aakashmth522

MTH 522 Project-3

I’ll now move on to visualize how earnings are distributed within each department. This will give the earnings spread a clear visual depiction. This might make it easier to see trends and anomalies in the data.

Then, today, I examined employee earnings reports spanning the years 2011 to 2022 in order to comprehend the rise in total payroll, the decline in the workforce during that time, and the rise in average earnings per employee.

Subsequently, I intend to use the employee’s zip code to display the earnings distribution on a map and investigate whether the employee’s pay affects where they live.

To comprehend the variation and find any outliers, I examined the distribution of earnings within the departments today. To clearly illustrate the earnings spread, this required computing the standard deviation of earnings for each department and presenting the results.

I then determined the department-specific earnings standard deviation. An understanding of the earnings distribution within each department was given by the standard deviation. A larger range of incomes among the department’s personnel is indicated by a higher standard deviation. The most variable salaries are found in the Superintendent’s office, Boston Police Department, and BPS High School Renewal. Understanding the salary scale and distribution within the department may benefit from this.

The Employee Earning report dataset has a number of columns, including POSTAL, which lists postal codes, and NAME, DEPARTMENT_NAME, TITLE, and other types of earnings.

I’ll continue examining the TOTAL_GROSS earnings distribution among the various departments today. determining the dataset’s highest earners. Including a summary of typical pay by title or department.

The Boston Police Department has the largest overall gross profits among the top 10 departments, followed by the Boston Fire Department and BPS Special Education.

Subsequently, I ordered the dataset’s top 10 earners by total gross earnings. The people on the list work in a variety of departments, with the Boston Police Department being represented among the highest paid.

I then compiled the average salary by title and department. The superintendent’s office had the highest average earnings, followed by the Boston Fire Department and School Support & Transformation. The average total gross earnings by department. This overview sheds light on the typical pay scales for the various departments.

I continued to analyze the Employee Earning Report dataset today.  I used median earnings to depict the regular earnings distribution among the top ten departments. The central tendency and distribution of profits within various departments can be compared with the aid of this visualization.

My investigation revealed that the dataset included information on about seven different categories of employee earnings. Each kind includes a few rows with no data at all, indicating that the corresponding employee does not receive any money from this kind of earnings.

The number of rows for each sort of earnings for which there is no data is listed below. These empty rows should be filled with 0 to 

to further the analysis of this dataset.

REGULAR   600
RETRO         20112
OTHER         7378
OVERTIME 16392
INJURED      21983
DETAIL         21088
QUINN_EDUCATION   21835

Now that we’ve covered the basics of time series analysis, I’m prepared to discuss how I’m using it for our BPDA economic indicators project.

Finding patterns and trends in Boston’s economy throughout time is my main objective. I’m doing this by examining data points like hotel occupancy rates, employment rates, housing costs, and traffic at Logan Airport. We can see how these data points have changed over time and spot any reoccurring trends by looking at them in chronological order.

This is how I’m going about it: I start by scanning the dataset for trends. This entails determining whether specific economic indicators have been rising, falling, or remaining largely stable over time. For instance, I might discover that there has been an upward trend in hotel occupancy rates. 

trend in the summer, signifying the height of traveler activity.

I’m now looking at seasonality. Finding patterns that recur on a regular basis is required for this. Do certain months always see an increase in property prices? Is there a specific season of the year when employment peaks? Comprehending these periodic patterns might be essential for organizing and formulating policies.

Additionally, I’m watching for any anomalies or distinct data points that deviate from the norm. These could be indicators of unusual occurrences or shifts in Boston’s economic landscape.

I’m eager to discuss the next stage of our investigation into the dataset of BPDA economic indicators. We are entering the domain of Time Series Analysis at this point. I want to go over what time series analysis is, how it’s used, why it’s important, and where it’s usually utilized before getting into how we’re using it for our project.

One statistical method for working with time-ordered data points is time series analysis. Imagine it as a movie, where each frame, or data point, represents a moment in time that, when combined, tells a tale. We can better comprehend the underlying structure and evolving trends in the data thanks to this study.

Why hence apply Time Series Analysis? It all comes down to the “when.” We can gain a better knowledge of trends and seasonal effects by knowing when things happen and how patterns recur over the course of days, months, or years. This is important in areas like economics, where knowledge of cycles can help make better decisions. Examples of these cycles include times when individuals spend more, when tourism peaks, and when job markets shift.

How is Time Series Analysis used? It all comes down to looking at the data in relation to time. We search for patterns that reoccur at regular intervals, such as an increase in hotel reservations in the summer, seasonality (when something is continuously rising or falling), and anomalies or outliers. We can predict future trends based on historical patterns by using statistical models, which isinvaluable in planning and decision-making.

Here is a summary of what I discovered: Approximately 3,940 foreign flights arrived and departed from Logan Airport per month on average. During peak hours, this number even increased to 5,260 flights. This indicates that a large number of foreign visitors were arriving in Boston. The hotels were also rather full, with an average of 82% of the rooms reserved, and a night’s stay costing roughly $244.

It appears that there were typically 356,000 jobs available in Boston based on our analysis of employment data. However, the unemployment rate, or total number of unemployed persons, was just about 4%. This is something we might want to investigate further because it varies throughout time. Furthermore, Boston real estate can be highly expensive.

The typical cost of a home could occasionally reach $517,750.

There is still plenty to learn; this is only the beginning. I’m going to continue examining the statistics to find out more information regarding the state of the Boston economy.

My primary focus in today’s class was learning how to do time series analysis using a particular dataset. I used a dataset that I got from Analyze Boston that included the average monthly hotel costs in Boston from January 2013 to December 2019. This dataset offered a thorough framework for investigating many facets of time series research.

I loaded the dataset and looked at its structure to get started. For our analysis, the three most important columns were “year,” “month,” and “hotel_avg_daily_rate.” I then combined the year and month columns to create a datetime index, which I then used as the index for our time series data. I was able to visually evaluate trends, seasonality, and anomalies by charting the time series data. This action is essential since it aids inknowing the general pattern of the data and directs additional investigation.

We also talked about the importance of stationarity in time series analysis in class. When a time series is considered stationar, it means that its variance and mean do not alter over time. To guarantee dependable analysis, it is crucial to verify stationarity. We investigated techniques to attain stationarity for non-stationary time series, like series differencing.

All things considered, the course gave a thorough introduction to time series analysis utilizing the dataset of Boston’s average monthly hotel rates. We learned a lot about analyzing and interpreting time series by looking at the dataset’s structure, visualizing the data, and realizing how important stationarity is data effectively.

I’ve made the decision to concentrate on the “Economic Indicators” dataset from Analyze Boston for my third project. This dataset, which was compiled by the Boston Planning and Development Authority (BPDA) every month from January 2013 to December 2019, includes a plethora of statistics regarding economic trends in the City of Boston. I think this dataset will provide insightful information since I’m interested in economic indicators and because inclusive growth planning requires a grasp of economic statistics.

Among the many datasets at my disposal, I think studying economic indicators will enable me to examine important elements like work, housing, travel, and real estate development—all of which are vital. This decision supports my objective of carrying out insightful research and adding to our comprehension of the city’s financial dynamics.

I’m excited to dig into this dataset, glean insightful knowledge, and help the project succeed by offering a thorough examination of Boston’s economic indicators.