact same stimuli with just a subtle variation among the LEVELS I, II, and III; therefore, they are comparable in terms of length, quality, and every other aspect.
- the lists are made to avoid that the same subject could be presented with the same trial in two different forms.
The main problem is that it is not clear to me how to conceptualize the LIST variable, in that it is on the one hand a between-subjects variable (different subjects are presented with different lists), but on the other hand, it is a within-subject variable, in that subjects from different experiments are presented with the same list.
For the moment, here's the solutions I've tried:
1 - Generalized Linear Mixed Model (GLMM). EXP, LIST, and LEVEL as fixed effect; and participants as a random effect. In this case, the problem is that the estimated covariance matrix of the random effects (G matrix) is not positive definite. I hypothesize that this happens because the GLMM model expects every subject to go through all the experiments and lists to be effective. Unfortunately, this is not the case, due to the nested design.
2 – Generalized Linear Model (GLM). Same family of model, but without the random effect of the participants’ variability. In this case, the analysis runs smoothly, but I have some doubts on the interpretation of the p values of the fixed effects, which appear to be massively skewed: EXP p = 1, LIST p = 1, LEVEL p < .0001. I’m a newbie in these models, so I don’t know whether this could be a normal circumstance. Is that the case?
3 – Three-way mixed ANOVA with EXP and LIST as between-subjects factors, and LEVEL as the within-subjects variable with three levels (I, II, and III). Also in this case, the analysis runs smoothly. Nevertheless, together with a good effect of the LEVEL variable (F= 15.07, p < .001, η2 = .04), I also found an effect of the LIST (F= 3.87, p = .022, η2 = .02) and no interaction LEVEL x LIST (p = .17).
The result seems satisfying to me, but is this analysis solid enough to claim that the effect of the LEVEL is by no means affected by the effect of the LIST?
Ideally, I would have preferred a covariation perspective (such as ANCOVA or MANCOVA), in which the test allows an assessment of the main effect of the between-subjects variables net of the effects of the covariates. Nevertheless, in my case the classic (M)ANCOVA variables pattern is reversed: “my covariates” are categorical and between-subjects (i.e., EXP and LIST), so I cannot use them as covariates; and my factor is in fact a within-subject one.
To sum up, my final questions are:
- Is the three-way mixed ANOVA good enough to claim what I need to claim?
- Is there a way to use categorical between-subjects variables as “covariates”? Perhaps moderation analysis with a not-significant role of the moderator(s)?
- do you propose any other better ways to analyze this paradigm?
I hope I have been clear enough, but I remain at your total disposal for any clarification.
Best,
Alessandro
P.S.: I've run a nested repeated measures ANOVA, wherein LIST is nested within EXP and LEVEL remain as the within-subjects variable. The results are similar, but the between-subjects nested effect LIST within EXP is significant (p = .007 η2 = .06). Yet, the question on whether I can claim what I need to claim remains.
Relevant answer
Answer
yes of course three way ANOVA
  • asked a question related to Nested
Question
2 answers
We are working with white-winged snowfinches, alpine bird species breeding in rock crevices, roofs and skilift pylons and struggle to access nests in some of the deeper cavities (50 cm to 1 m). We are using an endoscope, but it is often difficult to access nests in deep cavities when they are really contorted (as we dont know the internal structure of the cavities).
We are mainly interested in counting the number of chicks, but also to place ibuttons for temperature measurements if someone has an idea how to place (and retreat!) them.
I am interested to know which methods people working on similar cavity-breeding birds (preferably rock crevices, as we are facing unique problems ina ccessability and cavity structure as f.i. woodpeckers will not have) use to gather nest information (if at all?).
Thank you very much in advance, Christian
Relevant answer
Answer
To anwer solely to the problem of access to the nests hole/entrance in cliff/rock faces habitat, I can suggest you the single rope access (from above or below, it depends by the general context). We used this tecnique to access the rock face habitat to study and monitoring one rare alpine butterfly species:
  • asked a question related to Nested
Question
4 answers
Hi,
I have problem to choose i_parent_start and j_parent_start values in order to get the most inner domain to surround a given area/zone with wanted dimension (e.g: 10km*10km).
I want to compare collected data and that simulated using WRF.
Relevant answer
Answer
Hi every one,
I would like to ask you how to chose parameters/values in namelist.input for a given zone (e.g: tropical zone such as sub-equatorial African region). I attach my namelist file I am trying to use now.
  • asked a question related to Nested
Question
6 answers
Anderson, de Palma & Thisse have demonstrated the equivalence between a demand function derived from a CES direct utility function and a discrete-continuous logit model. I am pretty sure I have once seen that this can be extended to the nested extensions of CES utility functions and logit models. But I have lost track of the reference and I somehow do not find it on the web. Any hints?
Relevant answer
Answer
Perhaps also this paper by Frank Verboven
  • asked a question related to Nested
Question
8 answers
It has long been recognised that bumble bees most often nest in abandoned mammal (usually rodent) nests, and I believe various researchers have tested the effects of mammal scent in attracting queens to field hives, but I'm not aware of any positive results. However I have not been keeping up with literature for a while and may have missed it.
Do you know of results confirming the effect of mammalian odours?
Relevant answer
Answer
Dear Nelson,
this is a very interesting technical question which I personally never thought of. To my knowledge, the reason why bumble bees very often nest in abandoned mammal (mice and voles) nests is that they cannot dig themselves. According to many links available on the general internet it is generally accepted that some bumble bees can faintly smell the mice and voles that once built the nest and follow this scent until they find the entrance. Unfortunately I could not yet access a scientific article in which this behavior has been proven.
Good luck with your work!
  • asked a question related to Nested
Question
2 answers
To ask my questions, I need to set up a hypothetical experimental design.
Let's say that I am interested in participant evaluations of art made by two different people (famous artist A and unknown artist B)...each artist has painted 10 paintings in the same 10 different colors/styles (e.g. one blue sad painting, one red angry painting, one yellow happy painting, etc). Thus, I now have 10 pairs of incredibly similar paintings, half from each artist.
Under the assumption that participants can't tell which paintings came from which artist (pretested), I am now curious as to whether or not using the name of each artist as a label will influence participant evaluations of skill on a 1-7 Likert scale. Thus, half my participants see the true labels and half see false (totally reversed) labels.
Here are my questions:
What kind of multi-level model (if any) would be most appropriate in this setting? Nesting within individual? Nesting within pairing (e.g. red pair, blue pair, green pair)?
Please correct me if I am wrong as I am very new to multi-level analysis. So far, it seems like the answer is to try both types of nesting using a random intercept and randoms slope?
Relevant answer
Answer
Mulitilevel model is A structure based on many different concentriclevels which can be used to construct many different shapes.
Multilevel models are particularly appropriate forresearch designs where data for participants are organized at more than one level (i.e., nested data). The units of analysis are usually individuals (at a lower level) who are nested within contextual/aggregate units (at a higher level).
Multilevel models recognise the existence of such data hierarchies by allowing for residual components at each level in the hierarchy. For example, a two-level model which allows for grouping of child outcomes within schools would include residuals at the child and school level. Thus the residual variance is partitioned into a between-school component (the variance of the school-level residuals) and a within-school component (the variance of the child-level residuals). The school residuals, often called ‘school effects’, represent unobserved school characteristics that affect child outcomes. It is these unobserved variables which lead to correlation between outcomes for children from the same school.
  • asked a question related to Nested
Question
1 answer
Hello,
(I hope i made sense and thank you so much for your help. I am an undergrad student and a beginner and it would really help with clarity.)
I am working on a correlational meta-analysis paper. One of the variables "Empathy" is organised in three subgroups and the other variables has outcomes that are more than one i.e. effect sizes from the subscale elements correlation with the subgroup of empathy.
So, if empathy has three subgroups - x , y and z and the second variable, say measures professional competency using a scale that has dimensions like, working speed, resilience and if i have effect sizes from all of these groups like, x with working speed, x with resilience and so on. Would that make a multi-level study?
Relevant answer
Answer
Multi-level modeling is mainly used when you have samples from different clusters (e.g., countries or districts. I could not understand your question properly so it is hard to say if you need multilevel model.
  • asked a question related to Nested
Question
2 answers
Hi, I have been trying to run the WRF model for 24 hours over a month (September 2018). I am using three two way nested domains (9km, 3km and 1km) with 63 explicitly defined vertical levels over a part of peninsular India. My timestep is 30. I am getting cfl errors only on some days, while for others the model run is completed without any errors. I have used the same domains and other runtime options for the month of January, 2019 as well and had no issues there. What might be the issue here and how can I attempt to resolve it? Please help me out.
Relevant answer
Answer
I changed my time step to 18 and it worked. Thankyou!!
  • asked a question related to Nested
Question
5 answers
Asking for a friendly soul that knows how to fix this error or that understands why this is appearing.
Not exactly sure what happened but this error appears every time I try to do a GAM with random effects (bs="re", with mgcv package). This is strange since appears not only to new models but even to models that previously worked (multiple times). I made sure the data has no NA's, scientific data, or random formulas. Also, I am not using the date format to avoid errors has previously worked as it is.
I also tried to transform the data into a data frame via as.data.frame(x) but the same error occurred.
I have been playing a bit with the formula and it appears that every time the random effects bs="re" are present, either the 2 of them (Site, State) or only one of them (Site), it is when the error occurs. If I take them completely out of the formula it works perfectly.
I am thinking that could be:
  1. Some incompatibility with another package that I may have installed but tried to solve this with no effect. Removed all the most recently installed packages and the error persisted.
  2. Other could be any update to the mgcv package?
Does anyone have an idea on how to fix this or why this is appearing
```
gam_2a <- gam(Total_Items ~ s(DayI0, k=14) + s(Site, State, bs="re"), offset(log(EffortDayC)),data = x,family=poisson(link="log"),method = "REML")
```
Description of the variables:
Total_Items = Number of items of debris found per event;
DayI0 = Number of days since first clean up (numeric);
Site = Site of sampling (Sites are within States);
State = State of sampling;
EffortDayC = Effort(Length of the beach, number of volunteers, duration of sampling)*DayC(interval of sampling);
See the str (data) below.
Relevant answer
Answer
Hi, difficult to know without looking at your code or knowing what data you are using.
I left my question because mgcv was having incompatibility with another package (see above), both had the same function name. That could be one of the problems? But I am guessing here. Maybe try to run mgcv:gam(x~y...) and see if the results persist. Another solution would be to ask a question on stack or crossvalidated.
:)
  • asked a question related to Nested
Question
4 answers
Hi,
I am trying to set up WRF model and I would like to specify explicit eta levels. My study will primarily be focused on storms and the boundary layer, so ideally, I would like to have very high resolution upto 3 km altitude. I am using three domains of 9km, 3km and 1km resolutions, with two way nesting. I am unaware of any thumb rules we need to follow or factors we need to keep in mind while deciding the vertical levels. Can you please educate me about them and help me out?
Also, I was told that, in case we don't want to specify eta levels, the number of vertical levels needs to be
Height of model top/ (0.1*Resolution of innermost domain)
Can you please help me understand why this is the case?
My model top will be around 20km (50 hPa), so if I go by this rule, I will end up using 200 vertical levels. Please help me understand why it is necessary to have these many levels.
Thankyou.
Relevant answer
Answer
A related issue is the consistency between vertical & horizontal spacings. A paper was written by Mahrer in the 90s and another by by Fox-Rabinovich & Lindzen
All the best
  • asked a question related to Nested
Question
8 answers
I am exploring passive monitoring methods to determine nest box use. The design will combine regular physical visits to each nest box, a subset of boxes with camera surveillance, but the question is what to do with the others.
I have considered using a simple temperature logger (e.g., ibutton) to record changes in temperatures within boxes. However, this is complicated by the likelihood each box will have its own ambient temperature profile. This would have to be determined for each box and over seasons to allow calibration and be able to differentiate the presence/absence of a homeotherms using the box (the focus of the study). This is further complicated due to some of the species may enter torpor while in the box (resulting in a false negative).
I would be grateful for any suggestions. Any device/method will need to be simple, cheap, and low maintenance.
Relevant answer
Answer
Hi William,
Thanks for your story.
The boxes I install are rarely more than 3m above ground (they are in rehabilitated areas so nothing much higher than 3m for a decade or so). A pole camera would be a bit of overkill for this work, but from what I understand the cameras used in those setups are quite good quality (optics and resolution). I tend to rely on endoscopes for minimal intrusion. The problem is getting high quality equipment that isn't going to cost me the better part of the research budget. I am trialing a whole slew of options from ebay (cheap and cheerful) and have so found one particular product (unbranded) that seems to be better than the others (a wifi version that comes with 1.5m, 2m, 5m semi-rigid cords).
The problem for me is being able to monitor potential use for all those times we are not there poking our endoscopes in the nest box. Having cameras is fine but is not always possible due to the density of vegetation at our sites, i.e., can be very dense and any moving vegetation will set off the cameras. I have considered ibuttons to measure temperature changes but it would be difficult to calibrate to ambient temperature on a 24hr/7day/365 day annual cycle.
I guess I am looking at what others may have considered using in the past. I think I mentioned previously a design for a SMART nest box, although I do think this may be one step too far for the sort of studies we do.
Thanks again.
  • asked a question related to Nested
Question
7 answers
Hello all-
I am trying to only detect (meaning no relative expression yet) a certain marker via taqman probe in DNA from old FFPE samples. I have tried to "increase my signal" by performing a nested PCR by running the profile without the probe and then purifying the PCR product (column based-Qiagen). I then went on to the secondary PCR using the Taqman probe. My detection was clean but low (high Ct values). The nested workflow resulted in pretty much the same Ct values as a single run (non-nested). I fear I am losing anything I am gaining during the purification process.
Is it absolutely required to purify between primary and secondary PCR's when doing a nested process?
Thanks!
Andrew
Relevant answer
Answer
Purification may not be needed if your DNA was extracted with high purity. You can proceed to secondary PCR. We have done this successfully without purification, yet with excellent outcome.
  • asked a question related to Nested
Question
4 answers
Fellow Researchers,
I am currently running an experiment where primary cell lines derived from 4 patients are being cultured in 2 different conditions. I am examining expression levels of several genes in 3 technical replicates in both conditions and trying to find out whether change in culturing method has a signifcant impact on them considering all cell lines.
I am using Nested t-test for my statistical analyses, but having doubts whether or not it is the right choice since data from the same cell line in diffrent conditions is not paired. Would you suggest me to change the test or keep using it? What alternative would you suggest?
Relevant answer
Answer
if more than2 groups, you can use nested anova with graph pad
  • asked a question related to Nested
Question
12 answers
I've conducted an RCT in which I'm testing the effect of a group mindfulness intervention on depressive symptoms. Only one group was running at a time so there were four study waves, with each wave of participants being randomized to intervention or control. Outcomes were measured bi-weekly for 6 months. I'm testing the effect of intervention using PROC MIXED in SAS with bi-weekly assessments nested within participant identified in the repeated statement.
A reviewer has suggested that I include treatment wave as a random factor in the model. However, the interaction between treatment and study wave (as fixed effects) is not even close to significant (p = .99), suggesting that the effect of treatment is the same across waves. Is this sufficient justification to keep my analyses as they are and not include treatment wave as a random factor? Thanks!
Relevant answer
Answer
For me there are two issues here - conceptual (in relation to target of inference) and practical (what can be estimated).
In relation to the Centre's advice (which I did not write!), likelihood procedures can have real problems of estimation (achieving convergence) when the number of groups is small. Full uncertainty modelling via (say) MCMC does not usually suffer from this but you usually end up with wide (asymmetric) credible intervals for the estimated variance as this term cannot go negative (producing a positively skewed posterior distribution). You may then not able to say much about any differences.
Conceptually, if your classification is 'fixed' such that the categories exhaust the possibilities ( there are only two types of school such that private and public are not a sample of all possible types of school) then I would include a dummy in the fixed part of the model to get the difference in the means. Conversely if the categories are representative of wider entities (eg schools) then I would treat as a random classification and as a level in a multilevel model. You are then estimating the variance summarising unexplained between school variation in general.
Returning to the original question, I do not see the four waves as being meaningfully representative of all possible waves, so I would include as a set dummies in the fixed part. I am then trying to infer to those 4 specific waves which might have certain characteristics (eg pre and post Covid) that might affect the results for the key variable of interest. Of course, I could see some making the opposite case!
  • asked a question related to Nested
Question
9 answers
Hi,
Is it possible in GENLINMIXED (SPSS version 25) to specify a model with two crossed random effects (not nested) for a binomial outcome variable? (It is possible with MIXED).
but I would prefer using SPSS
PAtrick
Relevant answer
Answer
John P Capitanio nice! good luck with your analyses :-)
  • asked a question related to Nested
Question
3 answers
I am trying to analyze a model on SPSS with:
- one within-subject factor with 2 levels.
- two between-subject factors: one categorical (2 levels) and another continuous.
- also, we are hypothesizing an interaction term between the two (the categorical and the continuous variables) between-subject factors.
I am having a hard time running the model on SPSS. I have found recommendations with similar problems asking to run a nested model (not sure how to run that on SPSS). However, I am not sure what model to run and how to run it on SPSS.
Relevant answer
Answer
If it is something like a continuous variable measured at baseline and after a fixed time in individuals with age and gender as between-subject variables, then you can use linear regression. The continuous measurement at the fixed time will be your dependent variable and age, gender, and baseline measurement will be the independent variables in the model.
  • asked a question related to Nested
Question
3 answers
Hello!
I have a dataset of n=3000 nested within 8 countries with approximately 200 or 400 responses in each country. I originally planned to perform multilevel modelling with 4 dependent variables (DV) as fixed effects in SPSS.
The DV variables are responses in a scale of 1-100 and this kind of variables is treated as metric in psychology.
However, all my DV and the error terms are clearly skewed or clearly curtotic. My questions are:
1. I have read that in some cases the size of the dataset or the number of nesting groups allow to use the general linear model. Does it make sense, however, to do so if the dataset clearly shows extreme tendencies? It looks to me like clearly different distributions, but I am not sure how to define them. Should I regard them as continuous distributions?
2. Am I right to think that data transformation is not a good option if there is a different form of distribution?
3. What would be the advantages and disadvantages of bootstrapping or simulation?
4. What would be good reasons for using a generalized linear or a mixed model?
5. Would it be appropriate to perform a factor analysis of the four DV. If not, are there alternatives?
I would appreciate if someone can answer any of these questions or suggest some not very technical references !
Relevant answer
Answer
Thank you Philip D DeWitt and Abdulrazzag Falah for your valuable replies!
Mahalanobis distance works quite well. There are still a handful of outliers but I suppose that they should not play a big role in a sample of over 3000 persons.
Philip D DeWitt Thank you also for your publication! I did not have time to read it yet, but I think it will add to my understanding as much as your thorough explanations. You are right that countries should be a fixed effect. It takes for me some time until I grasp such a new procedure like multilevel modelling.
  • asked a question related to Nested
Question
3 answers
HI all,
I have been working with daily diaries data ( 6 emotions of which 3 positive and 3 negative) were assessed for 30 days. These observations (1level data) are then nested within subjects (2nd level data) who are further nested in three groups (approx.50 in each group, 3rd level data).
What am I struggling with is finding out how to manage the time covariate in 1level data because the daily observations were further nested in odd and even days and then three groups of people toward who the participants were asked to indicate the feelings for.
In short,
on odd days a person was asked to indicate 6 feelings ( disgust, empathy, anger, sympathy, regret, respect) toward x1, s1, s2, s3, s4, s5, a1
on even days indicate the same six feelings toward x2, s6, s7, s8, s9, x3
As you can see, x represents one type of group of representatives, s second type and a1 stands alone.
My role is to find out if there is any difference in intraindividual variability of emotions between the 3 groups.
I will appreciate any tip how to manage all this complexity. Thanks so much!
Relevant answer
Answer
FFFF
  • asked a question related to Nested
Question
1 answer
I am using the NLME package to run regressions using lme(DV~IV).
I am including random intercept and random slope for two IVs, all of these by subject.
I have it currently written as lme(data = data, fixed = DV ~ X1 + X2, random = reStruct (~1+X1+X2 | subject).
When switching the ordering of X1 and X2 in the random structure, I get different results, which makes me believe that there is some sort of nesting.
There is very little information (that I can find) on multiple predictors (I find plenty on code for random slope for 1 predictor), especially for NLME. Any help understanding what's going on and how to properly write the code would be tremendously appreciated.
Relevant answer
Answer
  • asked a question related to Nested
Question
2 answers
I'm using generalized linear mixed models (GLMMs) with the package nlme (Pinheiro et al., 2018), employing a Gaussian distribution. My study only has 6 samples with 72 replicas (Petri dishes). After some considerations, we have a fix factor with 2 levels and two random factors with 2 and 6 levels. The subjects are soil fungi that were given different edaphic parameters. My question are: Is it proper to add other parameters as random factor considering our reduced number of samples?
Relevant answer
Answer
In principle, you can add as much random factors as you like. The benefit would be, that with each random effects factor you can detect underlying systematic variation within your samples. If you think it is reasonable to assume that each factor adds to explaining this variance than you can go ahead including more random factors. However, with each random factor you risk overfitting your data and that your model can not be computetd.
You might thus consider identifying relevant factors beforehand (e.g., by correlation matrix) in order to find the factors that are most likely to explain the most variance. You can also compare models on the basis of information criteria (AIc, BIC, ...) which also penalizes random factors that do not add explanatory power to the model.
  • asked a question related to Nested
Question
1 answer
Hi,
I fitted a Gamma GLMER to predict the amount of organic matter (OM) stored in plants using plant area (PA) and species as fixed effects. I collected the plants in different trees and different forests, thus I included these factors as random effects (tree within forest).
This is the code that I used to fit the model
glmer(OM~ PA + Species + (1|Site:Tree), family = Gamma(link = "log"))
Now I would like to present the statistical model and I am following the protocol proposed by Zuur and Ieno (2013). I used the following equation to describe the model.
OMijk ~ Gamma (µijk)
E(OMijk) = µijk
var(OMijk) = μ2/ν
Sitei ~ N(0,σ2site)
Treej ~ N(0,σ2tree)
log(µijk) = PAijk + Speciesijk + Sitei + Treej
I think this equation does not reflect the nested structure of the random effects.
It is the presentation of my model correct?
Thanks
Relevant answer
Answer
Interested
  • asked a question related to Nested
Question
2 answers
Consider a polytomous categorical dependent variable Y, which can assume values equal to 0, 1, or 2.
If, for instance, the state 2 is conditioned to the occurrence of the state 1, the multinomial logistic regression remains an option, or am I forced to use the hierarchical/nested one?
The core of my question is: if one of the considered states is conditioned to another one, will the multinomial way be biased?
Relevant answer
Answer
The multinomial logit model assumes that one choice is independent of others ( independence of irrelevant alternatives IIA).
If this is violated, other alternative models should be applied. Think about Mixed Logistic regression that solves this problem to an extent. This is even better than nested logit models.
  • asked a question related to Nested
Question
2 answers
We are currently doing research on heron nesting/reproducing in an urban context. Any examples will help a lot. Thanks!!
Relevant answer
Answer
Thanks very much! In my case here (Kunming, China) heronries have boundaries defined/interrupted by artificial structures, roads for example. It seems that to "cross" them would mean failure in nesting. We once found a pair or two Little Egrets attempting that way, then after egg laying one day the parents vanished with broken eggs found on the floor.. Besides those very few nests had been built close to an entertainment facility, there are also natural enemies, squirrels and cats that could mess up the breeding cycle. I'm interested in linking examples together to see what all the possible factors could be underlying heronry disappearance and life span, because under natural (ideal conditions) one seems to exist for a rather long time. Thanks again for sharing your study :)
  • asked a question related to Nested
Question
1 answer
I would like to ask a recommendation of a statistical test to answer a question related to an unusual data structure.
I am testing if birds change nest parental care behavior depending on offspring health status. I video recorded nests in the field, and calculated the proportion of time that parents of each nest spent on different behaviors types (eg. Brooding, Feeding or Absent). In this situation, if a parental spends more time on “Brooding”, the proportion of time on “Absent” will decline. In other word, the frequency of each behavior is not independent (and the sum will be always 1).
Furthermore, my data have several structures. Nest can have 1,2 or 3 nestlings. Parental care could be influenced by nestling age. Offspring could be not infected in a first record but become infected in the next one. Video records have different lengths (it depends of battery duration of each record, but is usually from 50-70 min).
Relevant answer
Answer
I am not aware of any particular GLMM for modeling this specific type of data, but if you use hierarchical Bayesian modeling with a Dirichlet distribution for your dependent variable, all should be ok :)
  • asked a question related to Nested
Question
7 answers
Im refering to Andy Field's example in his book Discovering statistics using SPSS, 3rd edition, page 728, where he gives an example of a data structure with level 1 variable is a memory recall question. The question is how many memories can the student recall out of 15?
However, Field does not go on to explain this example, this is exactly what I am looking to structure in my own data.
I have 3/11 choices that respondents selected on a question. If the three choices (or three memories from Andy's example) are to be entered as level 1, how will I set up my data in SPSS. Im interested whether the selection of those choices had an impact on the outcome variable. Since these selections are not independent of each other they ought to be nested within the individual. Does anyone have anu guidance?
I am attaching the image of Andy's data structure.
Relevant answer
Answer
A few more things yo need to know about multilevel modelling
1) you need replicates that is the lower level is a repeated measurement of the higher level e.g. pupils in school ; teeth in mouth . If you do not have replicates you cannot multilevel model. EG if you only have 1 person in each house , you cammot
  • asked a question related to Nested
Question
8 answers
Dear colleagues,
could somebody recommend publications dedicated to efforts and results on increasing the nesting success in waterbirds preferring low banks for breeding (waterfowl, gulls, waders, etc) in habitats being vulnerable of severe water table variation? I mean samples for constructing artificial islands/banks, floating islands, or artificial nests; attracting birds to safer but unusual habitats with sound playing and dummies; and any other measures... and their results. In other words, what was been made ny humans for more number of successful nests in such unstable circumstances, and how much effective were such efforts?
Results, which were published in journals or at Internet pages, are interesting. Of course, I'm most interesting in trials being successful, but unsuccessful trials add us some experience as well. Having already found few publications on this subject, I'd like to find more ones though.
  • asked a question related to Nested
Question
1 answer
I would be happy for your help in choosing the right test.
I have 2 independent groups of trees. Each group has 6 trees of the same type. Each group received a different type of irrigation. For each tree the trunk diameter was measured daily for 30 days. The measurements were performed in July and November for 4 years.
I want to test the main effect of the type of irrigation, the main effect of the season and the interaction effect between the two. Which model should you run? How to treat a the within subject factor?
I understand that there are two between subject factors and two within subject that one is nested within the other.
Avshi
Relevant answer
Dear Colleague
you can try GLM to see the effect of irrigation, season and tree. regards,
Redimio
  • asked a question related to Nested
Question
5 answers
Hello to the COMSOL experts,
is it possible in COMSOL Multiphysics to update the model parameters after an optimization based on the results of these optimization? (Ideally without using Livelink for Matlab due to license limitations.)
An example to illustrate: Say I have some model whose geometry depends on the global parameters a, b, c.
Case 1:
I run a standard Parametric Sweep over a, and for each a I run a nested Optimization to find an optimum b = b_opt to minimize some objective function X. Then for each a I have a b_opt. This works nicely!
Case 2:
Now I want to include another optimization for some objective function Y, using the parameter c. I don't want to optimize for X and Y at the same time with parameters b and c, because they are nearly independent. I rather want to optimize X with b, acquiring b_opt, and then Y with c while using the previously determined b_opt as value for b. This is computationally much quicker.
It is of course possible manually, i.e. running the first optimization, looking at the result and assigning b_opt to parameter b, but since I have the outer parametric sweep over a I would like to let COMSOL take care of this automatically.
tl;dr
What I want COMSOL to do:
for each value of parameter a (Sweep):
- Optimize objective X with parameter b, this delivers b_opt
- Assign b = b_opt (and keep constant) during following optimization
- Optimize objective Y with parameter c, this delivers c_opt
then for each a I would have one b_opt and one c_opt
Does somebody know how to accomplish this? Many thanks in advance!
Hermann
Relevant answer
Answer
If I understood properly you want to achieve the optimization for different cases of a, I think you can do this by using the parameter switch in your optimization rather than a common sweep over parameters. You can run the optimization of the different cases in that way. Check this example from COMSOL:
  • asked a question related to Nested
Question
3 answers
I have a big data which contains 4787 Observations and almost 100 variables. Questionnaire has some nested questions like selected respondents are asked to Answer Q#2 if they have answers Q#1 as YES and Q#8 would be answered by those who answered Q#4 as YES, like that data is shrinking and missing values are increasing. So, how to handle this kind of missing data in R which are systematic missing not the user-missing data.
Firstly, if I am deleting all the observation with NA, it results in losing 75% of the data and losing good data points.
Secondly, Mice package in R is for user-missing data ( situation in which respondent failed to answer the question).
Kindly help in this regard
Relevant answer
Answer
Hello Saeed,
This type of missing data is ignorable, since response-contingent questions (e.g., Do you own an automobile? If so, what brand?) that are properly skipped avoids having unqualified respondents give answers to questions.
So, if you are engaging in an analysis that involves one or more response-contingent questions, you are necessarily restricted to those for whom the question applies. This usually means a subset of the total sample.
It's not a flaw; it's nothing that would require imputation.
Good luck with your work.
  • asked a question related to Nested
Question
3 answers
Dear All,
I am writing a proposal entitled: Variables Affecting the Perceptions of Students toward their Native English Speaking Teachers (NESTs) and Non-Native English Speaking Teachers (NNESTs). The study aims to answer: 1. What are the perceptions of students toward their NESTs and NNESTs? 2. What are the personal variables that affect their perceptions?
Perception is measured through the 39 statements answerable by a 5-point Likert scales: agree, strongly agree, neutral, disagree, and strongly disagree.
I will test the hypothesis: There is no significant relationship between the students' personal characteristics/variables and their perceptions toward their NESTs and NNESTs.
Personal variables include:
1. Gender (male and female)
2. Religion (1-Islam; 2. Christian; 3. Hindu, etc.)
3. Mother tongue/first language (1-Arabic; 2-Spanish; 3. Mandarin, etc.)
4. Class level (4, 5, 6)
5. Country of origin
6. Age
7. Length of stay in Canada (year)
I would highly appreciate if you could you tell me the appropriate statistical tools to be employed, considering the nature of the data.
Many thanks,
Albert
Relevant answer
Answer
Hi Albert Maganaka , since "perception" is a construct (not directly observable) that you are trying to measure with 39 questions, you may want to use:
1) Factor analysis to synthetize the 39 answers into 1 or 3 measures of perception. As your variables are categorical, you may need to use categorical PCA or nonlinear FA - but some people will use simple factor analysis or PCA since you have 5 points in your Likert scale (i.e. if you are ready to assume that your data can be treated as scale-level data).
2) Then you can use a t-test to measure if the synthetized measures of perception are different on average for NESTs compared to NNESTs. Maybe you want to consider here a non-parametric test, too, as e.g. Kruskal-Wallis, depending on the empirical distribution of the condensed measures of perception.
3) You can use regression analysis to regress the the synthetized measures of perception against the personal variables.
  • asked a question related to Nested
Question
6 answers
I built a two levels hierarchical data like parents in families. I want to summarize my data. I have 100 parents nested in 34 families and I used variable such as parents gender and age in level 1 (individual level) and family income, family structure as level 2 (family level variables).
If I want descriptive statistics for each level i.e., individual and family level, should I built two table: 1 with level 1 stats using 100 as denominators for means and a another table with level 2 variable using 34 as denominator for calculations?
My head tells me to check with survey Package in r for complex survey design.
Can any one help me?
Thanks
Relevant answer
Answer
You probably could use the Maximum likelihood (ML) and restricted maximum likelihood (REML) estimation. Type I and Type III sums of squares can be used to evaluate different hypotheses. Type III is the default.
Do you suspect there to be correlated or non constant variability?
Then you can use the GLM Univariate or GLM Repeated Measures procedure.
Also you can alternatively use the Variance Components Analysis procedure if the random effects have a variance components covariance structure and there are no repeated measures.
  • asked a question related to Nested
Question
2 answers
I have to prepare the slides of pollen which I have collected from the nests of native solitary pollen bees. The samples are preserved in 70% ethanol as pollen mass itself. I am looking for a standard procedure to prepare pollen slides for taking their pictures in a scanning electron microscope.
Relevant answer
Answer
Thank you Sir
  • asked a question related to Nested
Question
5 answers
Hello everyone, I am planning to use camera to monitor activities on Nest of Asian Woollyneck. It nests on Tree (Platform), of about nest height 15-35 m. Which camera could be effective for this work ? Please recommend.
Relevant answer
Answer
I'm preparing a bit the same project, but for monitoring falcons, and found this solution: https://www.wildlifemonitoringsolutions.com/browning-2020-patriot.html?SID=igrnva9c171ks51euc396bgr27&___store=english
Probably it's helpfull for your project too
  • asked a question related to Nested
Question
7 answers
I have a excel sheet with positive and negative value. I have 4 grades to be assigned. How can I use a formula to assign the grades? I have tried using the IF nested function but due to negative value I am unable to do so. I have used this formula (IF(B4>89,”A”,IF(B4>79,”B”,IF(B4>69,”C”,IF(B4>59,”D”,”F”)))))
Can you have a look at the excel sheet below? the number in bracket refers to the score.
Thank you
Relevant answer
I think using many IF in formula is not a good t practice. I suggest to use INDEX & MATCH and create the scale on a separate sheet. Please find the attached file with my solution. This approach is more flexible. For example, as far as I know, it should be use "E" for scores which are between 0 and 30, and you can just add it to the sheet and will work.
  • asked a question related to Nested
Question
4 answers
I want to use linear mixed model in R program. I have many explanatory variables and some of them are nested. I read about this but I did not find the correct R coding. Is it possible to do the same code as the generalized linear model but adding the random effect. If so, how can I right it in R?
Sincerely,
Yassine.
Relevant answer
Answer
You can fit the linear mixed-effects model using the R package 'lme4'. You can find the details of this package here https://cran.r-project.org/web/packages/lme4/vignettes/lmer.pdf
  • asked a question related to Nested
Question
5 answers
I want to measure canopy area of nesting trees used by lesser adjutant stork. It nests on trees of height above 15 meter in general. Preferred tree is mostly the bombax ceiba (silk cotton) tree.
Relevant answer
Answer
@Santosh Bajagain,
Please take a look at the article below, especially its methodology section.