About NKormanik

NKormanik · ‎03-12-2022

@Reeza wrote: make rules such as : if X2, X3, X4 are high this person is likely to be in the high performing group. Precisely. That's what I've been trying to do. Stepwise regression is supposed to eliminate the variables that are not meaningful.

NKormanik · ‎03-11-2022

@pink_poodle wrote: The observation with 92% correctness of prediction had to satisfy the criteria of many of the 100 predictors, not just X1. I'm interpreting that single observation to be golden -- like a nugget of solid gold among the rock rubble. True, not only X1 to take note of, but all the 'significant' variables Proc Logistic has come up with. Say: X1, X7, X33, X49, X81. Those all make up the Super Team. Take extra special note of 'em. When those babies line up, you're pretty safe to bet big.

NKormanik · ‎03-11-2022

@Reeza, well, that there are other statistical tools available that can help solve the problem is hugely encouraging. Absolutely for sure. Presently, however, I'm attempting to gain something from Proc Logistic. Like, anything. When it becomes totally apparent that Proc Logistic is a bust, then I'll move on.

NKormanik · ‎03-11-2022

Thanks @PaigeMiller. Well, then, given the information in the table at top, particularly Probability, how might one use this information? The challenge is: We seek a high Y outcome, we have Xi - Xn, how can the table above help us achieve our objective? (note: Multicollinearity is supposed to be less of a problem with Logistic Regression, than it is with Linear Regression.)

NKormanik · ‎03-10-2022

Today's question is about interpreting. Please see the following table: Predicted This table was created by Proc Logistic. Model is to predict i_50505_Z. There are around 100 independent variables (not shown). The 'Probability' has to do with 'Odds Ratio' -- the odds of arriving at i_50505_Z = 1, versus i_50505_Z = 0. The column is sorted with highest Probability at top. I find this table to be fascinating, if I'm interpreting it correctly. It 'scores' every single observation in the entire dataset. Looking across the independent variables, IFF a particular variable is found to be 'significant' (from other not shown tables), and the Probability is shown to be high, the value for that independent variable observation is the best to choose for arriving at the desired dependent variable target. Example: You're targeting i_50505_Z to be in the top 10% (i.e., i_50505_Z = 1). Probability is 0.922 for a particular observation. Independent variable X1 (p<.001) for that observation is (say) 4.7. Then X1=4.7 is a pretty darn good guess for arriving at your objective. In other words, given a circumstance where you see X1=4.7 you are highly likely to find high values of i_50505_Z. Discovering this is the precise purpose of the statistical analysis. If the program can't do it, ask for a refund. Please share your thoughts and clarifications. Nicholas Kormanik p.s. -- a side issue. Notice that in the i_50505_Z column is 0.39. Such value is certainly not among the top. Really curious how that got to be included.

NKormanik · ‎03-08-2022

@Patrick That's some beautiful code!

NKormanik · ‎03-07-2022

@Patrick , TOURMALINE TITAN, you are definitely on track. I agree more than 100%.

NKormanik · ‎03-07-2022

@SASKiwi That's what I've been figurin' as well. All it would take is a bit of different metadata to throw off the usual Windows compare programs. (I think such programs are able to 'overlook' metadata differences in .mp3 files, by the way. Title, Album, Artist, etc., tucked in right before the actual song begins.) One can easily get a sense of SAS metadata by creating the smallest SAS dataset and look at it's size -- 99% of such a dataset appears to be made up of metadata. Why hasn't some genius coded the needed macro yet??!! Compare all datasets in given library.....

NKormanik · ‎03-06-2022

I suspect there should be at least one set of duplicates. Just a hunch. (By the way, what I'm doing is running a number of Proc Logistics, but using different options (as usual with SAS, options are abundant). I think the results for some of the output tables/datasets for these options combinations should be identical. Just wanted to check that out.) Regarding using hash, etc., that's what I thought various Windows compare programs do. Was surprised when they came up empty, as far as finding duplicates. One such program is AllDup .

NKormanik · ‎03-06-2022

4950!! Even with multi-threaded SAS OnDemand, seems a whopper. Hate to get permanently kicked off. On a stand-alone desktop, yikes. Plus, how would one code it anyway? (Time for more macro learning.... Humphh....)

NKormanik · ‎03-05-2022

Bonus Question: If you had to do a 2-dataset comparison, given 100 datasets, how many comparisons would you have to do to check each and every one of 'em? Explain your answer.

NKormanik · ‎03-05-2022

I'm about to search for answers. Who knows if I'll find a solution. But, just putting this up here, in case one of you has some thoughts and wants to share. So, 100 datasets in a library. It's possible that some of them are identical to each other, with merely different names. I've used standard Windows tools to test this out, and the results came back negative. Curious if SAS concurs? Google is indicating that Proc Compare has possibilities. However, comparing two datasets at a time, given 100 datasets, doesn't seem to be the way to go. Looking forward, as always, to your responses. Nicholas Kormanik

NKormanik · ‎03-03-2022

Doing a series of Proc Logistics on multiple datasets (finally!). SAS seems to have frozen after getting through around 7 datasets (of 59 total). Trying everything I can think of to take a pulse to see if SAS is still alive. Resource Monitor shows it's running, 31 threads, 6.24% of CPU. Analyze Wait Chain says "One or more threads of sas.exe are waiting to finish network I/O." On a stand-alone machine? Is there a better way to ascertain whether the patient is alive or dead? Is it a good idea, or even possible, to 'flush' between iterations? In other words, before allowing SAS to proceed onto the next dataset, should I insist it visit the Ladies Room? How exactly do I do that? Thanks! Nicholas Kormanik

NKormanik · ‎03-01-2022

Goodness. "Press ANY key..." Where's the "ANY" key??!# Will retry. Thanks all for the help.

NKormanik · ‎03-01-2022

@Kurt_Bremser I've called the ETF variable in the dataset "ETF_List". Maybe that's the problem? 1 2 data _null_; 3 set sas_1.ETF_dataset; 4 call execute('%nrstr( 5 %let etf = ' !! value !! '; 6 %include "c:\0_sas_1\logistic_all.sas", 7 )'); 8 run; NOTE: Numeric values have been converted to character values at the places given by: (Line):(Column). 5:17 NOTE: Variable value is uninitialized. NOTE: There were 59 observations read from the data set SAS_1.ETF_DATASET. NOTE: CALL EXECUTE generated line. 1 + %let etf = .;%include "c:\0_sas_1\logistic_all.sas", 2 + %let etf = .;%include "c:\0_sas_1\logistic_all.sas", ERROR: Open code statement recursion detected. 3 + %let etf = .;%include "c:\0_sas_1\logistic_all.sas", ERROR: Incorrect %INCLUDE statement will not be executed. There is a syntax error. 4 + %let etf = .;%include "c:\0_sas_1\logistic_all.sas", ERROR: Open code statement recursion detected. 5 + %let etf = .;%include "c:\0_sas_1\logistic_all.sas", ERROR: Incorrect %INCLUDE statement will not be executed. There is a syntax error. etc. etc.

Online Status	Offline
Date Last Visited	yesterday

When is your SAS program good enough???

Re: Reset SAS without restarting SAS????

Reset SAS without restarting SAS????

Re: PROC GAMSELECT

Re: PROC GAMSELECT

PROC GAMSELECT

Re: Fascinating exchange with LLM

Fascinating exchange with LLM

Re: Trouble getting a macro to execute....

Trouble getting a macro to execute....

Re: When is your SAS program good enough???

Re: When is your SAS program good enough???

Re: When is your SAS program good enough???

Re: When is your SAS program good enough???

Re: When is your SAS program good enough???

Re: Using SAS Studio Online to Convert A Dataset

Re: User wants SAS code to return to Log window

Re: Logistic Regression -- Understanding Maximum Likelihood

Re: Interpreting 'Predicted' in Proc Logistic -- What's your take?

Interpreting 'Predicted' in Proc Logistic -- What's your take?

Re: Interpreting 'Predicted' in Proc Logistic -- What's your take?

Re: Interpreting 'Predicted' in Proc Logistic -- What's your take?

Re: Interpreting 'Predicted' in Proc Logistic -- What's your take?

Re: Interpreting 'Predicted' in Proc Logistic -- What's your take?

Interpreting 'Predicted' in Proc Logistic -- What's your take?

Re: 100 datasets in library... Are any of them duplicates?

Re: 100 datasets in library... Are any of them duplicates?

Re: 100 datasets in library... Are any of them duplicates?

Re: 100 datasets in library... Are any of them duplicates?

Re: 100 datasets in library... Are any of them duplicates?

Re: 100 datasets in library... Are any of them duplicates?

100 datasets in library... Are any of them duplicates?

Hmmm.... Is SAS Dead In The Water?, or Just Taking It's Time?

Re: Macro code to iterate through list

Re: Macro code to iterate through list