Explore chapters and articles related to this topic
How Data Science Happens
Published in Natalie M. Scala, James P. Howard, Handbook of Military and Defense Operations Research, 2020
“Microdata” are data that represent a single observation of something (Samarati, 2001). The speed of a vehicle at one point in time as it goes down the highway is microdata. And so is the age of the driver. This is different from the way you are used to seeing the data. News reports, briefings, and other presentations tend to focus on summary statistics, rather than the individual data elements. Summary statistics include percentages, means, and standard deviations. Microdata are the individual observations that compose those summary statistics and are a greater focus of data science than means and percentages.
Generating synthetic occupants for use in building performance simulation
Published in Journal of Building Performance Simulation, 2021
Handi Chandra Putra, Clinton Andrews, Tianzhen Hong
We consider two categories of data sets to inform the generation of our synthetic occupant population. The socio-demographic data is cross-sectional and attributed to the individual and group populations at a particular geographical location. The data set draws from two sources, including the National Household Travel Survey (NHTS) (Administration 2017) and Public Use Microdata Survey (PUMS) (U.S. Census 2015). The occupant behaviour data set draws on a dataset on occupant behaviour that was part of the deliverables of an international project, Annex 66. Annex 66 was established under the International Energy Agency’s Energy in Buildings and Communities Program (short name: IEA Annex 66) with aims to provide resources for occupant behaviour research (International Energy Agency 2017). The dataset includes 4,324 observations. The larger and more recent ASHRAE Global Thermal Comfort Database II data set has been introduced in (Licina et al. 2018) and it includes approximately 81,846 occupant-specific data points spread across 160 buildings worldwide between 1995 and 2016. Similar to the socio-demographic data set, the two occupant behaviour data sets are cross-sectional and collected with a sole purpose to support the building occupant behaviour research. This study is interested in subsets of the dataset associated with specific building types.
Evaluating spatial and seasonal determinants of residential water demand across different housing types through data integration
Published in Water International, 2018
Saeed Ghavidelfar, Asaad Y. Shamseldin, Bruce W. Melville
Socio-economic information for households was obtained from the Statistics New Zealand Data Lab (Statistics-NZ, 2015) for the censuses of 2006 and 2013. The Data Lab provided access to the microdata (data on specific people, households, and businesses). From the census microdata, it is possible to estimate household and housing information (e.g. household income, household size, education, number of bedrooms, etc.) for different types of housing across different areas. We collected the census information of households living in detached houses and low-rise apartments (joined dwellings of one, two, or three storeys) at the census area unit level. Information on high-rise apartments (joined dwellings of four or more storeys) also was collected at the meshblock level. The meshblock and the area unit are the smallest and second-smallest geographical census units in New Zealand, respectively (Statistics-NZ, 2015). For detached houses and low-rise apartments, the household information was collected at the area unit level because in these sectors, due to the low density of housing, many census variables were not available at the meshblock level to protect the privacy of residents.