topic Re: Regression Analysis in Statistical Procedures

Regression Analysis

KafeelBasha — Sun, 09 Oct 2016 06:19:02 GMT

Hello

Please help me with below questions

1) Difference between estimates and standardized estimes in regression analysis.

2) Why do we get t stats in Linear regression and z stats in Logistic regression.

3) Please provde some references to Time series Analysis.

Thanks

Re: Regression Analysis

Norman21 — Sun, 09 Oct 2016 06:54:36 GMT

This site will have the answers to those questions:

http://www.ats.ucla.edu/stat/sas/

Re: Regression Analysis

Reeza — Sun, 09 Oct 2016 06:56:34 GMT

I don't think Q2 is correct.

Re: Regression Analysis

KafeelBasha — Sun, 09 Oct 2016 08:25:26 GMT

Let me frame the question again

In the linear regression analysis output table we are having a column on t value.

In the logistic regression anlaysis output table we are having a column on z value.

Is there any specific reason for it?.

Thanks

Re: Regression Analysis

Norman21 — Sun, 09 Oct 2016 08:33:54 GMT

Yes, there is a specific reason for this. Have a look here:

http://zencaroline.blogspot.co.uk/2011/04/difference-between-z-test-and-t-test_10.html

Re: Regression Analysis

Reeza — Sun, 09 Oct 2016 08:35:33 GMT

Post a screenshot of what you're referring to please.

Re: Regression Analysis

Ksharp — Sun, 09 Oct 2016 08:39:35 GMT

t value is ususally for small size of sample.

z value is for the large size of sample.

When the size of sample is big enough, t almost equal z.

Here REG use t value , I guess REG want get more accurate parameter estimate.

Re: Regression Analysis

Norman21 — Sun, 09 Oct 2016 08:51:42 GMT

With simple linear regression, by default the "Parameter Estimates" table contains the estimates of and together with the t statistics and the corresponding p-values for testing whether each parameter is significantly different from zero.

http://support.sas.com/documentation/cdl//en/statug/68162/HTML/default/viewer.htm#statug_reg_gettingstarted01.htm

Re: Regression Analysis

Reeza — Sun, 09 Oct 2016 09:54:34 GMT

And logistic regression using chi square AFAIK, not Z. I'm curious as to where OP is seeimg Z or under what circumstances that's generated.

http://support.sas.com/documentation/cdl//en/statug/68162/HTML/default/viewer.htm#statug_logistic_examples01.htm

Re: Regression Analysis

Reeza — Sun, 09 Oct 2016 20:02:55 GMT

@KafeelBasha wrote:

2) Why do we get t stats in Linear regression and z stats in Logistic regression.

I tried a variety of regressions this morning and couldn't get any z-statistics from Logistic Regression using PROC LOGISTIC. Are you using a different procedure? Please post code and data to replicate your issue.

Re: Regression Analysis

KafeelBasha — Mon, 10 Oct 2016 15:14:17 GMT

Hello

I tried with R function glm().

Please refer the below link

http://www.ats.ucla.edu/stat/r/dae/logit.htm

Thanks

Re: Regression Analysis

StatDave — Mon, 10 Oct 2016 18:53:51 GMT

The Wald chi-square statistic presented in the LOGISTIC and GENMOD procedures for a logistic model are just the square of a Z statistic with identical p-value.

...and standardized estimates are detailed in the description of the STB option in the "Syntax: MODEL statement" section of the LOGISTIC documentation.

Re: Regression Analysis

Reeza — Mon, 10 Oct 2016 22:27:59 GMT

@StatDave thanks for clarification!