CD Skripsi

Perbandingan Metode Imputasi Untuk Mengatasi Data Hilang Pada Dataset Faktor-Faktor Yang Mempengaruhi Perubahan Iklim

---

ABSTRACT
Missing data contained in a dataset can affect the results of the analysis. This study uses a dataset of factors that affect world climate change from 1990 - 2020 which has missing data on all variables. This study aims to determine the best imputation method by comparing five imputation methods namely Mean Imputation, Median Imputation, linear interpolation, KNN Imputation, and Multiple Imputation by Chained Equation (MICE). The results obtained from the imputed data result that MICE is the best method for dealing with missing data in the dataset of factors that can affect world climate change by having the smallest RMSE value. RMSE value for mean imputation is 695 ×10−5, median imputation is 7707 ×10−5, linear interpolation is 702 ×10−5, KNN Imputation is 736 ×10−5, and a MICE of 129 ×10−5.
Keywords: Missing data, imputation, MICE.

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

1903114040

Penerbit

Pekanbaru : Universitas Riau – FMIPA – STATISTIKA., 2023

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

1903114040

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

STATISTIKA

Info Detail Spesifik

-

Pernyataan Tanggungjawab

TIAR

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar