By: Alan Cheung Background In this week’s blog, we will learn how to use the t-test and ANOVA statistical tests to compare different groups. In the t-test, we see if the means of two populations are statistically different. In ANOVA, we see if the difference among the means of multiple populations are statistically significant. In … More Comparing Groups
by Alan Cheung Background In this week’s blog, we will learn how to use correlations when analyzing Boston’s food establishment inspection data. According to Daniel O’Brien’s Urban Informatics: Using Big Data to Understand and Serve Communities, “in statistics, a correlation is used to evaluate the relationship between two numerical variables, specifically whether they rise and … More Correlation
Background In last week’s blog, we discussed about creating a latent construct and manifest variables. We used gentrification as our latent construct, and we used business turnover, types of restaurants, and instances of recent remodeling or new construction as our manifest variables. We also mentioned that we are using census tracts as our unit of … More Building Latent Constructs – Alan Cheung
Alan Cheung 2023-09-27 Introduction Continuing our data exploration on Boston’s food establishment inspections data, we will use new R tools, such as pipelines, to discover deeper insights about the data and the dynamics of the city of Boston. By the end of this post, you will learn how to: Approach analyzing an unfamiliar data set … More Pulse of the City: Food Establishment Inspections
Food inspections In the heart of Boston lies a treasure trove of data known as the “Food Establishment Inspections.” With a whopping 65,534 observations across 26 variables, it serves as a comprehensive record of individual inspections and outcomes for the city’s diverse food establishments. These inspections span from as far back as April 2006 to … More Tell a data story: Restaurant violations
Introduction Urban informatics uses data analytics to understand the behaviors, activities, and trends within cities. One of its many applications is to assess the quality and safety of food establishments. This blog post aims to guide you through an exciting data exploration journey, unraveling some intriguing questions and observations about food establishments in Boston. We … More Telling a Data Story
Introduction and Selection Rationale For my final city walk, I decided to utilize the variable of Inspection.Fail.Count (Number of failed health inspections per food establishment) to distinguish between different regions of Boston. For geographic boundaries, I utilized the Neighborhood Statistical Areas defined by the City of Boston, and aggregated Inspection Failures by NSA. This yielded … More City Exploration 3 – Food Inspections
Introduction to the Latent Construct of ‘Performance’ for Boston Food Establishments For the purpose of my city walk assignment, I decided to use my latent construct of “performance” as the filter variable to decide my neighborhood. Performance is a variable that is a latent construct of multiple continuous numerical variables within the dataset. The 11 … More City Exploration 2 – Downtown Boston and the Food Industry
Principal Components Analysis or PCA is a statistical method used to reduce the dimensionality of a large dataset with multiple variables, lowering the number of variables while retaining a significant amount of the information of the original dataset. From a geometrical perspective, a principal component created through this analysis represents the directions of the data … More Latent Construct – Food Inspections
Shreyas Shaktikumar Working in the Food Inspections group, the dataset I am working with consists of two large files, one with a detailed record of every food inspection and associated violation records for every inspection conducted at Boston food establishments between 2010 and 2020, and the second consisting of aggregated inspection/violation data for establishments combined … More REVEALING KNOWLEDGE THROUGH FOOD INSPECTION DATA
Seeing Boston Neighborhoods through Administrative Data 