A warming planet and persistent increases in temperature and humidity experienced by humans call for an urgent focus on which indicators of excess heat are the most informative. Several heat indicators have been developed to assess past heat conditions and inform future actions. We compare and contrast the relative merits of two indicators, namely, the heat index and the excess heat factor in urban contexts. Both the indicators have been used by official agencies in high income countries, such as the United States of America and Australia, and are also receiving increasing attention in India. The analysis presents a new approach towards assessing the usefulness of a heat indicator, wherein the indicator acquires value when placed in specific stress contexts. A two-step approach is adopted. First, an analytical framework of the urban heat-health issue is developed, based on the interdisciplinary expertise of the authors, and the framework is used to assess the two indicators. Second, data from two Indian cities located in different climatic zones, one experiencing very dry heat and the other very humid heat conditions is used to compute, compare and contrast the findings from the two heat indicators. The computation uses R software with data from the Ogimet repository and the Indian Meteorological Department. Findings reveal that the indicators are distinct but complementary and if used together can lead to a more effective strategy for reducing heat-health risks for Indian cities. An interactive graphical tool is provided to help the interested reader explore the indicators.

A presentation about measures of central tendency that gives a general descriptive overview, real world examples, as well as explanations on when it is more appropriate to use each measure of mean, median, or mode.

An analysis of 3 stocks over the course of a year.

Data-Driven Insights for Wyoming Community Colleges. Presented at the Wyoming Mathematics Articulation Conference 2026 at Eastern Wyoming College in Torrington, WY, on April 18th, 2026.

Tugas anmul modul 2

Analisis ini bertujuan untuk mengelompokkan data preferensi wisata pengguna berdasarkan dataset Travel Reviews menggunakan beberapa metode clustering, yaitu K-Means, K-Medians, DBSCAN, Mean Shift, dan Fuzzy C-Means. Dataset yang digunakan merupakan data mentah yang diperoleh dari UCI Machine Learning Repository, yang berisi penilaian pengguna terhadap berbagai kategori tempat wisata. Sebelum dilakukan proses clustering, data terlebih dilakukan preprocessing berupa penghapusan fitu yang tidak relevan serta normalisasi menggunakan metode standardisasi untuk memastikan keseragaman skala antar fitur. Penentuan jumlah cluster optimal dilakukan menggunakan metode Elbow dan Silhouette, yang menunjukkan bahwa jumlah cluster terbaik adalah dua. Setiap metode clustering diimplementasikan dan dievaluasi menggunakan Silhouette Coefficient untuk mengukur kualitas pemisahan cluster. Hasil evaluasi menunjukkan adanya perbedaan performa antar metode, di mana metode dengan nilai silhouette tertinggi dipilih sebagai metode terbaik (K-Means). Selain itu, dilakukan Analysis Data Eksploratiion (EDA) pada hasil clustering terbaik untuk mengidentifikasi karakteristik setiap cluster berdasarkan nilai rata-rata fitur. Hasil analisis menunjukkan bahwa terdapat pola pengelompokan pengguna berdasarkan preferensi terhadap kategori wisata tertentu. Analisis ini menegaskan bahwa pemilihan metode clustering yang tepat sangat berpengaruh terhadap kualitas hasil pengelompokan, serta pentingnya evaluasi kuantitatif dalam menentukan metode terbaik.

Analisis Clustering Dataset WineQT