Hi    I have the following dataset and I want to create a formula that calculates the max profit from a certain amount of capital. The dataset below shows horserace data over a few hours. The field scrapetime is the time the latest data was taken about the race. The outcome is the horse being backed, the return percentage is the expected return on capital, the Time_to_event to the numbers of hours to the event starts, the max stake is the Max_Stake is the maximum amount that can be placed on the horse.      I have two variables: timeto and capital which I have set as follows:   %let timeto = 2; /* max of two hours to event*/ %let capital = 1000; /* max capital of €1000 */   I want the algorithm to do the following   sort by scrapetime /* which is fine apply timeto restriction i.e. only apply algorithm to rows where the timeto is less than 2 hours /* which is fine   So in the first event below the timeto restriction is met so the max_stake of 52 is placed and the capital_remaining = 1000-52 = 948   Here is the difficult part, i want the algorithm to work through each line but retain information from the previous lines.   So, for example, the second event is after the first event has taken place and the first bet lost so my remaining capital is still 948 (if it has one it would be 948+416= 1364)   So for each row it needs to determine which of the previous races have occurred between this event and the last and adjust the capital accordingly. I'm not sure how to do this. But the description of what I want at each row is   1. Have any previous events finished since the last row 2. If so what is the capital asjustment (this is just +profit if win and no adjustment if lose)   and to keep doing this until it gets to the last row       Event scrapetime event_time Outcome Return_Perc Time_To_Event Max_Stake Outcome Potential Profit Listowel 15SEP16:16:25 2016/9/15 - 16:40 Jack The Wire 0.02 0.3 52 Lose 416 Ayr 15SEP16:16:51 2016/9/15 - 17:20 Henley 0.01 0.5 18 Win 225 Crayford 15SEP16:16:52 2016/9/15 - 16:57 Lordsbury Dolly 0.02 0.1 15 Lose 44 Listowel 15SEP16:16:57 2016/9/15 - 17:45 Dos Picas 0.01 0.8 13 Lose 26 Ayr 15SEP16:16:57 2016/9/15 - 17:20 Catwilldo 0.04 0.4 629 Lose 4180 Pontefract 15SEP16:17:04 2016/9/15 - 17:10 Queen Of The Stars 0.01 0.1 1188 Win 567 Pontefract 15SEP16:17:34 2016/9/15 - 17:40 Irish Optimism 0.01 0.1 562 Win 821 Chelmsford City 15SEP16:17:34 2016/9/15 - 17:50 Prince Of Cool 0.01 0.3 28 Lose 112 Chelmsford City 15SEP16:17:38 2016/9/15 - 17:50 Prince Of Cool 0.01 0.2 485 Lose 1892 Chelmsford City 15SEP16:17:47 2016/9/15 - 18:20 Free Bounty 0.02 0.6 422 Lose 836 Chelmsford City 15SEP16:17:49 2016/9/15 - 18:20 Free Bounty 0.02 0.5 432 Lose 854 Chelmsford City 15SEP16:17:51 2016/9/15 - 18:20 Free Bounty 0.02 0.5 334 Lose 661 Chelmsford City 15SEP16:17:53 2016/9/15 - 19:50 Paper Faces 0.02 2 806 Lose 2338 Pontefract  15SEP16:17:59 2016/9/15 - 18:10 Bay Mirage 0.01 0.2 129 Win 1071 Pontefract  15SEP16:18:00 2016/9/15 - 18:10 Mon Brav 0.02 0.2 119 Lose 1258 Belmont Park 15SEP16:18:25 2016/9/15 - 18:30 Majestic Jessica 0.04 0.1 37 Win 95 Hove 15SEP16:18:46 2016/9/15 - 19:01 Kilmurry Luke 0.02 0.3 32 Lose 57 Belmont Park 15SEP16:18:48 2016/9/15 - 19:01 Dunk A Din 0.06 0.2 26 Win 192 Belmont Park 15SEP16:18:50 2016/9/15 - 19:01 Dunk A Din 0.06 0.2 18 Lose 133 Newcastle 15SEP16:19:06 2016/9/15 - 19:11 Bramble Diamond 0.03 0.1 74 Win 137 Delaware Park 15SEP16:19:29 2016/9/15 - 19:45 Tizthefastlaine 0.01 0.3 90 Lose 180 Delaware Park 15SEP16:19:31 2016/9/15 - 19:45 Tizthefastlaine 0.02 0.2 104 Win 208 Delaware Park 15SEP16:19:33 2016/9/15 - 19:45 Tizthefastlaine 0.02 0.2 107 Lose 212 Henlow 15SEP16:19:41 2016/9/15 - 19:47 Act Of War 0.02 0.1 13 Win 46 ... View more

  Hi   I have a number of factors in my dataset and each factor has a number of levels. What I want to achieve is shown below. My code performs a proc genmod on the dataset for each factor which produces the first 2 tables below to a dataset. The first table shows the correlation matrix for one of the factors (which has 6 levels); the second dataset shows the parameter estimates and standard errors for each of the parameters.     I want the code to loop through each combination of paramters (there are 15 combinations) and calculate the standard error of the differences and output the results to a table like the last time shown below. The formula for the standard error of differences I am using is:   Std(p1-p2) = sqrt[ Std(p1)^2 + Std(p2)^2 - 2*Std(p1)*Std(p2)*corr(p1,p2) ]   Then this is divided by the difference in the two paramters   so Std(p1-p2)/(p1-p2)   I've tried using contrast and other statements but I need it to be this exact formula and to be able to create a macro that performs this for difference factors with difference number of levels.     Correlation Matrix    RowName Prm1 Prm2 Prm3 Prm4 Prm5 Prm6 Prm1 1 -0.1487 -0.0531 -0.11 -0.2161 -0.1575 Prm2 -0.1487 1 0.0079 0.0163 0.0321 0.0234 Prm3 -0.0531 0.0079 1 0.0058 0.0115 0.0084 Prm4 -0.11 0.0163 0.0058 1 0.0238 0.0173 Prm5 -0.2161 0.0321 0.0115 0.0238 1 0.034 Prm6 -0.1575 0.0234 0.0084 0.0173 0.034 1       Paramter Estimates   RowName Estimates Std Error Prm1 0 0 Prm2 -0.0086 0.428094 Prm3 0.077144 1.199069 Prm4 -1.28369 0.578712 Prm5 0.206858 0.294558 Prm6 0.498941 0.404168     Standard Error of Differences   RowName Prm1 Prm2 Prm3 Prm4 Prm5 Prm6 Prm1             Prm2             Prm3 1481%           Prm4             Prm5             Prm6                   Standard Error of Differences Factor 1 Factor 2 Std Diff (%) Prm1 Prm1 … Prm1 Prm2 … Prm1 Prm3 1481% Prm1 Prm4 … Prm1 Prm5 … Prm2 Prm2 … Prm2 Prm3 … Prm2 Prm4 … Prm2 Prm5 … Prm3 Prm3 … Prm3 Prm4 … Prm3 Prm5 … Prm4 Prm4 … Prm4 Prm5 … Prm5 Prm5 …   My proc genmod code that produces the correlation and paramter estimates table is shown below.     proc genmod data=insurancedata; class glm31_cover_type(ref="COMP"); Weight NbClaims; model AvgClaim = glm31_cover_type/ dist=gamma link=log obstats SCALE=DEVIANCE CORRB; ods output ParameterEstimates =myObStats CORRB = CorrMatrix; run;    I have attached my dataset.   ... View more

I'm trying to figure out how the Contrasts statement works   I'm running a simple glm on a single factor (glm31_cover_type)   I want to test whether each of the parameter estimates is independent from the other levels of the factor cover type. I've read a few articles on this but it seems quite complicated. I thought there would just be a statement that would produce something like the attachment.   How would I adjust my code below so that I get something like the attached? So, for each level of the factor I want to get the standard error of the parameter differences. There are 5 levels so 5+4+3+2+1 = 15 standard errors.    Specifically I'm confused by the "contrast label factor 1 -1" code. How do I change this to incororate a test of all parameter differences in the factor.       proc genmod data=insurancedata; class glm31_cover_type(ref="COMP"); Weight NbClaims; model AvgClaim = glm31_cover_type/ dist=gamma link=log obstats SCALE=DEVIANCE CORRB; contrast 'Label1' glm31_cover_type 1 -1 ; ods output ParameterEstimates =myObStats CORRB = CorrMatrix Contrasts = TestOfContrasts; run; ... View more

  I'm having an issue with proc format.   I create a format table using the following code:   data quote_policy_map; infile map1 firstobs=2 dlm = ',' dsd missover lrecl = 10000 ; format start 8. label $20. ; input start label ; fmtname = "QuotePolMap"; run; proc format cntlin = quote_policy_map fmtlib; run; A screenshot of the dataset is shown below:         I have another dataset called fleet_quote_pols (screenshot below)     I want to use the format table to read in value for the policy nunber where there is a matching quote number. Here is the code I'm using:   data fleet_quotes_pols1(drop = quote_no key rename = (quote_no2 = quote_no )) ; set fleet_quotes_pols; quote_no2 = input(quote_no,comma8.); policy_no1 = put(quote_no2,QuotePolMap.); run;   The code is returning policy numbers from the format table when there is a matching quote number BUT when there is not match it returns the quote number which I don't understand. Below is a screenshot of the dataset fleet_quotes_pols1. The cell with the red box is what I want but every other cell under the field policyno1 should be blank as there isn't a match.     Any ideas where I'm going wrong?   ... View more