# Search results

1. ### Comparing across two models

It is an internal state document so I don't think you could access it. It was published by the Division of Vocational Rehabilitation in Washington State in February 2007. The title is Examining Washington State's Vocational Rehabilitation Rates: Why the Decline. Many of the people would not be...
2. ### Comparing across two models

This came from a logistic regression "We tested whether the effect of a factor was the same, stronger or weaker after 2000 by comparing the log odd coefficient of a factor in the 97-98 cohort with that in the 2002-2003 cohort. For example the effect of unemployment rate was .2 in the 2002-2003...
3. ### Reporting ordinal regression results

I think the AIC might be your best bet to choose among models. There are something like 34 pseudo R squared for logistic regression and they vary a lot. None that I have seen are easy to explain, they are not the percent of explained variance. Often they do not add to 100 percent (that is one)...
4. ### Time Series Question

thanks everyone.
5. ### Time Series Question

While I am at it does anyone know of a good time series regression book that is not heavy on theory and matrices? I know plenty that are heavy on both, none like this... :p
6. ### Correlation

If the level of a variable never changes then its a constant and there is no covariance or correlation between it and a random variable. Formally I think the correlation is zero, but your software may be treating it as undefined and thus an error.
7. ### Time Series Question

Can you run time series regression when various variables are integrated of a different order? Including in those cases when the variables are not cointegrated? I have read various authors come to totally different opinions on this topic. :p
8. ### Newey-West HAC

"The Newey-West HAC-robust standard errors for the OLS estimators are consistent when the error term is heteroskedastic, autocorrelated, or both, as long as the regressors are stationary and ergodic." This confuses me since they are used with time series primarily and its unlikely that all the...
9. ### Two for one: Unique variable values

If the values in the original table are unique to start with can't you just sample without replacement?
10. ### GIS

thanks trinker.
11. ### Why One Sample For Confidence Intervals?

To me the CLT (a theory) is very different from the CI (a calculation). CI require assumptions about the distribution, commonly a normal distribution is assumed. Because of the CLT, if the sample size is large enough even if the population is non-normal you can still calculate a CI which relies...
12. ### Question on sample size and statistical test

Percentages are just a ratio. So I can't imagine why you would not be able to run ANOVA with them.
13. ### Why One Sample For Confidence Intervals?

I don't think the Central Limit Theorem uses any samples. Its a theory that says something will occur were you to use many samples. The confidence interval is being estimated from a sample for an unknown true population. It can't be estimated from multiple samples (unless you combined them into...
14. ### GIS

I don't have longitude and latitude. I have addresses.
15. ### Results interpretation 3 or more dummy variable

Normally a dummy variable only has two levels (normally they are 0 and 1). If you have a categorical variable with 3 levels you create two dummies (with 4 levels you create 3 etc). There are F tests, that tells you if a categorical variable made up of multiple dummies is significant on its own...
16. ### Odds ratio of 1.00 while the IV is statistically significant

With enough power, millions of cases, you can get statistical significance for nearly anything. That says nothing about the effect size per se other than it is likely the true effect size in the population. That said, a odds ratio of 1 is essentially a linear regression slope of zero so the...
17. ### Gaussian process and Gaussian regression

By gaussian do you mean linear regression? I believe that the joint probability reflects how you solve for Y given a set of X. Most practitioners ignore the theory behind the regression which is what this deals with.
18. ### Quandt likelihood ratio test , does SAS do this at all?

A chow test tells you if at a specific point in time the relationship between X and Y changes. That is the slope is different at specific periods in time. It is generally used in time series data. I don't understand the mailing stuff part??? hlsmith do you know how you difference a variable...
19. ### type ii error

I think the original number is ANOVA or regression. I suspect the latter number is just a descriptive statistic of a poll.
20. ### Multiple Regression

There is dispute if likert scale is ordinal or interval like. If its ordinal (if the dv is ordinal) then linear regression is not an appropriate method.