Classification rates: non‐parametric verses parametric models using binary data
Estimations of the conditional mean and the marginal effects for particular small changes in the covariates have been of interest in financial, economics and even educational sectors. The standard approach has been to specify a parametric model such as probit or logit and then estimating the coefficients by maximum likelihood method. This is only applicable when the distribution form from which the data has been drawn is known. Non parametric methods have been proposed when the functional form assumptions cannot be ascertained. This research sought to establish if non parametric modeling achieves a higher correct classification ratio than a parametric model. The local likelihood technique was used to model fit the data sets. The same sets of data were modeled using parametric logit and the abilities of the two models to correctly predict the binary outcome compared. The results obtained showed that non‐parametric estimation gives a better prediction rate (classification ratio) for a binary data than parametric estimation. This was achieved both empirically and through simulation. For empirical results two different data sets were used. The first set consisted of loan applications of customers and the second set consisted of approved loans. In both data sets the classification ratio for non‐parametric method was found to be 1 while that for parametric was found to be 0.87 (only 87 out of the 100 observations were correctly classified) and 0.83 respectively. Simulation was done based on sample sizes of 25, 50, 75, 100,150,200,250,300 and 500. The simulated results further showed that the accuracy of both models decrease as sample size increases.
Key words: Parametric, non‐parametric, local likelihood, logit, confusion matrix and classification ratio
Open access articles published in the Journal of Agriculture, Science and Technology are under the terms of the Creative Commons Attribution (CC BY) License which permits use, distribution and reproduction in any medium, provided the original work is properly cited. The CC BY license permits commercial and non-commercial re-use of an open-access article, as long as the author is properly attributed.
Copyright on any research article published in the Journal of Agriculture, Science and Technology is retained by the author(s). The authors grant the Journal of Agriculture, Science and Technology with a license to publish the article and identify itself as the original publisher. Authors also grant any third party the right to use the article freely as long as its original authors, citation details and publisher are identified.
Use of the article in whole or in part in any medium requires proper citation as follows:
Title of Article, Names of the Author, Year of Publication, Journal Title, Volume (Issue) and page. Links to the final article on the JSRE website are encouraged.
The Creative Commons Attribution License does not affect any other rights held by authors or third parties in the article, including without limitation the rights of privacy and publicity. Use of the article must not assert or imply, whether implicitly or explicitly, any connection with, endorsement or sponsorship of such use by the author, publisher or any other party associated with the article.
For any reuse or distribution, users must include the copyright notice and make clear to others that the article is made available under a Creative Commons Attribution license, linking to the relevant Creative Commons web page. Users may impose no restrictions on the use of the article other than those imposed by the Creative Commons Attribution license.
To the fullest extent permitted by applicable law, the article is made available as is and without representation or warranties of any kind whether express, implied, statutory or otherwise and including, without limitation, warranties of title, merchantability, fitness for a particular purpose, non-infringement, absence of defects, accuracy, or the presence or absence of errors.