cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Search instead for 
Did you mean: 
datalligence
‎09-01-2015
  • 35 Posts
  • 0 Likes Given
  • 0 Solutions
  • 1 Likes Received

Re: Test for Difference in Proportions - T Test? Proc GLM?

by Fluorite | Level 6 in Statistical Procedures
‎08-30-2009 02:22 AM
‎08-30-2009 02:22 AM
Thank you so much Steve! I have also found out how the Z test for proportions is very very similar to the "equal variances not assumed" version of Student's t test for independent samples when you have a binomial dependent variable (0/1). Gonna write about this on my blog. Thanks again. http://datalligence.blogspot.com/ ... View more

Re: Ranking huge dataset

by Fluorite | Level 6 in Statistical Procedures
‎08-28-2009 07:31 AM
‎08-28-2009 07:31 AM
Hi Pabitra, According to SAS, PROC RANK stores all values in memory of the variables for which it computes ranks. Check out the below paper for a workaround, http://www.nesug.org/Proceedings/nesug04/pm/pm05.pdf Hope it helps. Datalligence http://datalligence.blogspot.com/ ... View more

Re: Test for Difference in Proportions - T Test? Proc GLM?

by Fluorite | Level 6 in Statistical Procedures
‎08-27-2009 08:52 AM
‎08-27-2009 08:52 AM
Thank you Steve. So my guess is Proc GLM uses the Z test for proportions. I also did a chi-square test on renewal rates between 2 groups, and a 2-sample test for proportions (using Z stat). The p-values came out very similar. My question or doubt is, why or when is the Z-test for proportions called the T-test? According to the SAS online doc, "PROC GLM handles models relating one or several continuous dependent variables to one or several independent variables." So how does it handle a categorical/binomial dependent variable? Which test or statistics does it use when the dependent variable is binomial (Yes/No, 0/1)? And under what assumptions does it equate the categorical dependent variable to a continuous dependent variable? Thanks again. ... View more

Test for Difference in Proportions - T Test? Proc GLM?

by Fluorite | Level 6 in Statistical Procedures
‎08-27-2009 07:17 AM
‎08-27-2009 07:17 AM
Hi, I am coming across a lot of cases where people are talking about, or using T-Test when they are comparing campaign response rates, membership renewal rates, etc. My understanding is that the T-Test is not appropriate for such cases. And that people are confusing the T-Test with the Two Sample test for proportions (which uses the Z stat). Personally speaking, I think the Chi Square test and its related tests (Fisher's Exact, Mc Nemar) are more appropriate for testing the differences in proportions/ratios. There is one case where people have actually used a Proc GLM to test the difference in renewals among customer groups based on different communication channels. So how can Proc GLM or the t-test which are meant for continuous dependent values be used for comparing proportions/ratios? Thanks ... View more

post chi-square test

by Fluorite | Level 6 in Statistical Procedures
‎08-05-2009 09:49 AM
‎08-05-2009 09:49 AM
I am doing a chi-square test to see if there is a difference in the membership renewal rates among multiple groups. The chi-square test is significant. Now, if I want to test which cells are different, how do i do the marascuilo procedure in SAS? I found out from some papers that I can do this with PROC GENMOD and PROC MULTTEST. Any suggestions? Thanks Message was edited by: datalligence ... View more

Re: Proc Means & Proc Summary

by Fluorite | Level 6 in SAS Procedures
‎02-23-2009 05:23 AM
‎02-23-2009 05:23 AM
Some more differences - If you don't mention the VAR statement, PROC SUMMARY produces a simple count of observations. But PROC MEANS analyzes all the numeric variables that are not listed in the other statements. - If you print the data created by PROC SUMMARY, you'll get _TYPE_ column along with the other descriptive statistics. - In PROC MEANS, number of records is N whereas it is denoted by _FREQ_ in PROC SUMMARY This is a very common interview question here in India 🙂 ... View more

Re: Camparing two data fields

by Fluorite | Level 6 in SAS Enterprise Guide
‎08-04-2008 05:03 AM
‎08-04-2008 05:03 AM
Not very sure of what you exactly want but i think you can try using the first.variable_name, last.variable_name, and the lag function. data yourdata; by name date; if first.date <> last.date then; diff_date=date-lag(date); diff_value=date-lag(value); .... .... Thanks, Romakanta ... View more

no default action for the library data type

by Fluorite | Level 6 in SAS Enterprise Guide
‎07-28-2008 04:55 AM
1 Like
‎07-28-2008 04:55 AM
1 Like
hi, i'm not able to view the libraries or the datasets. when i double-click on a library or a datset, i'm getting "no default action for the library data type" error. can somebody please help? thanks, romakanta ... View more

Re: proc cluster for mixed data

by Fluorite | Level 6 in SAS Procedures
‎06-25-2008 02:11 AM
‎06-25-2008 02:11 AM
FASTCLUS has a lot of limitations, and is not suitable for mixed data. I guess I will have to use PROC DISTANCE with Gower's dissimilarity. But when I run PROC CLUSTER, which distance method will be the most appropriate? Thanks, Romakanta ... View more

proc cluster for mixed data

by Fluorite | Level 6 in SAS Procedures
‎06-24-2008 08:32 AM
‎06-24-2008 08:32 AM
I have a data set of about 600,000 obs. The variables I would like to use for grouping observations/transactions include numeric and categorical variables. In PROC CLUSTER, which METHOD or distance measure would be the most appropriate? ... View more

Re: how to test the logisctic model

by Fluorite | Level 6 in SAS Forecasting and Econometrics
‎06-11-2008 07:37 AM
‎06-11-2008 07:37 AM
I guess you are talking about classifying new observations. In proc logistic, use the outmodel option. This saves the fitted model information in a data set. For example, proc logistic data=training_data outmodel=mylib.Fitted_Model; .... .... Use the above data Fitted_Model to model your new dataset, proc logistic noprint inmodel=mylib.Fitted_Model; score data=New_Data out=Scored_Data; .... Scored_Data will have the data and the predicted values. Romakanta ... View more

Re: compare values in consecutive rows and print rows based on some co...

by Fluorite | Level 6 in ODS and Base Reporting
‎05-09-2008 01:02 AM
‎05-09-2008 01:02 AM
chuck and cynthia, thanks a lot!!! now, i think i know how to attack this:-) i will work on this over the weekend. thanks again. romakanta ... View more

Re: compare values in consecutive rows and print rows based on some co...

by Fluorite | Level 6 in ODS and Base Reporting
‎05-08-2008 12:46 PM
‎05-08-2008 12:46 PM
Thanks Cynthia, I have tried the Lag function to compare values in consecutive rows but the problem is that it selects or extracts only the row below whenever there is a match. In the example below, only obs 2, 3, and 5 will be selected. But it should be obs 1, 2, 4 and 5. obs ori value lag value 1 100 2 100 100 3 300 100 4 200 300 5 200 200 Using arrays seems a better option but I don't how much time I can spend with the help manuals/documents 'coz this project's already under a time crunch! I'm still a newbie when it comes to reports/data manipulation as I use SAS Stat procedures most of the times on cleaned data 🙂 romakanta ... View more

compare values in consecutive rows and print rows based on some condit...

by Fluorite | Level 6 in ODS and Base Reporting
‎05-08-2008 02:26 AM
‎05-08-2008 02:26 AM
I have the following variables VehicleID, TransactDate, TransactTime, OdometerReading, TransactCity, TransactState. VehicleID is the unique vehicle ID, OdometerReading is the Odometer Reading, and the others are information related to the transaction time and location of the fuel card (similar to a credit card). The records will be first grouped and sorted by VehicleID, TransactDate, TransactTime and OdometerReading. Then all records where the Vehicle ID and TransactDate is same for consecutive rows, AND TransactCity or TransactState are different for consecutive rows should be printed. I also would like to add two derived variables. 1. Miles will be a derived variable that is the difference between consecutive odometer readings for the same Vehicle ID. 2. TimeDiff will be the second derived variable that will categorize the time difference for a particular vehicle on the same day. My report should look like: VehID TrDt TrTime TimeDiff Odometer Miles TrCity TrState 1296 1/30/2008 08:22:42 0:00:00 18301 000 Omaha NE 1296 1/30/2008 15:22:46 7:00:04 18560 259 KEARNEY NE Can someone please help me here? Thanks, Romakanta ... View more

reading/importing a .rpt file

by Fluorite | Level 6 in SAS Enterprise Guide
‎04-24-2008 05:44 AM
‎04-24-2008 05:44 AM
I have this .rpt file of about 100,000 records. I want to directly read or import this into SAS. The data is of fixed width type where fields are aligned in columns with spaces bewteen each field. When the file size was smaller, or the # of records were less I was able to import it into excel, save it as a tab-delimted text file and then import it directly into SAS. There are a lot of fields/variables and I don't want to use column inputs+informats for such a long list of variables, so how do i import/read this .rpt file into SAS? And can I use infile statement with column and informat specifications if there is no other option? Thanks, Romakanta ... View more
Contact Me
Online Status
Offline
Date Last Visited
‎09-01-2015 07:11 AM
Likes from
View All
Quick links