?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Using+penalized+likelihood+to+select+parameters+in+a+random+coefficients+multinomial+logit+model&rft.creator=Horowitz%2C+JL&rft.creator=Nesheim%2C+L&rft.description=The+multinomial+logit+model+with+random+coefficients+is+widely+used+in+applied+research.+This+paper+is%0D%0Aconcerned+with+estimating+a+random+coefficients+logit+model+in+which+the+distribution+of+each+coefficient%0D%0Ais+characterized+by+finitely+many+parameters.+Some+of+these+parameters+may+be+zero.+The+paper+gives%0D%0Aconditions+under+which+with+probability+approaching+1+as+the+sample+size+approaches+infinity%2C+penalized%0D%0Amaximum+likelihood+(PML)+estimation+with+the+adaptive+LASSO+(AL)+penalty+function+distinguishes%0D%0Acorrectly+between+zero+and+non-zero+parameters+in+a+random+coefficients+logit+model.+If+one+or+more%0D%0Aparameters+are+zero%2C+then+PML+with+the+AL+penalty+function+often+reduces+the+asymptotic+mean-square%0D%0Aestimation+error+of+any+continuously+differentiable+function+of+the+model%E2%80%99s+parameters%2C+such+as+a+market%0D%0Ashare+or+an+elasticity.+The+paper+describes+a+method+for+computing+the+PML+estimates+of+a+random%0D%0Acoefficients+logit+model.+It+also+presents+the+results+of+Monte+Carlo+experiments+that+illustrate+the%0D%0Anumerical+performance+of+the+PML+estimates.+Finally%2C+it+presents+the+results+of+PML+estimation+of+a%0D%0Arandom+coefficients+logit+model+of+choice+among+brands+of+butter+and+margarine+in+the+British+groceries%0D%0Amarket.&rft.subject=random+coefficients%2C+logit%2C+penalized+likelihood%2C+LASSO&rft.publisher=Centre+for+microdata+methods+and+practice+(cemmap)&rft.date=2019-09&rft.type=Working+%2F+discussion+paper&rft.language=eng&rft.source=++++(cemmap+Working+Paper++CWP50%2F19).+Centre+for+microdata+methods+and+practice+(cemmap)%3A+London%2C+UK.+(2019)+++++&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10060499%2F&rft.rights=open