Hasil Pencarian  ::  Simpan CSV :: Kembali

"Interviewer falsifications are relevant problem faced by institutions conducting census and surveys around the world, including BPS-Statistics Indonesia. Falsified data may cause serious impact to generated statistics even though the proportion of falsified data is very small. Usage of Computer Assisted Personal Interviewing (CAPI) in field data collection has proven to improve efficiency and effectiveness. In addition, the use of CAPI is believed to be able to detect data falsification better. This is because CAPI devices can produce a variety of metadata that can not be obtained when using paper questionnaires. This study discusses relevant features to detect interviewer falsification in CAPI-based surveys, validates them, and uses them to identify interviewer falsification automatically using data mining techniques so that human supervisors can take further actions. After analyzing relevant features and conducting experiment, the result showed that unsupervised classification algorithm using simple 2-means clustering could have up to 70,5% accuracy, while supervised classification using logistic regression could have up to 88,5% accuracy."

"Cluster analysis is a mult ivariate analysis technique used to classify objects such that the objects in a cluster are very similar and the objects in different clusters are quite different. This study will discuss the non-hierarchical clustering methods. The methods are C-Means Cluster and Fuzzy C-Means Cluster. These methods are suitable for large data and continuous variables. This study would also present the application of the methods on the case of village grouping according to the underdevelopment status in two regions of level II (Kota Metro and Kabupaten Lampung Timur) in Lampung Province. The unit of observations in this study are 257 villages in Kota Metro (22 villages) and Kabupaten Lampung Timur in Lampung Province obtained from the Village Potential Statistics (Podes - Potensi Desa) 2008.The results show that the optimal cluster in Kota Lampung data is 4, with a minimum value of the Fukuyama-Sugeno validity index is at -45.4649. As for the data of Kabupaten Lampung Timur, theoptimumnumber ofclustersis13,with aminimum value of the Fukuyama-Sugeno validity index is at 196.9629."

"Metode jackknife empirical likelihood adalah suatu metode statistika untuk membentuk interval kepercayaan bagi suatu parameter. Metode jackknife empirical likelihood merupakan pengembangan dari metode empirical likelihood ketika parameternya berbentuk fungsi nonlinier. Metode empirical likelihood sendiri merupakan metode statistika yang digunakan untuk membentuk interval kepercayaan untuk suatu parameter berdasarkan data yang diperoleh dari suatu pengamatan. Pada tugas akhir ini, akan dibahas mengenai pembentukan interval kepercayaan untuk mean absolute deviation dari suatu populasi menggunakan metode jackknife empirical likelihood. Mean absolute deviation itu sendiri merupakan salah satu dari ukuran penyebaran data, yaitu rata-rata harga mutlak dari simpangan data terhadap meannya. Distribusi asimtotik dari fungsi jackknife empirical likelihood ratio adalah suatu distribusi chi-kuadrat dengan derajat bebas satu. Fungsi jackknife empirical likelihood ratio ini akan digunakan untuk membentuk interval kepercayaan untuk mean absolute deviation.

---

Jackknife empirical likelihood method is a statistical method to construct the confidence interval for a parameter. Jackknife empirical likelihood method is modification of empirical likelihood method when the parameter is nonlinear function. Empirical likelihood method itself is one of the statistical method used to construct the confidence interval for a parameter based on the data obtained from an experiment. In this paper, we will discuss the construction of the confidence interval for the mean absolute deviation of a population using jackknife empirical likelihood method. Mean absolute deviation itself is one of the measures of dispersion of data, which is the average of the absolute deviations of the data set from its mean. The asymptotic distribution of jackknife empirical likelihood ratio function is a chi square distribution with one degree of freedom. Jackknife empirical likelihood ratio function will be used to construct confidence interval for the mean absolute deviation."