Data analysis answering questions using RStudio

neighborhood id：220 Borough ID：4

220: SO.Jamaica-Baisley Park

Data：https://go.wetransfer.com/t-VHUUlRqaYp

Question A：

1. Filter the data to include only residential real estate of your neighborhood. Group it by year, and summarize the data to show the average price of 1 square foot of real estate. List the results.
2. Do numbers show for all years? If a year shows N/A, why is that happening?
3. Filter your data to focus on residential real estate with adequate information for your model (remove fields with 0 for price or square feet)
4. Group the filtered data by year, and summarize the data to show the average price of 1 square foot of real estate. List the results.
5. Compare your selected neighborhood with 2 nearby neighborhoods. List the numbers.
6. Produce a plot that compares the neighborhoods. Explain the plot and the reason you chose that type of plot.

Question B：

Part One: Time Series

• Perform time series analysis on the total dollar amount of residential real estate sales on your neighborhood.
• Use sales beginning in the year 2009 to develop your model. Develop a forecast for the next 8 quarters of sales.
• Present your findings to include all the below:

• A table that shows the forecast numbers, confidence bands for the next 8 quarters.
• Define the model type that you used (Additive or Multiplicative) and why you used it.
• Determine whether your model factored trend and seasonality and why it did or did not.

Part Two: Regression Forecast

In this part, you are to develop two models. One that includes time only as a predictor. The other includes both time and seasonality. For both models, list and discuss the below points.

• The model equation.
• The significance of each predictor. What does that value represent and what does it mean for your model?
• The R squared and the adjusted R squared. What does each metric mean?

Part Three: Regression Prediction

Use a multiple regression model to determine the sale of a given residential property in your neighborhood. Include:

• Sale Date
• Year built
• Building type (categorical)
• Gross Square Feet
• Number of Units

After you build the model, answer the following questions

• what are the most and least useful predictors of the amount of a sale?
• Are there any redundant independent variables? How can you tell?
• According to your model from (3), which properties were the biggest bargains and which were the most overpriced? How might you account for these disparities?

Part Four: Analysis

Write a paragraph to summarize your findings with a focus on the output, interpretation of the output, and what the insights mean for our decision-making process