Browsing by Author "Mbaeyi, G. C."

Now showing 1 - 3 of 3
  • Item
    On discrimination procedure with mixtures of continuous and categorical variables
    (Taylor and Francis, 2016) Oyeyemi, G. M.; Mbaeyi, G. C.; Salau, I. S.; Muse, B. O.
    A discrimination procedure, based on the location model is described and suggested for use in situation where the discriminating variables are mixtures of continuous and binary variables. Some procedures that have been previously employed, in a similar situation, like Fisher’s linear discriminant function and the logistic regression were compared with this method using error rate (ER). Optimal ERs for these procedures are reported using real and simulated data for the case of varying sample size and number of continuous and binary variables and were used as a measure for assessing the performance of the various procedures. The suggested procedure performed considerably better in the cases considered and never did produce a result that is poor when compared with other procedures. Hence, the suggested procedure might be considered for such situations.
  • Item
    ON ESTIMATION OF COVARIANCE MATRIX WITH MIXTURES OF CONTINUOUS AND CATEGORICAL VARIABLES
    (Faculty of Physical Sciences, Federal University of Ndufu-Alike-Ikwo, Nigeria., 2017) Oyeyemi, G. M.; Mbaeyi, G. C.
    A method known as the Location Model for discriminant analysis when discriminating variables are mixtures of continuous and categorical variables, which, unlike the conventional Linear Discriminant procedure does not assign arbitrary scores to each state of the categorical variable was studied. An alternative to estimating the covariance matrix for evaluating the discriminant function was suggested since the Location Model still makes such distortion of treating categorical variable as if they are continuous when estimating the covariance matrix. We compare the performance of the two procedures using the accuracy rate produced by each method under various conditions. Our suggested method performed better than the location model over all cases considered.
  • Item
    ON THE ESTIMATION OF EMPTY CELL PROBABILITIES IN A CONTINGENCY TABLE
    (Anale Seria Informatica, 2018) Oyeyemi, G. M.; Mbaeyi, G. C.
    In this paper, an Independent Binary Model (IBM) is proposed. It is aimed at estimating cell probabilities in an r x c contingency table when some of the cells have zero count. Existing methods in this situation are either subjective or based on arbitrary decision of the researcher. The IBM is applied to sets of simulated data for various combinations of categorical variables. It is pointed out that the IBM could be an alternative for such situations especially when the result is needed for further analysis.