R help - Sep 2015 - There is an error when I performed chisquare and postanova test...:(

I am studying for a quiz and while I was solving two problems, an error
occured.
a) So the problem is we want to test if the block program makes a difference
in retention at ? = 1%
(which is the significance level)
This is the code I used to perform chisquare test.
My solution:
blockprogram <- matrix(c(18,15,5,8,4,10,5,7,18,10), nrow=2, byrow=T)
colnames(blockprogram) <- c("1 yr","2 yr","3
yr","4 yr","5+ yrs")
rownames(blockprogram) <- c("Non-Block","Block")	
chisq.test(blockprogram, conf.level=0.99) ==> This is the part where I
can't
run..
chisq.test(blockprogram, conf.level=0.99)$observed
chisq.test(blockprogram, conf.level=0.99)$expected
So my question is is it the *conf.level=0.99* where it is wrongly used?

b)I was able to run the one way anova but wasn't able to run on the
tukey's
test. I seriously do not know what went wrong... So, this is the original
problem:
The data set chicken.csv contains weights of chickens which are given 1 of 3
different food rations. Perform an ANOVA procedure to determine if the
weights of the chickens are significantly affected by the food rations they
are provided. In case a significant effect exists, perform a Tukey HSD
post-hoc procedure to identify under which ration the chickens will be
heaviest. Use a 5% level of significance.

SO here's the code I used to perform:
chicken <- read.csv("C:/Users/Win/Desktop/chicken.csv")
attach(chicken)
anova(lm(chicken$ration~chicken$weight))
anova.ration <- aov(chicken$ration~chicken$weight)
*posthoc.ration <- TukeyHSD(anova.ration, 'weight', conf.level=0.95)
=> This
is the part where I wasn't able to run :(*
tapply(ration,weight, mean, na.rm=T)
plot(posthoc.weight)

Thanks!




--
View this message in context:
http://r.789695.n4.nabble.com/There-is-an-error-when-I-performed-chisquare-and-postanova-test-tp4712770.html
Sent from the R help mailing list archive at Nabble.com.

Dear massmatics

The list has a no homework policy but in this case I feel I can depart 
from that. Have you tried reading the documentation for chisq.test?

On 25/09/2015 12:44, massmatics wrote:
> I am studying for a quiz and while I was solving two problems, an error
> occured.
> a) So the problem is we want to test if the block program makes a
difference
> in retention at ? = 1%
> (which is the significance level)
> This is the code I used to perform chisquare test.
> My solution:
> blockprogram <- matrix(c(18,15,5,8,4,10,5,7,18,10), nrow=2, byrow=T)
> colnames(blockprogram) <- c("1 yr","2 yr","3
yr","4 yr","5+ yrs")
> rownames(blockprogram) <- c("Non-Block","Block")	
> chisq.test(blockprogram, conf.level=0.99) ==> This is the part where I
can't
> run..
> chisq.test(blockprogram, conf.level=0.99)$observed
> chisq.test(blockprogram, conf.level=0.99)$expected
> So my question is is it the *conf.level=0.99* where it is wrongly used?
>
> b)I was able to run the one way anova but wasn't able to run on the
tukey's
> test. I seriously do not know what went wrong... So, this is the original
> problem:
> The data set chicken.csv contains weights of chickens which are given 1 of
3
> different food rations. Perform an ANOVA procedure to determine if the
> weights of the chickens are significantly affected by the food rations they
> are provided. In case a significant effect exists, perform a Tukey HSD
> post-hoc procedure to identify under which ration the chickens will be
> heaviest. Use a 5% level of significance.
>
> SO here's the code I used to perform:
> chicken <- read.csv("C:/Users/Win/Desktop/chicken.csv")
> attach(chicken)
> anova(lm(chicken$ration~chicken$weight))
> anova.ration <- aov(chicken$ration~chicken$weight)
> *posthoc.ration <- TukeyHSD(anova.ration, 'weight',
conf.level=0.95) => This
> is the part where I wasn't able to run :(*
> tapply(ration,weight, mean, na.rm=T)
> plot(posthoc.weight)
>
> Thanks!
>
>
>
>
> --
> View this message in context:
http://r.789695.n4.nabble.com/There-is-an-error-when-I-performed-chisquare-and-postanova-test-tp4712770.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> 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.
>
-- 
Michael
http://www.dewey.myzen.co.uk/home.html

Yes, so far, we only learned how to use chisq.test when performed at 0.05
significance level
But not when it is at 0.01



--
View this message in context:
http://r.789695.n4.nabble.com/There-is-an-error-when-I-performed-chisquare-and-postanova-test-tp4712770p4712772.html
Sent from the R help mailing list archive at Nabble.com.

As Michael suggests carefully read the help file (type ?chisq.test to bring up
the page) and match all the elements of your command with the elements listed on
the help page.

You do not need to use attach(chicken) given the code you are using and using
attach(data)  is generally considered bad practice. The two equations below are
equivalent and the second is better practice in R.

anova(lm(chicken$ration~chicken$weight)) # your code

anova(lm(ration ~ weight, data = chickens)) # cleaner code.

Also have a look at ?with

I'd suggest having a look at
http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-ex
and/or http://adv-r.had.co.nz/Reproducibility.html for some ideas on how to form
questions and supply sample data to R-help.

You are posting from nabble which does not supply any context for the help list.
If you are going to post here regularly I think everyone would be grateful if
you post directly to R-help from a mail program. Very few people here use nabble
and it is generally considered something of a curse.

Good luck on the quizz


John Kane
Kingston ON Canada

> -----Original Message-----
> From: 2hanl2da at naver.com
> Sent: Fri, 25 Sep 2015 04:44:59 -0700 (PDT)
> To: r-help at r-project.org
> Subject: [R] There is an error when I performed chisquare and postanova
> test...:(
> 
> I am studying for a quiz and while I was solving two problems, an error
> occured.
> a) So the problem is we want to test if the block program makes a
> difference
> in retention at ? = 1%
> (which is the significance level)
> This is the code I used to perform chisquare test.
> My solution:
> blockprogram <- matrix(c(18,15,5,8,4,10,5,7,18,10), nrow=2, byrow=T)
> colnames(blockprogram) <- c("1 yr","2 yr","3
yr","4 yr","5+ yrs")
> rownames(blockprogram) <- c("Non-Block","Block")
> chisq.test(blockprogram, conf.level=0.99) ==> This is the part where I
> can't
> run..
> chisq.test(blockprogram, conf.level=0.99)$observed
> chisq.test(blockprogram, conf.level=0.99)$expected
> So my question is is it the *conf.level=0.99* where it is wrongly used?
> 
> b)I was able to run the one way anova but wasn't able to run on the
> tukey's
> test. I seriously do not know what went wrong... So, this is the original
> problem:
> The data set chicken.csv contains weights of chickens which are given 1
> of 3
> different food rations. Perform an ANOVA procedure to determine if the
> weights of the chickens are significantly affected by the food rations
> they
> are provided. In case a significant effect exists, perform a Tukey HSD
> post-hoc procedure to identify under which ration the chickens will be
> heaviest. Use a 5% level of significance.
> 
> SO here's the code I used to perform:
> chicken <- read.csv("C:/Users/Win/Desktop/chicken.csv")
> attach(chicken)
> anova(lm(chicken$ration~chicken$weight))
> anova.ration <- aov(chicken$ration~chicken$weight)
> *posthoc.ration <- TukeyHSD(anova.ration, 'weight',
conf.level=0.95) =>
> This
> is the part where I wasn't able to run :(*
> tapply(ration,weight, mean, na.rm=T)
> plot(posthoc.weight)
> 
> Thanks!
> 
> 
> 
> 
> --
> View this message in context:
>
http://r.789695.n4.nabble.com/There-is-an-error-when-I-performed-chisquare-and-postanova-test-tp4712770.html
> Sent from the R help mailing list archive at Nabble.com.
> 
> ______________________________________________
> 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.
____________________________________________________________
Receive Notifications of Incoming Messages
Easily monitor multiple email accounts & access them with a click.
Visit http://www.inbox.com/notifier and check it out!