How could we create a mean excess plot (Hill estimator, etc.) in SAS  ?   ... View more

My data set look like this : Birth    Death    InfantDeath     Country 24.7      5.7           30.8             Albania I am using this code for analyse my data : PROC FREQ DATA = MYDATA; TABLE BIRTH*COUNTRY / CHISQ; RUN; Cramér's V is a measure of association between two nominal variables but I dont understnd why SAS compute Cramér's V for continuous variable and categorial variable ? In the output I got 0.2236 as V cramer for these variables : Birth and Country ... View more

I'am using the PROC GENMOD like this : PROC GENMOD DATA = LIFDAT; CLASS MFG; MODEL LIFETIME = MFG / DIST=GAMMA LINK=LOG TYPE3; RUN; but I dont understand why an estimated parameter equals zero What does it means ? can we change that ?   ... View more

Using PROC GENMOD, in "Criteria for Assessing Goodness of Fit" I got : Deviance = 0.6841 Scaled Deviance = 1.1002 What does it means ? Is my model good ? I know that a model with too large a deviance doesn’t fit the data well, but I dont know which deviance should I take ... View more

I have a GLM model :   PROC GENMOD DATA = MYDATA; CLASS COUNTRY JOB; MODEL MONEY = COUNTRY JOB / DIST = GAMMA LINK = LOG; RUN; I want to estimate the prediction error. How can I do 10-fold cross validation on my data with SAS ?     ... View more

I have 3 data : tab1, tab2 and tab3 like this :   tab1 : NAME1    NUMBER1  John      145 Max        200   tab2 : NAME2    NUMBER2 Johny      1415 Maximus        4200 Vince        765   and tab3 : NAME3    NUMBER3 Johnatan      145 Bruce        200   How to do a join like this ? :   NAME 1        NUMBER1         NAME2       NUMBER2        NAME3        NUMBER3 John                145                  Johny          1415                 Johnatan      145 Max                  200                Maximus        4200                 Bruce        200 .                         .                    Vince        765                             .               . ... View more

I have a large data (sorted by recent date) set like this :   ID             NAME             BEGIN              END               TOP 191080    John             25/04/2016    01/05/2016        NO 191080    John           08/06/2016    10/06/2016         NO 191080    John           21/06/2016    24/06/2016         Yes 191080    John           21/07/2016    24/09/2016         Yes 191141    Alex           16/01/2017    17/01/2017          NO 191141    Alex           22/02/2017    29/04/2017          NO   If "Yes" and "NO" occurs in TOP for an observation, then the most recent dates is choosen But if only "NO" occurs in TOP for an observation, then the minimum of BEGIN and maximum of END are choosen I mean how get this :   ID             NAME             BEGIN              END              191080    John           21/07/2016    24/09/2016     191141    Alex           16/01/2017    29/04/2017       ... View more

I have a data like this : ID             NAME      SURNAME            191080    John           WAYNE           191080    John           WAYNE          191080    John            WAYNE          191141    Alex            CLARK          191141    Alex            CLARK           I used PROC FREQ to count ID but I only get this :   ID              COUNT 191080           3 191141           2   But I want to count ID then add to my data, I mean how to get this :   ID             NAME      SURNAME      NUMBER          191080    John           WAYNE            3 191080    John           WAYNE            . 191080    John            WAYNE            . 191141    Alex            CLARK            2 191141    Alex            CLARK         .   ... View more

I have a large data set like this : ID             NAME             BEGIN              END              191080    John             25/04/2016    01/05/2016         191080    John           08/06/2016    10/06/2016          191080    John           21/06/2016    24/06/2016          191141    Alex           16/01/2017    17/01/2017  191141    Alex           22/02/2017    29/04/2017            For each first second row, I want to compute the difference (I mean get the number of days) between BEGIN  and END by ID For exemple for John : 08/06/2016 - 01/05/2016 = 38 21/06/2016 - 10/06/2016 = 11   and for Alex : 22/02/2017  - 17/01/2017 = 36   I mean how get this :     ID             NAME             BEGIN              END               RESULT 191080    John             25/04/2016    01/05/2016         191080    John           08/06/2016    10/06/2016           38 191080    John           21/06/2016    24/06/2016           11 191141    Alex           16/01/2017    17/01/2017  191141    Alex           22/02/2017    29/04/2017            36         ... View more