From a026326b4945812a5a8d1530b6d9613b9ad2cc99 Mon Sep 17 00:00:00 2001 From: John Darrington Date: Thu, 22 Nov 2012 16:25:06 +0100 Subject: [PATCH] Logistic Regression: Added a test to check the confidence interval display --- tests/language/stats/logistic.at | 266 +++++++++++++++++++++++++++++++ 1 file changed, 266 insertions(+) diff --git a/tests/language/stats/logistic.at b/tests/language/stats/logistic.at index 5f6232f7ca..b175244bdb 100644 --- a/tests/language/stats/logistic.at +++ b/tests/language/stats/logistic.at @@ -1206,3 +1206,269 @@ AT_CHECK([diff file1 file2], [1], [dnl AT_CLEANUP + +dnl Check that the confidence intervals are properly reported. +dnl Use an example with categoricals, because that was buggy at +dnl one point. The data in this example comes from: +dnl http://people.ysu.edu/~gchang/SPSSE/SPSS_lab2Regression.pdf +AT_SETUP([LOGISTIC REGRESSION confidence interval]) + +AT_DATA([ci.sps], [dnl +set FORMAT=F20.3 +data list notable list /disease age sciostat sector savings *. +begin data. +0 33 1 1 1 +0 35 1 1 1 +0 6 1 1 0 +0 60 1 1 1 +1 18 3 1 0 +0 26 3 1 0 +0 6 3 1 0 +1 31 2 1 1 +1 26 2 1 0 +0 37 2 1 0 +0 23 1 1 0 +0 23 1 1 0 +0 27 1 1 1 +1 9 1 1 1 +1 37 1 2 1 +1 22 1 2 1 +1 67 1 2 1 +0 8 1 2 1 +1 6 1 2 1 +1 15 1 2 1 +1 21 2 2 1 +1 32 2 2 1 +1 16 1 2 1 +0 11 2 2 0 +0 14 3 2 0 +0 9 2 2 0 +0 18 2 2 0 +0 2 3 1 0 +0 61 3 1 1 +0 20 3 1 0 +0 16 3 1 0 +0 9 2 1 0 +0 35 2 1 1 +0 4 1 1 1 +0 44 3 2 0 +1 11 3 2 0 +0 3 2 2 1 +0 6 3 2 0 +1 17 2 2 0 +0 1 3 2 1 +1 53 2 2 1 +1 13 1 2 0 +0 24 1 2 0 +1 70 1 2 1 +1 16 3 2 1 +0 12 2 2 1 +1 20 3 2 1 +0 65 3 2 1 +1 40 2 2 0 +1 38 2 2 1 +1 68 2 2 1 +1 74 1 2 1 +1 14 1 2 1 +1 27 1 2 1 +0 31 1 2 1 +0 18 1 2 1 +0 39 1 2 0 +0 50 1 2 1 +0 31 1 2 1 +0 61 1 2 1 +0 18 3 1 0 +0 5 3 1 0 +0 2 3 1 1 +0 16 3 1 0 +1 59 3 1 1 +0 22 3 1 0 +0 24 1 1 1 +0 30 1 1 1 +0 46 1 1 1 +0 28 1 1 0 +0 27 1 1 1 +1 27 1 1 0 +0 28 1 1 1 +1 52 1 1 1 +0 11 3 1 1 +0 6 2 1 1 +0 46 3 1 0 +1 20 2 1 1 +0 3 1 1 1 +0 18 2 1 0 +0 25 2 1 0 +0 6 3 1 1 +1 65 3 1 1 +0 51 3 1 1 +0 39 2 1 1 +0 8 1 1 1 +0 8 2 1 0 +0 14 3 1 0 +0 6 3 1 0 +0 6 3 1 1 +0 7 3 1 0 +0 4 3 1 0 +0 8 3 1 0 +0 9 2 1 0 +1 32 3 1 0 +0 19 3 1 0 +0 11 3 1 0 +0 35 3 1 0 +0 16 1 1 0 +0 1 1 1 1 +0 6 1 1 1 +0 27 1 1 1 +0 25 1 1 1 +0 18 1 1 0 +0 37 3 1 0 +1 33 3 1 0 +0 27 2 1 0 +0 2 1 1 0 +0 8 2 1 0 +0 5 1 1 0 +0 1 1 1 1 +0 32 1 1 0 +1 25 1 1 1 +0 15 1 2 0 +0 15 1 2 1 +0 26 1 2 1 +1 42 1 2 1 +0 7 1 2 1 +0 2 1 2 0 +1 65 1 2 1 +0 33 2 2 1 +1 8 2 2 0 +0 30 2 2 0 +0 5 3 2 0 +0 15 3 2 0 +1 60 3 2 1 +1 13 3 2 1 +0 70 3 1 1 +0 5 3 1 0 +0 3 3 1 1 +0 50 2 1 1 +0 6 2 1 0 +0 12 2 1 1 +1 39 3 2 0 +0 15 2 2 1 +1 35 2 2 0 +0 2 2 2 1 +0 17 3 2 0 +1 43 3 2 1 +0 30 2 2 1 +0 11 1 2 1 +1 39 1 2 1 +0 32 1 2 1 +0 17 1 2 1 +0 3 3 2 1 +0 7 3 2 0 +0 2 2 2 0 +1 64 2 2 1 +1 13 1 2 2 +1 15 2 2 1 +0 48 2 2 1 +0 23 1 2 1 +1 48 1 2 0 +0 25 1 2 1 +0 12 1 2 1 +1 46 1 2 1 +0 79 1 2 1 +0 56 1 2 1 +0 8 1 2 1 +1 29 3 1 0 +1 35 3 1 0 +1 11 3 1 0 +0 69 3 1 1 +1 21 3 1 0 +0 13 3 1 0 +0 21 1 1 1 +1 32 1 1 1 +1 24 1 1 0 +0 24 1 1 1 +0 73 1 1 1 +0 42 1 1 1 +1 34 1 1 1 +0 30 2 1 0 +0 7 2 1 0 +1 29 3 1 0 +1 22 3 1 0 +0 38 2 1 1 +0 13 2 1 1 +0 12 2 1 1 +0 42 3 1 0 +1 17 3 1 0 +0 21 3 1 1 +0 34 1 1 1 +0 1 3 1 0 +0 14 2 1 0 +0 16 2 1 0 +0 9 3 1 0 +0 53 3 1 0 +0 27 3 1 0 +0 15 3 1 0 +0 9 3 1 0 +0 4 2 1 1 +0 10 3 1 1 +0 31 3 1 0 +0 85 3 1 1 +0 24 2 1 0 +end data. + +logistic regression + disease WITH age sciostat sector savings + /categorical = sciostat sector + /print = ci(95). +]) + +AT_CHECK([pspp -O format=csv ci.sps], [0], [dnl +Table: Dependent Variable Encoding +Original Value,Internal Value +.000,0 +1.000,1 + +Table: Case Processing Summary +Unweighted Cases,N,Percent +Included in Analysis,196,100.000 +Missing Cases,0,.000 +Total,196,100.000 + +note: Estimation terminated at iteration number 4 because parameter estimates changed by less than 0.001 + +Table: Model Summary +Step 1,-2 Log likelihood,Cox & Snell R Square,Nagelkerke R Square +,211.195,.120,.172 + +Table: Categorical Variables' Codings +,,,Parameter coding, +,,Frequency,(1),(2) +sciostat,1.000,77,1,0 +,2.000,49,0,1 +,3.000,70,0,0 +sector,1.000,117,1, +,2.000,79,0, + +Table: Classification Table +,,,Predicted,, +,,,disease,,"Percentage +Correct" +,Observed,,.000,1.000, +Step 1,disease,.000,131,8,94.245 +,,1.000,41,16,28.070 +,Overall Percentage,,,,75.000 + +Table: Variables in the Equation +,,,,,,,,95% CI for Exp(B), +,,B,S.E.,Wald,df,Sig.,Exp(B),Lower,Upper +Step 1,age,.027,.009,8.647,1,.003,1.027,1.009,1.045 +,savings,.061,.386,.025,1,.874,1.063,.499,2.264 +,sciostat,,,.440,2,.803,,, +,sciostat(1),-.278,.434,.409,1,.522,.757,.323,1.775 +,sciostat(2),-.219,.459,.227,1,.634,.803,.327,1.976 +,sector,,,11.974,1,.001,,, +,sector(1),-1.235,.357,11.974,1,.001,.291,.145,.586 +,Constant,-.814,.452,3.246,1,.072,.443,, +]) + +AT_CLEANUP + -- 2.30.2