Bert Gunter
2020-Dec-15 15:43 UTC
[R] multiple t-test with different species and treatments
Unless there is good reason not to, always cc r-help, which I have done here. Bert Gunter On Tue, Dec 15, 2020 at 1:16 AM Lingling Wen <wenlingling912 at gmail.com> wrote:> Dear Bert Gunter, > Good day, > Thank you for your comments about the posting policy. I am sorry for > bothering you with the text against the posting policy in this list. I will > read the policy carefully and improve it in my future posting. > Regarding the question I asked, actually, it is for my experiment data > analysis but not homework. I've tried code as followed: > library(dplyr) > library(tidyverse) > library(rstatix) > library(ggpubr) > test <- read.csv(file.choose(), header=TRUE) > print(test) > > mydata <- test %>% > pivot_longer( > cols = c(3:8), > names_to = "Metabolites", > values_to = "Relative content", > values_drop_na = FALSE) > > mydata > stat <- group_by(mydata, Metabolites,Treatment) %>% > t_test('Relative content' ~ Treatment) %>% > adjust_pvalue(method = "BH") %>% > add_significance() > > When I run the code, it always shows error like this: Error in > terms.formula(formula) : invalid term in model formula. > Because I have a lot of metabolic data to deal with, I think R will help > to save a lot of time so I am learning to use it. But I could not figure > out what's the problem when it gives error feedback. > > It would be very appreciated if I could get help from the list. > Thank you! > > Lingling > > > > > On Mon, 14 Dec 2020 at 01:19, Bert Gunter <bgunter.4567 at gmail.com> wrote: > >> 1. Please read and follow the posting guide linked below. >> 2. No html -- this is a plain text list. >> 3. Use ?dput to provide us your data so that we don't have to convert it >> for you. >> 4. We expect you to first make an effort to do your own coding. See >> ?t.test, which you could also >> have found yourself by a web search (rseek.org is a reasonable place to >> search from for R-related stuff, >> though I have usually found that a plain google search does the job). >> 5. Is this homework? -- this list has a no homework policy (see the >> posting guide). >> >> Bert Gunter >> >> "The trouble with having an open mind is that people keep coming along >> and sticking things into it." >> -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) >> >> >> On Sun, Dec 13, 2020 at 2:33 PM Lingling Wen <wenlingling912 at gmail.com> >> wrote: >> >>> Dear R users, >>> I would like to ask for help with the code of multiple t-test. I have a >>> dataset as followed: >>> Species Treatment var1 var2 var2 var4 var5 var6 >>> Blue D 0.022620093 0.125079631 0.04522571 0.010105835 0.013418019 >>> 1.455646741 >>> Blue D 0.02117295 0.073544277 0.0311234 0.008742305 0.03261776 >>> 0.982196898 >>> Blue D 0.021896521 0.112681274 0.05664344 0.013512548 0.032380618 >>> 1.777003683 >>> Green D 0.032749726 0.087705198 0.13699174 0.009902168 0.083534492 >>> 1.553758965 >>> Green D 0.036468693 0.115829755 0.10941521 0.012139481 0.206929915 >>> 2.610557732 >>> Green D 0.043594022 0.062832712 0.12232853 0.015045559 0.111687593 >>> 1.99552401 >>> Orange D 0.022617656 0.11465489 0.02882994 0.013304181 0.018175693 >>> 1.72075866 >>> Orange D 0.026211773 0.099294867 0.03387876 0.013408254 0.02971197 >>> 2.184955376 >>> Orange D 0.032205662 0.057267709 0.03883165 0.007744362 0.026553323 >>> 1.27255601 >>> White D 0.041135469 0.085531343 0.06921425 0.011496168 0.010196895 >>> 0.573205411 >>> White D 0.045142458 0.111429194 0.03546278 0.009196729 0.009968818 >>> 0.748529991 >>> White D 0.031471913 0.050175149 0.05233851 0.011447205 0.010424973 >>> 0.92385457 >>> Blue W 0.022222296 0.112334911 0.04080824 0.016064488 0.031047157 >>> 0.885523847 >>> Blue W 0.040238733 0.121941307 0.04239768 0.010310538 0.020106944 >>> 0.751643349 >>> Blue W 0.031508947 0.131547704 0.05212774 0.015720985 0.013932284 >>> 0.881234886 >>> Green W 0.021070032 0.121018603 0.38202466 0.022152283 0.038479532 >>> 0.662605036 >>> Green W 0.026562365 0.108269047 0.44028708 0.019344875 0.090798566 >>> 0.746330971 >>> Green W 0.02926478 0.084080729 0.32376224 0.012609717 0.097744041 >>> 0.969301308 >>> Orange W 0.02456562 0.134535891 0.09135624 0.007701481 0.017310058 >>> 0.966322354 >>> Orange W 0.032095541 0.149347595 0.06048885 0.010332579 0.017457175 >>> 0.561561725 >>> Orange W 0.039120696 0.141941743 0.02962146 0.005889924 0.017162941 >>> 0.502529091 >>> White W 0.033903057 0.061460583 0.0492955 0.012457767 0.029929334 >>> 0.70986421 >>> White W 0.033630233 0.115782233 0.02675399 0.021391535 0.023774961 >>> 1.176680075 >>> White W 0.030638581 0.065074112 0.03678494 0.014781912 0.03529703 >>> 0.805500558 >>> I wanted to perform a t-test between the treatment "D" and "W" of each >>> species for all of the variables (var1, var2,...). Could anyone suggest >>> the packages or code for this analysis? >>> >>> [[alternative HTML version deleted]] >>> >>> ______________________________________________ >>> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see >>> https://stat.ethz.ch/mailman/listinfo/r-help >>> PLEASE do read the posting guide >>> http://www.R-project.org/posting-guide.html >>> and provide commented, minimal, self-contained, reproducible code. >>> >>[[alternative HTML version deleted]]
Jeff Newmiller
2020-Dec-15 17:09 UTC
[R] multiple t-test with different species and treatments
Dear Lingling Wen: Bert has forwarded your message to the list because one person cannot usually answer every question... so many heads are better than one. However, you seem to have neglected his other advice about providing a complete example including data. Further, you are using several specialized packages that may require more specific assistance than you may find on this list... as the Posting Guide warns you, such packages are technically out of scope here (because contributed packages may introduce hidden behavior that only people familiar with those specific packages can recognize). If someone unfamiliar with the package can run your example (not possible here because of lack of data) they might see something about the errors that can help anyway. The one R-language issue I can see in your code is the use of single-quote marks (used for entering string literals) on what should probably be a variable rather than back-tick quotes (used to denote language symbols). On December 15, 2020 7:43:56 AM PST, Bert Gunter <bgunter.4567 at gmail.com> wrote:>Unless there is good reason not to, always cc r-help, which I have done >here. > >Bert Gunter > > > >On Tue, Dec 15, 2020 at 1:16 AM Lingling Wen <wenlingling912 at gmail.com> >wrote: > >> Dear Bert Gunter, >> Good day, >> Thank you for your comments about the posting policy. I am sorry for >> bothering you with the text against the posting policy in this list. >I will >> read the policy carefully and improve it in my future posting. >> Regarding the question I asked, actually, it is for my experiment >data >> analysis but not homework. I've tried code as followed: >> library(dplyr) >> library(tidyverse) >> library(rstatix) >> library(ggpubr) >> test <- read.csv(file.choose(), header=TRUE) >> print(test) >> >> mydata <- test %>% >> pivot_longer( >> cols = c(3:8), >> names_to = "Metabolites", >> values_to = "Relative content", >> values_drop_na = FALSE) >> >> mydata >> stat <- group_by(mydata, Metabolites,Treatment) %>% >> t_test('Relative content' ~ Treatment) %>% >> adjust_pvalue(method = "BH") %>% >> add_significance() >> >> When I run the code, it always shows error like this: Error in >> terms.formula(formula) : invalid term in model formula. >> Because I have a lot of metabolic data to deal with, I think R will >help >> to save a lot of time so I am learning to use it. But I could not >figure >> out what's the problem when it gives error feedback. >> >> It would be very appreciated if I could get help from the list. >> Thank you! >> >> Lingling >> >> >> >> >> On Mon, 14 Dec 2020 at 01:19, Bert Gunter <bgunter.4567 at gmail.com> >wrote: >> >>> 1. Please read and follow the posting guide linked below. >>> 2. No html -- this is a plain text list. >>> 3. Use ?dput to provide us your data so that we don't have to >convert it >>> for you. >>> 4. We expect you to first make an effort to do your own coding. See >>> ?t.test, which you could also >>> have found yourself by a web search (rseek.org is a reasonable place >to >>> search from for R-related stuff, >>> though I have usually found that a plain google search does the >job). >>> 5. Is this homework? -- this list has a no homework policy (see the >>> posting guide). >>> >>> Bert Gunter >>> >>> "The trouble with having an open mind is that people keep coming >along >>> and sticking things into it." >>> -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) >>> >>> >>> On Sun, Dec 13, 2020 at 2:33 PM Lingling Wen ><wenlingling912 at gmail.com> >>> wrote: >>> >>>> Dear R users, >>>> I would like to ask for help with the code of multiple t-test. I >have a >>>> dataset as followed: >>>> Species Treatment var1 var2 var2 var4 var5 var6 >>>> Blue D 0.022620093 0.125079631 0.04522571 0.010105835 0.013418019 >>>> 1.455646741 >>>> Blue D 0.02117295 0.073544277 0.0311234 0.008742305 0.03261776 >>>> 0.982196898 >>>> Blue D 0.021896521 0.112681274 0.05664344 0.013512548 0.032380618 >>>> 1.777003683 >>>> Green D 0.032749726 0.087705198 0.13699174 0.009902168 0.083534492 >>>> 1.553758965 >>>> Green D 0.036468693 0.115829755 0.10941521 0.012139481 0.206929915 >>>> 2.610557732 >>>> Green D 0.043594022 0.062832712 0.12232853 0.015045559 0.111687593 >>>> 1.99552401 >>>> Orange D 0.022617656 0.11465489 0.02882994 0.013304181 0.018175693 >>>> 1.72075866 >>>> Orange D 0.026211773 0.099294867 0.03387876 0.013408254 0.02971197 >>>> 2.184955376 >>>> Orange D 0.032205662 0.057267709 0.03883165 0.007744362 0.026553323 >>>> 1.27255601 >>>> White D 0.041135469 0.085531343 0.06921425 0.011496168 0.010196895 >>>> 0.573205411 >>>> White D 0.045142458 0.111429194 0.03546278 0.009196729 0.009968818 >>>> 0.748529991 >>>> White D 0.031471913 0.050175149 0.05233851 0.011447205 0.010424973 >>>> 0.92385457 >>>> Blue W 0.022222296 0.112334911 0.04080824 0.016064488 0.031047157 >>>> 0.885523847 >>>> Blue W 0.040238733 0.121941307 0.04239768 0.010310538 0.020106944 >>>> 0.751643349 >>>> Blue W 0.031508947 0.131547704 0.05212774 0.015720985 0.013932284 >>>> 0.881234886 >>>> Green W 0.021070032 0.121018603 0.38202466 0.022152283 0.038479532 >>>> 0.662605036 >>>> Green W 0.026562365 0.108269047 0.44028708 0.019344875 0.090798566 >>>> 0.746330971 >>>> Green W 0.02926478 0.084080729 0.32376224 0.012609717 0.097744041 >>>> 0.969301308 >>>> Orange W 0.02456562 0.134535891 0.09135624 0.007701481 0.017310058 >>>> 0.966322354 >>>> Orange W 0.032095541 0.149347595 0.06048885 0.010332579 0.017457175 >>>> 0.561561725 >>>> Orange W 0.039120696 0.141941743 0.02962146 0.005889924 0.017162941 >>>> 0.502529091 >>>> White W 0.033903057 0.061460583 0.0492955 0.012457767 0.029929334 >>>> 0.70986421 >>>> White W 0.033630233 0.115782233 0.02675399 0.021391535 0.023774961 >>>> 1.176680075 >>>> White W 0.030638581 0.065074112 0.03678494 0.014781912 0.03529703 >>>> 0.805500558 >>>> I wanted to perform a t-test between the treatment "D" and "W" of >each >>>> species for all of the variables (var1, var2,...). Could anyone >suggest >>>> the packages or code for this analysis? >>>> >>>> [[alternative HTML version deleted]] >>>> >>>> ______________________________________________ >>>> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see >>>> https://stat.ethz.ch/mailman/listinfo/r-help >>>> PLEASE do read the posting guide >>>> http://www.R-project.org/posting-guide.html >>>> and provide commented, minimal, self-contained, reproducible code. >>>> >>> > > [[alternative HTML version deleted]] > >______________________________________________ >R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see >https://stat.ethz.ch/mailman/listinfo/r-help >PLEASE do read the posting guide >http://www.R-project.org/posting-guide.html >and provide commented, minimal, self-contained, reproducible code.-- Sent from my phone. Please excuse my brevity.