Scribd
Upload
110 views9 pages

Problemas c.3

Student Ivan Eduardo Calderon Flores is majoring in structures and submitted assignment 1 for the subject design of experiments. The assignment involved comparing two entities using reference distributions, tests, and confidence intervals for problems 1-8 from chapter 3. The document discusses using R Studio to perform two sample t-tests on data from experiments measuring asbestos fiber readings with and without the use of chemical s-142, as well as data from experiments measuring plate readings labeled A and B, and plates labeled PLATEA and PLATEB. The conclusions are that the s-142 chemical is effectively reducing asbestos fiber readings based on the first t-test, and that there are no statistically significant differences between the plate readings based on the

Uploaded by

Ivan Eduardo Calderon Flores
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
110 views9 pages

Problemas c.3

Student Ivan Eduardo Calderon Flores is majoring in structures and submitted assignment 1 for the subject design of experiments. The assignment involved comparing two entities using reference distributions, tests, and confidence intervals for problems 1-8 from chapter 3. The document discusses using R Studio to perform two sample t-tests on data from experiments measuring asbestos fiber readings with and without the use of chemical s-142, as well as data from experiments measuring plate readings labeled A and B, and plates labeled PLATEA and PLATEB. The conclusions are that the s-142 chemical is effectively reducing asbestos fiber readings based on the first t-test, and that there are no statistically significant differences between the plate readings based on the

Uploaded by

Ivan Eduardo Calderon Flores
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

STUDENT NAME:

CALDERON FLORES IVAN EDUARDO

MAJOR IN STRUCTURES

SUBJECT:
DESIGN OF EXPERIMENTS

ASSIGNMENT 1:
CHAPTER3
COMPARING TWO ENTITIES: REFERENCE
DISTRIBUTIONS, TESTS, AND CONFIDENCE INTERVALS
PROBLEMS 1-8

August 7th, 2015

Considering the readings:


A) Wthout s-142= 8,6
B) With s-142= 3,4
Assuming UA>UB, analyzing the data in R Studio we get the following
results:
Two Sample t-test
data: A and B
t = 3.1305, df = 2, p-value = 0.04434
alternative hypothesis: true difference in means is greater than 0
95 percent confidence interval:
0.2353569
Inf
sample estimates:
mean of x mean of y
7.0
3.5
Since p-value = 0.04434 < 0.05 the hypothesis UA>UB is taken as true,
the readings of asbestos fiber are higher without the s-142, therefore
we could assume the s-142 is working, but given that we only have two
readings using the chemical, and checking the historical results we can
see this results have been previously obtained without the use of the
chemical, further testing is necessary for an accurate answer.

She might have asked this question so she can be sure that the results
obtained are valid for the study and there are no other factors that migh
t have altered the readings affecting the comparation between them.

We begin with a null hypothesis UA=UB stated by one group who says
there is no difference and an alternative hypothesis UAUB stated by
the other group saying there is a difference.
Analyzing the data with R studio checking if A is greater than B we get
the following results:
Two Sample t-test
data: a and b
t = 0.93326, df = 6, p-value = 0.1934
alternative hypothesis: true difference in means is greater than 0
95 percent confidence interval:
-0.2434838
Inf
sample estimates:
mean of x mean of y
3.075 2.850
With p-value = 0. 1934 > 0.05, the null hypothesis is accepted therefore
there is not a significant difference between this readings.

We begin stating a null hypothesis UA=UB and an alternative hypothesis


UAUB
Analyzing the data with R studio we get the following results:
Two Sample t-test
data: PLATEA and PLATEB
t = 1.2111, df = 12, p-value = 0.1246
alternative hypothesis: true difference in means is greater than 0
95 percent confidence interval:
-0.06286564
Inf
sample estimates:
mean of x mean of y
1.208714 1.075429

With p-value = 0.1246 > 0.05, the null hypothesis is accepted therefore
there is not a significant difference between this readings.
There is an apparent systematic difference visible in some of the
readings but after making the t-test shows theres no difference.

You might also like