Claim Missing Document
Check
Articles

METODE FUZZY TOPSIS MADM SEBAGAI ALTERNATIF PENGAMBILAN KEPUTUSAN MENENTUKAN PENERIMA BEASISWA PPA BERBASIS WEB Halim, Bravura Candra; Alamsyah, Alamsyah; Sugiman, Sugiman
Unnes Journal of Mathematics Vol 5 No 1 (2016)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v5i1.13107

Abstract

This study examines the decision making to determine the scholarship recipients Improving Academic Achievement (PPA) at the State University of Semarang (UNNES) with details of criteria that include student GPA, number of credits taken, the value of student affairs, and the income of parents. The decision making process admission PPA UNNES scholarship implemented with the programming language of PHP with MySQL database and calculations using the method of Fuzzy TOPSIS Multiple-Attribute Decision Making (MADM). The results of reception system PPA UNNES scholarship in this study is a ranking by 50 students of the value of the preferences of the applicants and then taken by students who ranked top 10 of the results of ranking of preferences for recommended escapes in scholarship acceptance PPA UNNES. Based on these results it can be concluded that a web-based decision support systems can be built using TOPSIS Fuzzy MADM with the structure of the programming language PHP and MySQL as a Database Management System (DBMS). In the development of future systems, can be done by adding other data supporting the selection of scholarship PPA
PERBANDINGAN AKURASI MODEL ARCH DAN GARCH PADA PERAMALAN HARGA SAHAM BERBANTUAN MATLAB Sunarti, Sunarti; Mariani, Scolastika; Sugiman, Sugiman
Unnes Journal of Mathematics Vol 5 No 1 (2016)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v5i1.13108

Abstract

This article aims to get model data stock Unilever Indonesia Tbk. use the model ARCH and GARCH as well as comparing forecasting accuracy of the result of the next five days ahead model ARCH and GARCH on the stock Unilever Indonesia Tbk. use MATLAB. The methods used are design application forecasting uses GUI MATLAB, next model ARIMA Box-Jenkins, identification ARCH effect, forecasting use the model ARCH and GARCH, and compares the results second forecasting model that is based on the value of RMSE. On residual ARIMA best namely ARIMA(1,1,1) detected the effects ARCH so that data can modeled ARCH and GARCH. Model ARCH and GARCH best respectively namely ARCH(3) and GARCH(1,1). Based on value RMSE be seen that model best for forecasting the next five days ahead of data Unilever Indonesia Tbk. produced bymodels GARCH(1,1) because it has value RMSE smallest with equation conditional mean and conditional variance
ESTIMASI MULTIVARIATE ADAPTIVE REGRESSION SPLINES (MARS) PADA INDEKS HARGA SAHAM GABUNGAN (IHSG) Asriani, Elisa Desi; Sugiman, Sugiman; Hendikawati, Putriaji
Unnes Journal of Mathematics Vol 5 No 2 (2016)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v5i2.13130

Abstract

The purpose of this study is to know: (1) a estimation best MARS on CSPI with criteria GCV; (2) importance predictors variables against the model best obtained. Variabels affecting Composite Stock Price Index (CSPI) are inflation, interest rate, exchange rate the Rupiah againts the u.s.dollar, Dow Jones index, Nikkei 225 index, and Hang Seng index. MARS model is derived by combination of BF, MI, and MO through trial and error. MARS method on CSPI because nonparametric and high dimention is data has variabels predictors from 3 to 20 and data sampel from 50 to 1000. The analysis MARS method on CSPI with do testing parameters of regression nonparametric model, standaritation, and The results estimation MARS best on CSPI is BF=18, MI=1, and MO=1, GCV minimum is 0,05640. Predictors variables that were significans are inflation; exchange rate the rupiah againts the US$; Dow Jones index; interest rate; and Nikkei 225 index with contributions of importance are 100%; 86,54114%; 84,31259%; 38,18755%; and 32,75410%.
KETEPATAN KLASIFIKASI DENGAN MENGGUNAKAN METODE MULTIVARIATE ADAPTIVE REGRESSION SPLINE (MARS) PADA DATA KELOMPOK RUMAH TANGGA KABUPATEN CILACAP Anam, Saroful; Sugiman, Sugiman; Sunarmi, Sunarmi
Unnes Journal of Mathematics Vol 6 No 1 (2017)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v6i1.13638

Abstract

Groups of households based on per capita expenditure is composed of two groups of poor households and non-poor households, to separate individuals or objects into a group so it can be located ata particular group can use the method of classification. The purpose of this study was to determine the classification results and errors in the results classification of households in Cilacap district based on the factors affecting the level of poverty in Cilacap with methods Multivariate Adaptive Regression Spline (MARS). MARS is a nonparametric regression method that can be used for high-dimensional data is. To get the best MARS models, do a combination of value Basis Function (BF), Maximum Interaction (MI), and the Minimum Observation (MO) by trial and error. The best model is the model that is used in combination with BF = 45, MI = 3, MO = 1 because it has the smallest value that is equal to 0,030 GCV. Based on the variables that affect groups of households in Cilacap, the result of classification of 37 households with poor category, 34 households appropriately classified as poor, while one 3 households are classified as poor. Likewise, of the 113 households with non-poor category, 113 households appropriately classified into the category of not poor, and no household misclassified into the household with non-poor category. Retrieved classification accuracy of 98.00% of the value of Apparent Error Rate (APER) at 2.00% and the Press's Q test showed that statistically MARS method has been consistent in classifying the data. So as to further research on the classification suggested using the method MARS, by looking at the value of the smallest GCV and GCV value if they have the same smallest it can be seen with the smallest MSE value judgment.
PERBANDINGAN UJI HASIL SIMULASI MONTE CARLO DAN SIMULASI BOOTSTRAP DALAM ANALISIS SAHAM UNTUK MENGHITUNG NILAI VaR DATA Mawarti, lida; Sugiman, Sugiman; Kharis, Muhammad
Unnes Journal of Mathematics Vol 7 No 2 (2018)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v7i2.14109

Abstract

Harapan investor terhadap investasinya adalah mendapatkan pengembalian optimal dengan tingkat risiko tertentu. Perlu adanya perhitungan risiko agar tetap berada dalam tingkatan terkendali. Salah satu metode statistika untuk mengukur besar risiko yang ditimbulkan yaitu Value at Risk (VaR). Metode untuk mengestimasi Value at Risk menggunakan Simulasi Monte Carlo dan Simulasi Bootstrap. Pada penelitian ini menggunakan software Microsoft Excel dan SPSS. Data yang digunakan adalah data penutupan saham PT Indosat Tbk dari 1 Januari 2015 sampai dengan Desember 2015. Tujuan penelitian adalah membandingkan nilai taksiran VaR menggunakan program Simulasi Monte Carlo dan Simulasi Bootstrap. Langkah yang digunakan untuk menganalisis adalah menginput data, mengidentifikasi karakteristik data,menghitung nilai return, menghitung parameter mean dan standar deviasi, menghitung nilai acak dari return, menghitung nilai acak dengan parameter, menghitung nilai risiko tertinggi, menghitung VaR, melakukan simulasi sebanyak n kali, menghitung MSE. Hasil estimasi VaR tingkat kepercayaan 95% per 1 rupiah selama 1 hari menggunakan Simulasi Monte Carlo yaitu -12615.77. Sedangkan estimasi menggunakan Simulasi Bootstrap adalah -1330.62 dengan n=113 dan B*=1000. Nilai MSE dari Simulasi Monte Carlo sebesar 0,0514925 sedangkan dari Simulasi Bootstrap adalah 0.00059420. Nilai MSE Simulasi Bootstrap lebih kecil bila dibandingkan nilai MSE Simulasi Monte Carlo.
Pemodelan Geographically Weighted Regression (GWR) dengan Fungsi Pembobot Kernel Gaussian dan Bi-Square Lutfiani, Nurul; Sugiman, Sugiman; Mariani, Scolastika
Unnes Journal of Mathematics Vol 8 No 1 (2019)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v8i1.17103

Abstract

Model spasial Geographically Weighted Regression (GWR) adalah salah satu metode statistika yang dapat digunakan untuk menganalisis faktor risiko secara spasial dengan pendekatan titik. Fungsi pembobot yang digunakan untuk model GWR adalah fungsi kernel gaussian dan bi-square. Langkah analisis yang dilakukan yaitu melakukan pengujian dengan metode OLS. Dalam pengujian diperoleh 2 variabel yang signifikan, selanjutnya melakukan pengujian menggunakan metode GWR. Membandingkan nilai R2 dan AIC antara model GWR dengan fungsi pembobot kernel gaussian dan bi-square menggunakan Program R. Berdasarkan hasil penelitian yang diperoleh Tabel ANOVA untuk menguji kebaikan GWR secara global, model GWR lebih efektif daripada OLS. Diperoleh model GWR dengan fungsi pembobot gaussian di Kabupaten Cilacap yi = 0,017574 – 0,714742X1 + 0,812049X3 , nilai R2 sebesar 77,47% , nilai AIC sebesar 53,44198 dan model GWR dengan fungsi pembobot bi-square di Kabupaten Cilacap yi = -0,024805 -0,716867X1 +0,832846X3, nilai R2 sebesar 76,19%, nilai AIC sebesar 54,64947. Nilai R2 terbesar dan nilai AIC terkecil dimiliki oleh model GWR dengan kernel gaussian.
PERBANDINGAN HASIL OPTIMASI PADA METODE BROWN’S ONE-PARAMETER DOUBLE EXPONENTIAL SMOOTHING MENGGUNAKAN ALGORITMA NON-LINEAR PROGRAMMING BERBANTUAN MATLAB Novalia, Dyah; Sugiman, Sugiman; Sunarmi, Sunarmi
Unnes Journal of Mathematics Vol 7 No 1 (2018)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v7i1.20381

Abstract

Pemulusan eksponensial ganda satu parameter dari Brown merupakan salah satu pemulusan eksponensial dengan satu parameter, yaitu parameter . Beberapa algoritma nonlinear programming dapat digunakan untuk menyelesaikan masalah optimasi. Tujuan dari penulisan skripsi ini adalah mendapatkan nilai parameter optimal pada pemulusan eksponensial ganda satu parameter dari Brown menggunakan algoritma golden section, algoritma pencarian dikotomis dan algoritma kuadratis dengan bantuan software Matlab R2009a. Hasil perhitungan dari ketiga algoritma tersebut dibandingkan, lalu dilakukan peramalan menggunakan pemulusan eksponensial ganda satu parameter dari Brown. Pada penelitian ini, proses untuk mendapatkan parameter optimal dengan menggunakan algoritma golden section membutuhkan 16 iterasi hingga didapatkan nilai optimal sebesar dan MAPE sebesar 0,10719%. Algoritma pencarian dikotomis membutuhkan 13 iterasi hingga didapatkan nilai optimal sebesar dan MAPE sebesar 0,10720%. Sedangkan algoritma kuadratis membutuhkan 3 iterasi hingga didapatkan nilai optimal sebesar 0,206883 dan MAPE sebesar 0,10720%. Berdasarkan hasil perhitungan tersebut maka algoritma kuadratis lebih efektif karena jumlah iterasi yang dibutuhkan lebih sedikit sehingga waktu yang dibutuhkan juga lebih efisien
The growth of mathematical imagination of students of a deaf school when learning using Problem-Based Learning assisted by manipulative teaching aids Ni'mah, Lailatun; Sugiman, Sugiman
Unnes Journal of Mathematics Education Vol 9 No 2 (2020): Unnes Journal of Mathematics Education
Publisher : Department of Mathematics, Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujme.v9i2.40540

Abstract

The ability of mathematical imagination is important in daily life for children with deaf disabilities. One effort to foster mathematical imagination is through a problem-based learning model assisted by manipulative props. This study aimed to: (1) find out whether the results of the mathematical imagination final test of deaf students with the application of the Problem-Based Learning assisted by manipulative props are better that the results of the initial test; (2) describe the mathematical imagination of the deaf students; (3) find out the growth of mathematical imagination of the deaf students. This research was mixed-method research that used a sequential exploratory design with a one-group pretest-posttest design. The population of this research was the students of a special school for disabilities (SMALBN) in Salatiga, Indonesia, while the sample was a random class from the 11th classes. The method used in this research were observation, documentation, tests, and interviews. Quantitative analysis showed that the final test of mathematical imagination result was better than the results of the initial test. Qualitative analysis yield a description of mathematical imagination that included aspects such as scientific sensitivity, scientific creativity, and good scientific productivity. The scientific sensitivity aspect of the imagination growth before learning was good, and the scientific creativity aspect was quite good. After learning, it was obtained that scientific sensitivity, scientific creativity, scientific productivity were good. The study concluded that problem-based learning assisted by manipulative props could foster the ability of mathematical imagination of deaf students in 11th grade.
ESTIMASI PARAMETER REGRESI ROBUST MODEL SEEMINGLY UNRELATED REGRSSION (SUR) DENGAN METODE GENERALIZED LEAST SQUARE (GLS) Yulianto, Dimas Arif; Sugiman, Sugiman; Agoestanto, Arief
Unnes Journal of Mathematics Vol 7 No 2 (2018)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v7i2.21463

Abstract

Penelitian ini bertujuan untuk: (1) memperoleh hasil estimasi parameter pada data yang mengandung pencilan dengan menggunakan estimasi parameter regresi robust metode Least Trimmed Square (LTS); (2) memperoleh sistem persamaan regresi robust pada model Seemingly Unrelated Regression (SUR) dengan metode Generalized Least Square (GLS). Pada penelitian ini menggunakan data nilai inflasi umum di Kota Salatiga, Kota Pekalongan, Kabupaten Rembang, dan Kabupaten Demak. Estimasi parameter regresi pada data yang menggandung pencilan lebih baik menggunakan metode regresi robust daripada menggunakan metode OLS karena menghasilkan nilai R-Square yang lebih besar. Estimasi regresi robust padamodel Seemingly Unrelated Regression (SUR) metode Generlaized Least Square (GLS) lebih baik digunakan untuk mengestimasi pada data panel yang semua datanya mengandung pencilan karena menghasilkan nilai residual yang kecil.
PARAMETER ESTIMATION OF SPATIAL REGRESSION MODEL WITH GEOGRAPHICALLY WEIGHTED POISSON REGRESSION METHOD Fadlilah, Itsnaini Munjiyatul; Sugiman, Sugiman; Sunarmi, Sunarmi
Unnes Journal of Mathematics Vol 8 No 2 (2019)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/ujm.v8i2.23796

Abstract

Poisson Regression is one of the non-linear regression analysis whose Poisson distributed response variable.Geographically Weighted Poisson Regression (GWPR) is one of the statistical methods to analyze spatial data with point approach. The purpose of this research is to form GWPR model with fixed bisquare and adaptive bisquare kernel function, and compare best model of GWPR with kernel fixed bisquare and adaptive bisquare function. The data of this research is the percentage of poor people in Central Java Province. In this study there are seven (7) variables related to the percentage factor of the poverty population. The test obtained 2 significant variables are population life expectancy and income per-capita population has been adjusted .Based on the result of research, it is found that GWPR model is more suitable than Poisson regression. Provided Geographically Weighted Poisson Regression model with fixed bisquare fixed function and adaptive bisquare globally in Province of Central Java . The advantage of the model can be seen from the value of AIC. The AIC value obtained in the fixed bisquare kernel is 178,7446. Whereas, The AIC value obtained in adaptive kernel bisquare is 183.2349. The GWPR model with the fixed Bisquare kernel is better than GWPR adaptive bisquare.
Co-Authors Abdul Wakhid Achmalia, Aisyah Fany Adi Nur Cahyono Adli, Abiyyi Muhammad Alamsyah - Alfian Nur Aziz, Alfian Nur Alif Fauziah Sari, Alif Fauziah Amin Suyitno Anam, Saroful Aoyama, Kazuhiro Ardhi Prabowo Arief Agoestanto Arifah, Yekti Nur Arina Ulil Faroh Ariyadi Wijaya Asriani, Elisa Desi Atika Nur Sabrina Ayu Andira Bambang Eko Susilo Budi Waluya Budi Waluya Cynthia, Ari Danuri Danuri Dedeh Kurniasih Dwi Setyawan Dwi Sulistyaningsih Dwijanto Dwijanto, Dwijanto Eko Supriyadi Emi Pujiastuti Endang Sugiharti, Endang Eva Agustiana Rahayu Fadlilah, Itsnaini Munjiyatul Hajarul Masi Hanifatur Rohman Halim, Bravura Candra Hendri Handoko hengky tri ikhsanto, hengky tri ikhsanto Heri Retnawati Hidayah, Dina Yulia Hidayati, Intan Indah Urwatin Wusqo Ismail, Abid Khoirul Isnarto Isnarto Isnarto Isnarto Isti Hidayah Iwan Junaedi Iwan Junaedi Juwita, Puspa Khathibul Umam Zaid Nugroho Kinasih, Sekar Lutfiani, Nurul M. Asikin M.Pd S.T. S.Pd. I Gde Wawan Sudatha . Ma'unah, Siti Mawarti, lida Mohammad Asikin Much Aziz Muslim Muhammad Kharis Mulyono Mulyono Muslih Hasan Pambudi Ni'mah, Lailatun Nila Ubaidah Nila Ubaidah Novalia, Dyah Nuke Apriyanti Nur Fathaillah Pajrin Nurkaromah Dwidayati, Nurkaromah Paryanto Dwi Setyawan Pawestri Dian Purnamasari Pindo Apip Permana, Pindo Apip Pradewita, Wella Cintya Pradina, Putri Dwi Pujilestari, Sri Putri, Elanda Laksinta Putriaji Hendikawati Rianisa Scientisa A Riswanti Rini Rochmad - Safitri, Tias Saiful Arifin Scolastika Mariani Setiyani Sofyan Adian Mukti St. Budi Waluya Stevanus Budi Waluja Sukestiyarno Sukestiyarno Sulardjaka Sulardjaka Sunarmi Sunarmi Sunarti Supriyanti Supriyanti Suryani, Andika Resti Triwibowo, Zanuar Try Suprayo Tyas, Marita Ayuning Ulfiati, Leili Vika Oktoviani Wahyu Setyaningrum Walid Walid, Walid Wardono Wardono Wulandari, Arum Nur Y.L. Sukestiyarno Yaya S. Kusumah YL Sukestiyarno Yulianto, Dimas Arif Zaenuri Mastur Zaenuri Zaenuri Zaenuri Zaenuri Ziyana Endah Khairun Nisa'