Hello,   I have a dataset named victimsummary of unique crash ID's with dr_lic_num1 being the driver's license number.  Many dr_lic_num can show up in the dataset if they are involved in more than 1 crash.  I need to filter the dataset to output the records for dr_lic_num1's that occur more than n times.  At the beginning I am starting with n = 1 then working my way up after looking at the results. I tried this code: select * from (select ID, dr_lic_num1, count(dr_lic_num1) as freq1     from victimsummary     group by ID, dr_lic_num1     ) where freq1 > 1; quit; Any help is greatly appreciated!\ -Charles ... View more

Hello~ I need help finding specific records in a dataset: I have one dataset called CRASH with contains auto crash records.  The dataset has crashid, driverid, and atfaultYN.  The crashid is unique for two records: the at fault driver and the not at fault driver.  Each record has the driverid as well as the atfaultYN variable which = 0 for atfault and 1 for not at fault.  Of course, one driver can have many crashes so driverid is repeated throughout the dataset but the crashID is unique to the two records of each crash.  Because the analysis was previously on drivers with high frequency of not at fault crashes to determine fraud, we have another dataset REAREND which has crash records for the drivers who have high frequency of not at fault crashes. So for example, I have: CRASH Crashid          driverID               AtfaultYN 110                2                              0 110                91                            1 118                6                              1 118                210                          0 122                91                            1 122                13                            0 256                87                            0 256                123                          1 REAREND Crashid          driverID               AtfaultYN 110                    91                         1 118                    6                           1 122                    91                         1 Now our analysis is on the drivers at fault.  I need to extract the crash record of the at fault drivers (atfaultYN=0) from CRASH for each crash for the not at fault drivers in REAREND. So I need: VICTIM Crashid          driverID               atfaultYN 110                    2                         0 118                    210                     0 122                    13                       0 There are 3 million crash records and only 796k crash records that I need, so I don't want the entire dataset, just the at fault crash records for the driverid in REAREND. Thanks in advance for your help! -C ... View more

Hello,   Good afternoon-- I am trying to write a program to automate outlier detection.  I need to produce a list of values > 3 or < -3 along with its variable name and obs number. I used proc standard to standardize my variables: data=work.prepstandard; set work.dataset (drop= id x1 x2 x3 x4 x5); run; PROC STANDARD DATA=work.prepstandard MEAN=0 STD=1 OUT=zstandards; VAR x6 x7 x8 x9 x10 x11 x12 x13 x14 x15 x16; run; Then tried running the following array, but it doesn't work: DATA work.outliers;     SET zstandards;        ARRAY x _NUMERIC_;          DO i=1 TO DIM(x);            IF x > 3 or x <-3 THEN DO;                obsNum= _N_;              OUTPUT;           END;        END; run; Did I do something wrong in the array, or is this the wrong way to go about it?  Thanks for helping me out...  I sincerely appreciate it! -Charles ... View more

Hello, I am writing a program and all I want is the Levene's Test statistic in PROC GLM-- I don't need the rest of the output. Is there any way to just extract the Levene's test or suppress everything but the Levene's test? Thanks for any help you could give! -Charles ... View more

Hello, I am trying to code a simple program in which the user inputs the libname then the dataset once and several proc's and data steps are used with this dataset.  I'd like to have the option for the user to block off portions of code to run one proc or one data set independently, so I can't put everything in one giant macro.  How can I have the user input the dataset location just once then have some sort of alias or another way of referring to this dataset multiple times?  Thanks for helping out a newbie! -Charles ... View more

Hello, I'm having trouble with doing the following, can anyone help? The dataset has the keyword sale or sales at the beginning, middle, or end of a string that is bracketed[], quoted "", or neither.  The dataset has an impressions variable and clicks variable for each observation and I need to indicate if sale or sales are at the beginning, middle or end of the string for sale or sales (separately) as well as keep the impressions and clicks to add up for each instance of each appearance of 'sale' or 'sales' in the string.    I need this to create a summary table of the number of impressions and the number of clicks for sale at the beginning, middle, and end of the string then do the same for sales. Ex: Keyword                                               Impressions                                  Clicks [sale on gas grills]                                   10                                                  2 "Gas grill sales"                                        0                                                  0 green egg sale grills                                 420                                             336 I wrote code last night that worked, but its highly specific to this dataset.  Is there a better way?  Thanks very much for your help. ... View more