AllExperts > Experts 
Search      

SAS

Volunteer
Answers to thousands of questions
 Home · More Questions · Answer Library  · Encyclopedia ·
More SAS Answers
Question Library

Ask a question about SAS
Volunteer
Experts of the Month
Expert Login

Awards

About Us
Tell friends
Link to Us
Disclaimer

 
 
 
 
About Shashank
Expertise
All SAS basic and macro prog. relatedquestionsI can answer. I have masters degress in Statistics too. so i can also interprete the results.

Experience
1.5 yr

 
   

You are here:  Experts > Computing/Technology > Computer Certification > SAS > about a SAS problem

Topic: SAS



Expert: Shashank
Date: 11/15/2005
Subject: about a SAS problem

Question
Thanks so much for your kind help. i know what does CI mean , in fact i have solve the problem (a)(b)(c) by using ANOVA test , i am now kind of confused what does the (d) mean , how to compute the CI for just one group 4, what does it compare to ? And how does it relate to f test?
the test requires us to use SAS program to do it .

Thanks a bunch !

Rachel
-------------------------
Followup To
Question -
HI, shashank,
 i am kind of desperate that i only have one day to finish the take home test:( thanks so mcuh for help me out. All problems are requried to use SAS code.

Pls see below:

1.   A manufacturer of television sets is interested in the effect on tube conductivity of four different types of coating for color picture tubes. The following conductivity data are obtained.
Coating Type            
1   143   141   150   146
2   152   149   137   143
3   134   136   132   127
4   129   127   132   129

(a)   Is there a difference in the conductivity due to coating type? Use á=0.05
(b)   Estimate the overall mean.
(c)   Find an estimate of the difference between coating types.
(d)   Compute a 95% confidence interval for the mean of coating type 4.



What does the question (d) mean , how can i interpert this?


thanks

Rachel
Answer -
we have to compute 95% CI considering all the observations,
I hope you know what is meant by confidence interval (CI).
It has upperbound and a lower bound, so we have to find a CI for mean of these observations such that out of 100 calculated means; 95 observed means will fall in this interval.
So you can particularly say about the effect on tube conductivity (this will the overall efeect as we are considering mean of all the observations)

If you want more help, you are welcome.

Shashank

Answer
To comute 95%CI for colour we can use the following
L.B = (mean of obs.) - (((STDEV of obs.)/sqrt(# of obs.*  Z (alpha/2))

U.B = (mean of obs.) + (((STDEV of obs.)/sqrt(# of obs.*  Z (alpha/2))

Where u can get value of  Z (alpha/2) from Normal tables.
# of obs= 4
mean of obs. = (139+127+132+129)/4
similarly you can calculate STDEV for 4 obs.

This will give you CI for 4th colour


you want to write SAS prog. for this?

Shashank


Add to this Answer    Ask a Question



  Rate this Answer
   Was this answer helpful?
Not at allDefinitely              
   12345  

     
About Us | Advertise on This Site | User Agreement | Privacy Policy | Help
Copyright  © 2008 About, Inc. About and About.com are registered trademarks of About, Inc. The About logo is a trademark of About, Inc. All rights reserved.