Ryan
was active Not recently activeActivity

Ryan replied to the topic 6 sigma application for tranprotation in the forum General 12 years, 3 months ago
Thanks for your insight Mark. It is much appreciated.

Ryan replied to the topic 8D report format in the forum Software/IT 12 years, 5 months ago
I could use some additional support (examples) creating an 8D for our company.
Any assistance would be great.
Thanks 
Ryan replied to the topic Difference between Correlation and Regression in the forum General 13 years, 1 month ago
This explanation is inaccurate. Regression does not tell us “cause and effect.” Such a conclusion would be based on the design, not the analysis. Ryan

Ryan replied to the topic Statistics knowledge in the forum General 13 years, 4 months ago
Hi Robert,
What book(s) would you recommend to learn the relationship between the distributions ChiSquare, t, F, and z?
Thanks,
Ryan 
Ryan replied to the topic Regression model in the forum General 13 years, 7 months ago
Here’s a nice primer on multiple regression:
http://www2.chass.ncsu.edu/garson/PA765/regress.htm
Ryan 
Ryan replied to the topic 2t sample test and anova in the forum General 13 years, 8 months ago
There are alternatives to the one way ANOVA for unequal variances such as (1) BrownForsythe and (2) Welch.
Ryan 
Ryan replied to the topic Empirical rule in the forum General 13 years, 9 months ago
The probability density function for the Gaussian (Normal) Distribution is:
where,
f(x) = vertical height of a point on the normal distribution
x = distance along the x axis
ó = standard deviation of the data distribution
µ = mean of the distribution
e = exponential constant = 2.71828
ð = pi = 3.14159 
Ryan replied to the topic Nonnormal distribution in the forum General 13 years, 9 months ago
Gman,
Daves is absolutely correct about the normality assumption.
1. The normality assumption for Regression/ANOVA is based on normality of the residuals, not the raw data. Having said that, if the residuals depart *substantially* from normality, this can become an issue! More importantly, though, you want your sample sizes between the levels o…[Read more] 
Ryan replied to the topic Nonnormal distribution in the forum General 13 years, 9 months ago
Gman,
If data are normally distributed, then a graph of the data should resemble a belllike curve:
http://content.answers.com/main/content/img/barrons/accounting/images/N4.jpg
Notice the belllike shape curve with more weight in the center and the tails tapering off to zero.
Create a histogram and see if it approximates the picture…[Read more] 
Ryan replied to the topic Factor Analysis and Component Analysis in the forum General 13 years, 9 months ago
The goal of principle components analysis (PCA) is to arrive at a smaller number of components that will extract the most amount of variance from a larger number of observed variables, whereas the goal of factor analysis (FA) is to explain common variance shared by the observed variables.
In PCA, the components are a linear combination of the…[Read more] 
Ryan replied to the topic Correlation and regression in the forum General 13 years, 9 months ago
It sounds like you need an introduction to multiple linear regression:
http://www2.chass.ncsu.edu/garson/pa765/regress.htm 
Ryan replied to the topic Interpreting Betas in Regression w/ transformations in the forum General 13 years, 10 months ago
I received help to answer my question. Please disregard original email.

Ryan replied to the topic Power in the forum General 13 years, 11 months ago
Statistical power is defined as the probability of rejecting a false null hypothesis. It is 1 minus beta, where beta is the probability of failing to reject a false null hypothesis. Power depends upon alpha (Type I Error), beta (Type II Error), sample size, effect size, and the directionality of the statitsical test. Generally spe…[Read more]

Ryan replied to the topic Correlation between survey responses? in the forum General 13 years, 11 months ago
The assumptions of linear regression are:
1. Linear relationship between the IV(s) and DV
2. Independece of the residuals
3. Homoscedasticity
4. Normality of residual distributions
You can assess (1) linearity by plotting residuals versus predicted values, (2) independence by looking at an autocorrelation plot, (3) homoscedasticity by l…[Read more] 
Ryan replied to the topic Polynomial Regression Under General Linear Model in the forum General 14 years ago
Thank you! I think I will purchase the book.

Ryan replied to the topic Paired T Test in the forum General 14 years ago
Paired t tests can be either twotailed (nondirectional) or onetailed (directional). Directional tests should be based on theory and/or previous research supporting this viewpoint.

Ryan replied to the topic Six Sigma in 5 yrs in the forum General 14 years ago
http://www.businessweek.com/print/magazine/content/07_24/b4038406.htm?chan=gl
For those of you discussing Six Sigma’s role in innovation, read this article for some insight into 3M’s experience. Deanb, I noted your reference to 3M and submit that this article illustrates an example of how one structured, prescriptive approach to SS stifled innovation.

Ryan replied to the topic Deviance Test? in the forum General 14 years, 1 month ago
Yes. I agree, Robert. Thank you again for all your help. Ryan

Ryan replied to the topic Deviance Test? in the forum General 14 years, 1 month ago
For those who are interested, I’ve come to learn that the deviance test they were most likely referring to was the Likelihood Ratio Test. I don’t think it’s the best approach to test for groupswithintreatments effects, but it is what it is.

Ryan replied to the topic (Partially) Nested Design Question in the forum General 14 years, 1 month ago
Robert,
Thank you for your thoughtful and detailed response.
The study I am proposing would involve a therapist providing both treatments. I can see how hospital effect could not be separated from therapist effect if there is only one therapist per hospital, but I do not understand why I cannot separate therapist effect from treatment effect.…[Read more]  Load More