statistics - Understanding co-efficients of logistic regression R -


this question understanding logistic regression output using r

here sample data frame:

    drugpairs             adverseevent  y    n 1   rebetol + pegintron       nausea   29 1006 2   rebetol + pegintron      anaemia   21 1014 3   rebetol + pegintron     vomiting   14 1021 4   ribavirin + pegasys       nausea    5  238 5   ribavirin + pegasys      anaemia   12  231 6   ribavirin + pegasys     vomiting    1  242 7 ribavirin + pegintron       nausea   15  479 8 ribavirin + pegintron      anaemia    7  487 9 ribavirin + pegintron     vomiting    9  485

this describes number of times particular drug pair has caused medically adverse event. (y=yes, n=no). ran logistic regression on data in r using following commands:

mod.form="cbind(y,n) ~ drugpairs * adverseevent" glmhepa.out=glm(mod.form, family=binomial(logit), data=hepatitis.df)

the summary output follows (only showing co-efficients table)

                                                      estimate std. error z value (intercept)                                          -3.8771     0.2205 -17.586 drugpairsribavirin + pegasys                          0.9196     0.3691   2.491 drugpairsribavirin + pegintron                       -0.3652     0.4399  -0.830 adverseeventnausea                                    0.3307     0.2900   1.140 adverseeventvomiting                                 -0.4123     0.3479  -1.185 drugpairsribavirin + pegasys:adverseeventnausea      -1.2360     0.6131  -2.016 drugpairsribavirin + pegintron:adverseeventnausea     0.4480     0.5457   0.821 drugpairsribavirin + pegasys:adverseeventvomiting    -2.1191     1.1013  -1.924 drugpairsribavirin + pegintron:adverseeventvomiting   0.6678     0.6157   1.085

i understand co-efficients give probabilistic odds. curious however, why there no co-efficients adverseeventanaemea , why there no co-efficient anycombination of drugs , adverse event anaemea? (the last 4 rows combination effects of drugs , adverse events)

the coefficients discrete variables effect differences (otherwise known contrasts). baseline taken lowest level of factor in sort order of hte levels vector, alphabetically sorted default. cna change sort ort change refence point , change coefficeints. interactions terms such have in teh second model never find useful @ coefficients thems selves. it's going better @ predicted effects selected comparisons.

and ... don't forget logistic modles coefficients estimated on log0odds scale. make use of predict more helpful because predict.glm using type= "response" allows report effects on probability scale.


Comments

Post a Comment

Popular posts from this blog

apache - Remove .php and add trailing slash in url using htaccess not loading css -

i have add following code htaccess file removing .php extension , add trailing slash urls. worked fine reduced page loading speed , css code not loading @ all. pages ugly. please help rewriteengine on rewritebase / ## hide .php extension snippet # externally redirect /dir/foo.php /dir/foo rewritecond %{the_request} ^[a-z]{3,}\s([^.]+)\.php [nc] rewriterule ^ %1/ [r,l] # add trailing slash rewritecond %{request_filename} !-f rewritecond %{request_uri} !/$ rewriterule . %{request_uri}/ [l,r=301] # internally forward /dir/foo /dir/foo.php rewritecond %{request_filename} !-d rewritecond %{request_filename}.php -f rewriterule ^(.*?)/?$ $1.php [l] we can rewrite urls using .htaccess files. before writing in .htaccess files need verify kind of server using. can check server adding a <?php phpinfo(); ?> in php page. ensure mod_rewrite module enabled in apache server. can identified checking phpinfo included page. common methods used url rewriting follows ...
Read more

javascript - jQuery show full size image on click -

pretty self explanatory not workking . i want display full image when user click on image... yes know there tons of plugins but i want keep simple. any idea ? css : .full { display: none; width: 500px; height: 500px; margin-left: 100px; margin-top: -300px; position: fixed; background-color: #f00; z-index: 6; } .thumbnail { width: 50px; height: 50px; } html: <img class="thumbnail" src="http://4.bp.blogspot.com/-uhbdp2esxng/txneptvi92i/aaaaaaaaaky/upfqis7zto0/s1600/rihanna-wallpaper.jpg"> jquery: $(document).ready(function() { $('.thumbnail').on('click', function() { var img = $('<img />',{src:this.src,'class':'full'}); $('.full').html(img).show(); console.log('done!'); }); }); try looking how jquery works. $(document).ready(function() { $('.thumbnail').on('click', function(...
Read more