vegans - Science topic

I am also interested how to perform a two-way ANOSIM in R (ideally using vegan package). Any reply to this?

So far, I did it using PAST software (https://www.nhm.uio.no/english/research/resources/past/) but I would appreciate an R-code.

The attachment needs a short explanation. I DO wish to edit the older version of a presentation I had given four years ago, and include references to the Pandemic (which back then had not yet happened which is why it was "missing" from the talk I had given then, and I was hoping a current response might come forth in a timely manner in time for me to do a NEW MS PowerPoint presentation) but the problem is in the timing, because it will be occurring in just merely four days' time from today, this Saturday at the VBS Synagogue's Library Minyan on the 10th of June, 2023.

Dear Juan,

I have not used PRIMER but I've been this week precisely working with PERMANOVA in R with vegan (with adonis2). I exactly had the same problem at first (P values of 1), until I realized the terms should be nested!

For example, my model has 4 fixed categorical factors, and three of them are nested into the first one (the symbol "/" is used in R for that). I want to test the single effects + nested effects:

permanova <- adonis2(Y ~ F1 + F2 + F3 + F4 + F1 / F2 / F3 / F4, data, method = "euclidean")

print(permanova)

The PERMANOVA table would have this structure:

Df SumOfSqs R2 F Pr(>F)

F1 ............................. 0.001 ***

F2 ............................ 0.001 ***

F3 ............................0.001 ***

F4 ............................ 0.001 ***

F1(F2) ............................0.104

F1(F2(F3)) ............................ 0.001 ***

F1(F2(F3(F4)))) ............................ 0.012 *

Residual ............................

Total ............................

I hope this can help you out, don't hesitate contacting me if you need some help or codes for it :)

Cheers,

Raquel

There is evidence that the quality of vitamin D supplements can impact their bioavailability and effectiveness in the body. Vegan production, duration of storage, and other factors can affect the quality of vitamin D supplements.

For example, vitamin D3 supplements derived from lanolin (a wax-like substance found in sheep's wool) are the most common type of vitamin D supplement. However, some people prefer to use vegan vitamin D3 supplements derived from lichen. While both forms of vitamin D3 are effective, the bioavailability of vegan vitamin D3 supplements may be lower than that of lanolin-derived supplements.

Additionally, the quality of vitamin D supplements can be affected by the duration of storage. Vitamin D3 is sensitive to light and heat, and prolonged exposure to either can degrade the quality of the supplement. Therefore, it is important to store vitamin D supplements in a cool, dark place and to use them before their expiration date.

Other factors that can impact the quality of vitamin D supplements include the presence of contaminants, the form of the supplement (e.g., liquid, capsule, tablet), and the presence of complementary micronutrients like magnesium and vitamin K2.

Overall, it is important to choose high-quality vitamin D supplements and to consider factors like production methods, storage conditions, and complementary micronutrients when using vitamin D to support immune function and overall health.

Yes, vegan production, duration of storage, and other parameters of quality can impact the bioavailability of vitamin D supplements.

For example, vegan vitamin D3 supplements derived from lichen may have lower bioavailability compared to animal-derived vitamin D3 supplements, such as those derived from lanolin. This is because the vitamin D3 in lichen is in the form of D3 precursors that need to be converted by the body into active vitamin D3. This conversion process can be less efficient than the conversion of animal-derived vitamin D3 into its active form.

Furthermore, the duration of storage can affect the bioavailability of vitamin D supplements. Vitamin D3 is sensitive to light and heat, and prolonged exposure to either can degrade the quality of the supplement. Therefore, it is important to store vitamin D supplements in a cool, dark place and to use them before their expiration date.

referrence :

Disclaimer: Vegan myself and spend some time in eating disorder research.

Currently, there are roughly three veganism "movements" at the same time: Their main motivations are: (1) animal rights, (2) environmental impact, (3) health. Empirically, the first two are on very stable grounds, the last is somewhat more unstable. For example, there is to date not much conclusive research showing health benefits of veganism vs. vegetarianism vs. diet with low (i.e., once a week) meat-intake. While there is increasingly good evidence that the former three diets have benefits over the standard "western diet".

My hypothesis would be that only the third group ("health") is at higher risk for eating disorders. I don't know of research on the topic and this is just my intuition. This group will likely be closely connected to the general "health/beauty/fitness" trends perpetuated by, e.g., instagram, influencers, certain brands, and the like. These trends itself have been shown to affect views and perceptions on body image, etc. So there is a obvious connection to eating disorder development. While this mostly would affect females, there is also a trend and some preliminary evidence for benefits of veganism in body building which, given the connection between body building, body image, muscle dysmorphia, and eating disorders, might again cause a statistical association between veganism and eating disorders in males.

On the other hand, I don't see a good reason to assume that the first two groups who are vegan out of ethical/environmental concerns should be excluded from ED studies. First, they might actually not be at higher risk for ED development. Second, this will, more and more with rising societal awareness of the terrible conditions in animal "production" and the strong positive impact of a plant-based diet on one's carbon foodprint, limit the number of eligible participants, making research harder. Third, again increasingly so with the number of people adopting a vegan lifestyle, this might actually introduce a bias as studies would then be less representative of the general population because a more or less relevant subgroup was excluded. This might be especially relevant for microbiom studies.

So, in conclusions: Maybe an assessment of the motivation for the participant's veganism would be a temporary solution? In the easiest case, a kind of Likert rating for each major motivation to then exclude those who are mostly vegan for health/fitness benefits? Of course, the correct solution would be to first assess whether my hypothesis above is correct to then apply it in participant selection...

A high p value occurs with a high R2 value due to low sample size. However, if your R2 is very high, say > 0.85, you can probably disregard the p value and say your model explains a lot of the response variability :)

Hello Thomas!

That sounds interesting. Are you planning on doing a research about it? And what age group are you thinking about?

Hello Cameron; Your description of the study sounds like the data a comparison of frequencies. That sounds like a Chi Square test is an appropriate place to begin. It is simple and quick...you can do it by hand. Best regards, Jim Des Lauriers

And, if it helps, neither Permanova nor Anosim require balanced designs. A lack of balance will reduce the number of possible permutations, and as discussed in the Anderson paper there may be some (marginal) effects on the Permanova statistic, but in general for a design like yours you'd be fine just carrying on with the standard approach.

Visit kindly the following useful RG link:

That is correct. Here is a short tutorial on how to do that https://rpubs.com/brouwern/veganpca

This program usually can import any type of data file (excel, csv, tx, etc.)

Hi Claire, you might already have answer to this, but I found the answer to your question in this blog:

https://chrischizinski.github.io/rstats/adonis/

Hello, it seems to me that Shiny does.

If you have presence/absence (binary) data you can, indeed, use a resemblance coefficient like Jaccard. You could calculate the decomposition of Jaccard between 2 samples into contributions from individual species, I suppose. What most people do in my experience is to use the Sorensen (or Dice) coefficient. This is simply the Bray-Curtis measure applied to binary data. Then SIMPER can be run as usual. The 'abundances' in the output will then be relative frequencies of occurrence. If you are using rank-based multivariate analyses then Jaccard and Bray-Curtis will give the same results as they are monotonically related to each other.

Kruskal ANOVA is univariate and would ignore the multivariate nature of the question. It is also true as Jaime Pinzon says that applying a test that assumes homogeneity of dispersions may not be appropriate if there is a presumption that different fish have different breadths of diet (specialists vs generalists, for example).

You are getting small differences that are highly significant because the numerous samples give you massive power, but you are in danger of missing the bigger picture. The underlying problem here is the sample grain, and this is well understood for such dietary studies. What is found in an individual fish's stomach only tells you what it has just eaten. The data are dominated by individual-individual noise. To improve the 'signal (diet) to noise (last meal)' ratio it is often appropriate to redefine your samples as the sum or average of a number of fish guts. Choose a number (say 4, or 5, or 10) and then randomly sample groups of fish of that size from your data within each of your combinations of factors. This will give you much more robust data relevant to differences in diet among levels of factors, rather than differences in last meals. Finally, the fish are 'doing the sampling' so you have no control over the sampling effort, so it would be sensible to standardize (convert to percentages) and maybe do a mild (square root) transformation prior to calculating appropriate resemblances (e.g. Bray-Curtis).

For hypothesis testing, if you aren't too bothered by differences in dispersion Permanova may be OK. Alternatively multiway ANOSIM (which gives measures of relative effect sizes) would be an appropriate method, although it's not in R yet as far as I know. For more see Lek E., Fairclough D. V., Platell M. E., Clarke K. R., Tweedley J. R. & Potter I. C. (2011) To what extent are the dietary compositions of three abundant, co-occurring labrid species different and related to latitude, habitat, body size and season? J. Fish Biol. 78, 1913–1943 for a fish example (they used a sample size of 4 fish I think). For comparison of Permanova and Anosim see doi:10.1111/aec.13059. 3-way ANOSIM (incorporating the Lek et al. data) coming soon in the same issue.

Yes, the incomplete information of producers regarding the production technologies used and the raw materials used, agricultural produce is a serious problem. I have noticed that this problem affects many food products that are produced on the basis of agricultural crops produced in the context of environmentally friendly farming. The information asymmetry between the producer and the consumer is still very high. In addition, the systems of verification of the environmental performance of agriculture, which produce pro-ecological agricultural produce, fruit and vegetables, should also be improved.

Regards,

Dariusz Prokopowicz

Calling Fis inbreeding coefficient is often misleading. The fixation coefficient Fis is basically a metrix of HW departure, which can be negative, in case of excess of heterozygosity (as underlined above).

Reason for excess of heterozygosity with microsatellites, may be related to different phenomena, such as randomness (you may check if your Fis are significantly different from 0), inbreeding avoidance, or small effective population size in species with sexual differentiation.

Hey Esther,

This is a good questions. If you are asking which pigment expression drives differences between Plant ID or Petal Type, I think you're looking for a SIMPER analysis as a follow up to your PERMANOVA and PERMDISP. So like let's say you know that Petal Type is significant and you detect a significant pairwise/contrast such that Petal Type A is significantly different than Petal Type B, you might want to know what pigments contribute most significantly to differences between Petal Type.

I could be wrong, but I believe this requires a SIMPER analysis.

Zhimeng Xu Dear Zhimeng, thank you very much for the suggestion! It is a perfect solution for this question.

I interested

Glycerol as a cryoprotectant depresses the freezing point of bacterial cells, enhancing supercooling. It does so by forming strong hydrogen bonds with water molecules, competing with water-water hydrogen bonding. This disrupts the crystal lattice formation of ice unless the temperature is significantly lowered. http://2011.igem.org/Team:Cambridge/Protocols/Glycerol_Stocks

It will be a problem because no one will eat meat. Therefore, the percentage of the herd of sheep and cows will increase dramatically and the percentage of sell and buy will be decreased and that will affect on the harmony of nature.

To compare shannon index results, you can do a hutcheson t test. Simply follow the below given link:

But to calculate whether ths samples are significantly differen, i would suggest you to do an Anosim test(in pair wise method) which would give you 3 p-values in pairs. If your p-values are <0.05 for any pair, you can interpret that result as "samples are significantly different'

Hello

Look at this link, maybe it will help you in this area

That's not a surprise - every metaheuristic will only provide a rough solution - never an optimal one, and there is no chance that one can estimate the distance.

Dear Jose,

Functions in package 'vegan' need input data.frame (or a dissimilarity matrix based on such data.frame) with the following structure:

- entities to be compared (called 'sites' by vegan) in the rows, and

- characteristics (called 'species') in the columns.

Vegan was written for vegetation analysis (this is why it uses misleading names for the entities and characteristics), but can be used for any dataset that is provided in the appropriate structure.

I'm not familiar with MicrobiomeAnalyst, but am sure that its result can be transformed somehow to the desired structure.

HTH,

Ákos

Interesting question

Hello Niamh,

You may run the one-way anova. The statistical power tends to track roughly the harmonic mean of per-group n (for your data, 4/(1/98 + 1/7 + 1/12 + 1/5) ~ 9 per group, which won't be a very powerful test unless group differences are pretty pronounced on whatever outcome measure is of import to you. I suspect that your groups emerged from their self-identification once the data were collected, and your "typical" participant was a self-described omnivore.

If that's all the data you are able to collect, then you'll have to live with it (and note that as a limitation to your study.) Obviously, the precision of group estimates will be best for the omnivore group, and worst for vegans and pescatarians.

FYI, it's for this reason (precision) that people often oversample subgroups known to be (or suspected to be) small when trying to estimate values for populations.

Good luck with your work.

try ggpairs function plot in GGally package.

If you want to know what happens month by month, then you can use month as a factor, but it is usual to pool data for years and assess seasonal or yearly changes