8. Model selection-2 - !"#$%&’$’($...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: !"#$%&’$’($ *+,-./"(&0 !"#1.%23 444 562"78 9:++ ;7"<.2$"%3 #= >&$?"78%#7 !&2@&2& -(A7"8?%B C?DED !4F5G *+, 562"78 9:++ !D -(A7"8?%-FEHI 5HIHJG4FK LFM IFN45G4J MHNMH554FK C&2% 44 F;GI4KH •-#/.0 $.0.(’#7 =#2 .O&1"7"78 &$$#("&’#7 P – M&7/#1"Q./ .O6.2"1.7%$B @0#(R./ &7/ [email protected]#(R./ – J#7T21&%#23 U?36#%?.$"$ %.$’78V &7&03$"$ – HO60#2&%#23 &7&03$"$ •-#/.0 $.0.(’#7 =#2 62./"(’#7P – 47%.2.$% (.7%.2$ #7 @."78 &@0. %# 62./"(% W?"(? (&%.8#23 &7 "7/"<"/S&0 #@$.2<&’#7 W"00 =&00 "7%# @&$./ #7 %?. <&0S.$ #= #7. #2 1#2. .O60&7&%#23 <&2"&@0.$D >. &2. 1#$% "7%.2.$%./ "7 %?. 62#6.2’.$ #= 62./"(’#7$ 1&/. @&$./ #7 #S2 0#8"$’( 1#/.0D ,,X !4F5G *+, 562"78 9:++ !D -(A7"8?% CMHE4JG4FK • 5S66#$. W. &2. "7%.2.$%./ "7 ?#W W.00 C5Y U18Z10V &% /"&87#$"$ 62./"(%$ W?.%?.2 %?. %S1#2 ?&$ 6.7.%2&%./ %?. 62#$%&’( (&6$S0.D • >. (&7 T% & 0#8"$’( 1#/.0 2.0&’78 C5Y %# 6.7.%2&’#7D • 5#1. 6.#60. 0"R. %# 0##R &% &7 .O%.7$"#7 #= M 9 %# 0#8"$’( 2.82.$$"#7[ 4 /#7\%D • 5"7(. %?. #S%(#1. W. W&7% %# 62./"(% "$ @"7&23B 4 62.=.2 %# .O&1"7. %?. $.7$"’<"%3 &7/ $6.("T("%3 #= & 62./"(’#7 @&$./ #7 6$& 0.<.0D • HO&160. =#00#W$D !4F5G *+, 562"78 9:++ !D -(A7"8?% ,,] C5Y YKE CMF5GYGH JYKJHM • ^#W W.00 (&7 W. 62./"(% 6.7.%2&’#7 #= %?. 62#$%&’( (&6$S0. @&$./ #7 C5Y 0.<.0 &% /"&87#$"$_ !4F5G *+, 562"78 9:++ !D -(A7"8?% ,,‘ 20 40 60 80 100 120 140 0.0 0.5 1.0 1.5 Logistic Regression PSA (mg/ml) Penetration of Prostatic Capsule (1 = yes) 4K 5GYGY !4F5G *+, 562"78 9:++ !D -(A7"8?% ,a: . logistic penetration psa Logistic regression Number of obs = 380 LR chi2(1) = 49.13 Prob > chi2 = 0.0000 Log likelihood = -231.58055 Pseudo R2 = 0.0959------------------------------------------------------------------------------ penetration | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]-------------+---------------------------------------------------------------- psa | 1.051456 .0097262 5.42 0.000 1.032565 1.070693------------------------------------------------------------------------------ . predict phat (option pr assumed; Pr(penetration)) . graph box phat, by(penetration) !Fb CIFG !4F5G *+, 562"78 9:++ !D -(A7"8?% ,a+ .2 .4 .6 .8 1 1 Pr(penetration) Graphs by penetration 4K 5GYGY • 5.7$"’<"%3 &7/ $6.("T("%3P !4F5G *+, 562"78 9:++ !D -(A7"8?% ,a9 . estat classification Logistic model for penetration-------- True -------- Classified | D ~D | Total-----------+--------------------------+----------- + | 45 17 | 62- | 108 210 | 318-----------+--------------------------+----------- Total | 153 227 | 380 Classified + if predicted Pr(D) >= .5 True D defined as penetration != 0-------------------------------------------------- Sensitivity Pr( +| D) 29.41% Specificity Pr( -|~D) 92.51% Positive predictive value Pr( D| +) 72.58% Negative predictive value Pr(~D| -) 66.04%-------------------------------------------------- False + rate for true ~D Pr( +|~D) 7.49% False - rate for true D Pr( -| D) 70.59% False + rate for classified + Pr(~D| +) 27.42% False - rate for classified -...
View Full Document

This note was uploaded on 02/09/2012 for the course STAT 513 taught by Professor Barbaramc.knight during the Spring '11 term at University of Washington.

Page1 / 19

8. Model selection-2 - !"#$%&’$’($...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online