STAT XXXXXXXXXXHW#7 Due Date: 4/01/2021 (Thursday) Homework must be submitted to Assignment #7 on Blackboard On the top right corner, write your name, date, and HW #. All problem numbers refer to the...

1 answer below »

·All problem numbers refer to the problem from Dean, Voss, and Dragulijic (DVD)


·Please summarize your results from statistical software such as R or SAS




STAT3119-10 HW#7 Due Date: 4/01/2021 (Thursday) Homework must be submitted to Assignment #7 on Blackboard On the top right corner, write your name, date, and HW #. All problem numbers refer to the problem from Dean, Voss, and Dragulijic (DVD) Please summarize your results from statistical software such as R or SAS (DVD #10.8) Hypothetical chemical experiment An experiment to examine the yield of a certain chemical was conducted in b = 4 different laboratories. The treatment factors of interest were A : acid strength (80% and 90%, coded 1, 2) B : time allowed for reaction (15 and 30 min, coded 1, 2) C : temperature (50◦ and 75 ◦C, coded 1, 2) The experiment was run as a randomized complete block design with the laboratories as the levels of the blocking factor. The resulting data (yields in grams) are shown in Table 10.22. The goal of the experiment was to find the treatment combination(s) that give(s) the highest average yield. (2 pts)  Plot the data and comment on your chosen plots. (2 pts)  Fit a block–treatment model to these data and show that the assumptions on the model are approximately satisfied. (1 pts)  Suppose that the pre-plan was to calculate a 99% set of pairwise comparisons between the treatment combinations using Tukey’s method, to calculate 99.5% intervals for the comparisons between the levels of A, B and C if these were not involved in interactions and a set of 99% intervals using Scheffé’s method for any other contrasts that look interesting. The overall confidence level would then be at least 96.5%. List any contrasts that you would like to examine further after looking at the plots in part (a). (2 pts)  Calculate an analysis of variance table and test any hypotheses of interest, each at level 0.025. State your conclusions clearly. (2 pts)  Calculate confidence intervals for the contrasts specified in part (c), and state your conclusions. (1 pts)  The objective of the experiment was to find the combination that gives the highest yield. Using all the information that you have gathered, which treatment combination would you recommend?
Answered 2 days AfterMar 31, 2021

Answer To: STAT XXXXXXXXXXHW#7 Due Date: 4/01/2021 (Thursday) Homework must be submitted to Assignment #7 on...

Sanchi answered on Apr 01 2021
153 Votes
Hypothetical Chemical Experiment
· Preparation of dataset
acid <- factor(rep(c("1", "2"), each = 4))
time <- factor(rep(c("1", "2"), times = 4))
temp <- factor(rep(c("1", "2"), times = 4))
y<- c(7.3,    9.5,    
13.8,    15.4,    16,    18.7,    11.3,    14.5,
8.8,    11.3,    15.3,    17.7,    17.9,    20.8,    12,    15.4,
11.7,    14.1,    17.2,    22.3,    22.6,    24.8,    16.9,    18.5,
6.2,    8.3,    11.2,    15.4,    16.8,    17.4,    8.2,    12.5)
results <- data.frame(y, acid, time,temp)
f = c("111", "112", "121","122","211","212","221","222") # treatment levels
k = 8 # number of treatment levels
n = 4 # number of control blocks
tm = gl(k, 1, n*k, factor(f)) # matching treatment
tm
blk = gl(n, k, k*n)
blk
results <- data.frame( blk,tm, y)
· Question 1 Plot the data and comment on your chosen plots.
library(ggplot2)
ggplot(data = results, mapping = aes(x = tm, y = y,group=1)) +
geom_line(aes(color = blk))
· Question2 Fit a block–treatment model to these data and show that the assumptions on the model are approximately satisfied.
Input-
fit.lm = lm(y ~ tm + blk, data = results)
fit.lm
Output-
Call:
lm(formula = y ~ tm + blk, data = results)
Coefficients:
(Intercept) tm112 tm121 tm122 tm211 tm212 tm221
7.131 2.300 5.875 9.200 9.825 11.925 3.600
tm222 blk2 blk3 blk4
6.725 1.588 5.200 -1.312
· Question 3 Suppose that the pre-plan was to calculate a 99% set of pairwise comparisons between the treatment combinations using Tukey’s method, to calculate 99.5% intervals for the comparisons between the levels of A, B and C if these were not involved in interactions and a set of 99% intervals using Scheffé’s method for any other contrasts that look interesting. The overall confidence level would then be at least 96.5%. List any contrasts that you would like to examine further after looking at the plots in part (a).
Input
pairwise$tm
pairwise$blk
Output
> pairwise$tm
diff ...
SOLUTION.PDF

Answer To This Question Is Available To Download

Related Questions & Answers

More Questions »

Submit New Assignment

Copy and Paste Your Assignment Here