Just happens in my case that 90% is very unlikely and 70% is usually good enough. According to our group of industrial engineers. However, I wanted to do some of my own research.
Main Topics
Browse All TopicsI am new to statistics and have been doing some reading about how regression analysis can be used to determine the strength of correlations.
How would I set up AND read an analysis to determine which variables are the most influential to Y (dependent variable). Also, how would I set up a confidence interval of 70%?
Y X1 X2 X3 X4
0.43 0 3 3 3
0.39 0 3 1 1
0.79 1 0 2.5 1
0.88 1 0 2.5 1
1.04 3 0 3 2
0.78 3 0 3 3
1.82 3 3 3 3
1.05 3 0 2 1
0.42 0 0 3 1
0.62 0 0 2 0
1.08 0 0 3 3
2.8 3 3 1 1
0.28 2 0 2 1
1.07 0 3 3 2
4.4 3 0 2.5 3
7.46 3 0 2 3
0.59 1 0 3 3
2.04 3 0 2.5 2
This Question has been solved and asker verified All Experts Exchange premium technology solutions are available to subscription members.
Experts Exchange has been collecting answers to technology questions since 1996…3 million and counting! If you have a question, chances are we already have your answer.
If you can't find the exact answer you're looking for, ask our exclusive community of 50,000 experts. You’ll get a personalized answer from a trusted professional.
Thousands of free tech tips, tricks, how-to’s and tutorials are available in our peer reviewed articles section. See for yourself how smart our experts are, no login required.
Access the answers to your technology questions today.
30-day free trial. Register in 60 seconds.
Members of the expert community talk about why the experience at Experts Exchange is different than what you will find anywhere else.

Try it out and discover for yourself.
30-day free trial. Register in 60 seconds.
Join the community of experts here and help other tech pros by answering question in your area of expertise. You can earn FREE access to all Experts Exchange's premium features and resources.
Yeah I know once I understood what all this statistical analysis means. Oddly enough the individual who made that statement is a contractor who is also a professor at a top ranked IE program. Anyways, I just wanted to learn and start doign the basics in Excel since it does all the Regression output and was hoping someone could explain how to interpret it quickly...nothing to in depth just the basics (e.g. high adj R-squared shows high correlation, F-test values, etc...)....
bs329,
Well, with the Analysis ToolPak add-in enabled, Excel will run regression analysis, for up to 16 independent
variables.
That said, as much as I adore Excel, I do not trust it to do my regression analyses for anything important.
1) Excel will occasionally compute a negative r^2. This is mathematically impossible, and yet Excel will do it
2) Excel does not do a good job of detecting relationships between the supposedly independent variables
For both of these reasons, if the analysis is for something important, I always go to Minitab. For serious
statistical work, you should use an application that is all about statistics.
As for what tests to use, forget the F test. While failing the F test will tell you that the regression model is
crap, there is nothing particularly useful about passing the F test.
Looking at the adjusted r^2 can be useful, but there are limits. For example, in social science articles, many
researchers are ready to do their own little happy dance when they get an r^2 of 40%. That's all well and
good, but it still leaves 60% (i.e., most of) the observed variance unexplained by the model.
Patrick
Business Accounts
Answer for Membership
by: matthewspatrickPosted on 2009-11-02 at 11:28:16ID: 25722755
bs329 said:
>>Also, how would I set up a confidence interval of 70%?
Why 70% In statistical analysis, it is very uncommon to use a confidence level below 90%. 95% and 99% are
most common.