cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota bogor,
Jawa barat
INDONESIA
FORUM STATISTIKA DAN KOMPUTASI
Published by Institut Pertanian Bogor
ISSN : 08538115     EISSN : -     DOI : -
Core Subject : Education,
Mathematics
Forum Statistika dan Komputasi (ISSN:0853-8115) was published scientific papers in the area of statistical science and the applications. It is issued twice in a year. The papers should be research papers with, but not limited to, following topics: experimental design and analysis, survey methods and analysis, operation research, data mining, statistical modeling, computational statistics, time series and econometrics, and statistics education.
Arjuna Subject : -
Articles 5 Documents
 1 
Search results for , issue "Vol. 16 No. 1 (2011)" : 5 Documents clear
JARINGAN SYARAF TIRUAN DAN ALGORITMA GENETIKA DALAM PEMODELAN KALIBRASI (STUDI KASUS : TANAMAN OBAT TEMULAWAK) Bartho Sihombing; . Erfiani; Utami Dyah Syafitri
FORUM STATISTIKA DAN KOMPUTASI Vol. 16 No. 1 (2011)
Publisher : FORUM STATISTIKA DAN KOMPUTASI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (325.262 KB)

Abstract

The problems in prediction of calibration model are multicolinearity and the number of variables is larger than the number of observations. Principal Component Analysis-Artificial Neural Network-Genetic Algorithm (PCA-ANN-GA) models were applied for the relationship between sample of concentration which is limited and transmittance data which is in large dimensions. A large number of variables were compressed into principal components (PC’s). From these PC’s, the ANN was employed for prediction of concentration. The principal components computed by PCA were applied as inputs to a backpropagation neural network with one hidden layer. The models was evaluated using GA for the best network structure on hidden layer. Root Mean Square Error (RMSE) for 80% training set and 20% testing set are 0.0314 and 0.5225, respectively. Distribution of data according to the percentage of training data and testing data were also very influential to obtain the best network structure with the smallest RMSE achievement. The best model for these methods is two layers Neural Network with eight neuron in the hidden layer.
PERFORMANCE COMPARISON BETWEEN KIMURA 2-PARAMETERS AND JUKES-CANTOR MODEL IN CONSTRUCTING PHYLOGENETIC TREE OF NEIGHBOUR JOINING Hendra Prasetya; Asep Saefuddin; Muladno .
FORUM STATISTIKA DAN KOMPUTASI Vol. 16 No. 1 (2011)
Publisher : FORUM STATISTIKA DAN KOMPUTASI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (307.91 KB)

Abstract

Bioinformatics as a recent improvement of knowledge has made an interest for scientist to collect and analyze data to provide the best estimate of the true phylogeny. The objective of this research is to construct and compare the phylogenetic tree of Neighbour Joining (NJ) based on different models (Kimura 2-Parameters and Jukes-Cantor) and to find out which model is more reliable on constructing NJ's tree. In order to build the tree, reliable set of data is conducted from D-loop mtDNA sequences that is available in Gen Bank. The nucleotide sequences come from Bison bison (American bison), Bos taurus (European cow such as Shorthorn), Bos indicus (zebu breeds), Bos grunniens mutus (one of subspecies of cow), and Capra hircus (species of goat). The reliability of each models was measured using the Felsentein's bootstrap method. The whole bootstrap process for each models was repeated 1.000, 5.000, and 10.000 times to detect its reliability. The performance was measured on the basis of the consistency of the topology relationship, the stability of nodes, the consistency of bootstrap confidence level (PB), standard error of distance, change of PB from (1.000-5.000) to (5.000-1.000), computational time, and  BIC score. NJ's phylogenetic tree with kimura 2-parameters and jukes cantor model have a good node stability and is also generally successful in representing topological relationships between taxa. The increasing of bootstrap replication number in common will increase the consistency of bootstrap confidence value ( . It means both models have a good reliability. But, when the number of sequences is large and the extent of sequence divergence is low, it is generally difficult to construct the tree by any models. In conclusion, Kimura 2-Parameters has a better performance than Jukes-Cantor.   Key words: phylogenetic tree, Neighbour Joining, Kimura 2-Parameters, Jukes-Cantor
PREFERENSI MAHASISWA IPB TERHADAP MATA KULIAH METODE STATISTIKA MENGGUNAKAN ANALISIS KONJOIN Eka Dewi Pertiwi; Utami Dyah Syafitri; Yenni Angraini
FORUM STATISTIKA DAN KOMPUTASI Vol. 16 No. 1 (2011)
Publisher : FORUM STATISTIKA DAN KOMPUTASI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (374.201 KB)

Abstract

Statistical method is one of the interdepth courses in Bogor Agricultural University (BAU) therefore, it is necessary to conduct an  evaluation in order to know the student's preference towards Statistics Methods course. Conjoint analysis is an analysis that can be used to determine the preference of students on teaching methods of Statistical Methods course. The combination of teaching methods are made using fractional factorial in which the level of  factor determined  was based on preliminary survey. Sampling techniques that  has been used was multistage sampling of students who had took the Statistical Methods course in 2009/2010. Based on conjoint analysis, the module, the number of students, and the time period of lectures are the top three  choices. The students tend to prefer materials that are appropriate with their major, modules that are well structured, a communicative lecturer, students as a teacher in review session, the number of student which is less than 50 students per class, and the time period of lecture is between 7-12 am.   Keywords :  statistical methods, preferences, conjoint analysis.
PENGARUH PEMILIHAN ARAH ACUAN 00 DAN ARAH ROTASI PADA ANALISIS KORELASI DAN REGRESI LINIER-SIRKULAR (STUDI KASUS: PETA KAWASAN RAWAN BENCANA LETUSAN GUNUNG Abdul Aziz Nurussadad; I Made Sumertajaya; Ahmad Ansori Mattjik
FORUM STATISTIKA DAN KOMPUTASI Vol. 16 No. 1 (2011)
Publisher : FORUM STATISTIKA DAN KOMPUTASI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (560.395 KB)

Abstract

The measurement results doesn't only consist of data with linear attributes, but also data with circular attributes. The circular data has a uniqueness that is not owned by the linear data, circular data is independent of the choice of 0o reference and rotation direction. The uniqueness of circular data analysis is tested in linear circular correlation and linear circular regression. The results of correlation analysis proved that the selection of the reference direction 0o can be done subjectively because the linear circular correlation results show the same value 0.899 for all possible selection of 0o reference and rotation direction. For linear circular regression, the model constructed has a same coefficient of determination that is 0.808 and the same b0, which is 5.231 for all possible selection of 0o reference and rotation direction. Similarly, statistics from the error of linear circular regression analysis have the same value, minimum = -2.693, quartile 1 = -0.835, median = -0.171, quartile 3 = 0.548, maximum = 8.421. Alleged circular linear regression parameters, namely b1 and b2, forming a cycle that each has in common b1 = -1.226 E-07-2.728 cos (α) - 2.655 sin (α) and b2 = 3.061 E-07-2.655 cos (α ) + 2.728 sin (α) where α is the position of the 0o reference direction in degrees on each model.   Keywords :  Directional Statistics, Circular Statistics, Linear-Circular Regression, Linear Circular Correlation
PENERAPAN METODE RANDOM FOREST DALAM DRIVER ANALYSIS Nariswari Karina Dewi; Utami Dyah Syafitri; Soni Yadi Mulyadi
FORUM STATISTIKA DAN KOMPUTASI Vol. 16 No. 1 (2011)
Publisher : FORUM STATISTIKA DAN KOMPUTASI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (348.56 KB)

Abstract

Driver analysis is one approach to know which  the greatest expalanatory variables influence the response variable. This analysis is well known in marketing research. In this area, explanatatory variables (X) and response variable (Y) ussually are measured by ordinal data and the relationship between those variables is non linier. One of the approach to build model on that situation is random forest. Two important things in random forest are size of random forest and sample size of X. In this research, we worked with  simulation to know the size of random forest which give higher accuration and more stabil. The simulation showed that the best condition achieved when the size of random forest is 500 and the sample size of X is 4.      Key words : driver analysis, random forest, variable importance.

Page 1 of 1 | Total Record : 5

 1 

Filter by Year

2011 2011


Reset
Filter By Issues
All Issue Vol. 20 No. 2 (2015) Vol. 18 No. 1 (2013) Vol. 17 No. 2 (2012) Vol. 17 No. 1 (2012) Vol. 16 No. 2 (2011) Vol. 16 No. 1 (2011) Vol. 15 No. 2 (2010) Vol. 15 No. 1 (2010) Vol. 14 No. 2 (2009) Vol. 14 No. 1 (2009) Vol. 13 No. 1 (2008) Vol. 12 No. 2 (2007) Vol. 12 No. 1 (2007) Vol. 11 No. 2 (2006) Vol. 11 No. 1 (2006) Vol. 10 No. 2 (2005) Vol. 10 No. 1 (2005) Vol. 9 No. 2 (2004) Vol. 8 No. 2 (2003) Vol. 8 No. 1 (2003) Vol. 7 No. 2 (2002) Vol. 6 No. 2 (2001) Vol. 6 No. 1 (2001) More Issue