Category: s18-busad360

Lesson 8: Measuring Forecast Error

Review:

  • Exam 1 Results
  • Remodeling Project

Presentation:

  • Forecast Error
    • MAD – mean absolute deviation
      • MAD = ∑|Actual – Forecast|/(Number of Forecasts)
    • MSE – mean square error
      • MSE = ∑(Actual – Forecast)^2/(Number of Forecasts)
    • MAD easier to interpret than MSE
    • Scatterplot comparison – actual vs forecast
    • Residual analysis
    • Outliers

Assignment:

  • Using your Exam 1 selling price estimates:
    • Compare your estimates with the Actual Selling Prices below
    • Generate a scatterplot with Actual vs Forecast values
    • Create a 1-page summary and submit in class on Wed
ID Address Neighborhood Beds Baths SqFt Actual Selling Price
1 1133 Beulah Central High School 2 1 856 55,000
2 1127 Cypress Minnequa Area 3 1 763 27,000
3 5136 Killdeer Northridge/Eagleridge 3 3 2,246 216,922
4 901 W 27th Northside/Avenues 4 2 2,078 153,000
5 74 Pennwood Regency and Meadows 5 3 2,112 179,900
6 805 Westacres Sunset Park 3 2 1,618 145,000
7 1623 Comanche Belmont 2 1 875 105,000
8 1431 E Ash Eastside 5 2 1,740 49,000

 

More

Lesson 7: Review for Exam 1

Review:

  • Part 1 Real Estate Multiple Regression Model
    • Bring your 1-page model summary to class on Wed
    • Bare minimum model = bare minimum passing grade
  • Exam 1 (in class) on Wed, Feb 7
    • Open note
    • Open calculator (I will have calculators you can borrow)
    • No use of PCs, tablets, laptops (or other computing devices)
    • No phones (or watches)
    • No leaving class during exam

Presentation:

  • Exam 1 Review Topics
    • Scatterplots
    • Correlation
    • Simple Regression
    • Multiple Regression
    • Interpretation of Regression Output
      • R^2
      • Coefficients > y-hat equation
      • t-statistics and associated p-values (individual variable significance)
      • F-statistic and associated p-value (overall model significance)
    • Multicollinearity
    • Interaction Variables
    • Dummy Variables
    • Index Variables
    • Produce y-hat estimate given x values

Assignment:

  • Work on your real estate model
  • Study for Exam 1

 

More

Lesson 6: Applied Regression Analysis (2 of 2)

Review:

  • Multicollinearity
  • Interaction Variables
  • F-Statistic
  • Exam 1 on Wed, Feb 7
    • See Exam 1 Part 1 instructions below
    • Review on Mon, Feb 5

Presentation:

Assignment:

  • Exam 1 Part 1
  • Multiple Regression Analysis
    • Select the worksheet corresponding to the last digit of your PID from this file: PuebloRealEstate_Exam1Data_ByPID
    • Build a regression model to estimate selling price
      • You must use 1 interaction variable
      • You must use 1 or more Dummy variables; or, you can create and use an Index variable
    • Prepare a 1-page summary of your model, including
      • Regression Output with highlights
      • y-hat equation (in equation format, not just a copy of the regression output)
      • Define the variables used in the model (if interaction, how is it calculated?)
      • Demonstrate how to apply the model
        • What “selling price” estimate would your model produce for a home in Belmont neighborhood, 3 bedroom, 2 bath, 1800 sqft
      • Think of your 1-page summary as a “poster” that explains your model
        • It should be clear and easy to understand
        • It should provide helpful text to explain different aspects of the model
    • Be prepared to answer questions about your regression model
    • You will use your model during Exam 1 and then turn it in after completion of the exam
    • Exam is “open notes” (so bring anything useful) but you may only submit the 1-page summary (I won’t accept a stack of different model outputs)

 

More

Lesson 5: Applied Regression Analysis (1 of 2)

Review:

  • Multiple Regression
  • Tutoring Available
    • David Mould
    • Mondays 11:15-1:15
    • HSB 110
  • Exam 1 on Wed, Feb 7

Presentation:

  • Applied Regression Analysis
    • Multicollinearity
    • Interaction Variables
    • F-Statistic
    • Demonstration with Sample Real Estate data
    • Estimate selling price for a 1500 sqft, 3 bd, 2 ba home

Assignment:

  • Build a regression model to estimate Real Estate selling prices
    • Use this data set Pueblo RE East Side
    • Use an interaction variable to avoid multicollinearity
    • Use your regression model to estimate selling prices for these 4 properties
      • Belmont 3 BR, 2 BA, 1600 SqFt
      • Belmont 4 BR, 3 BA, 2400 SqFt
      • East Side 3 BR, 1 BA, 1200 SqFt
      • East Side 2 BR, 1 BA, 800 SqFt
    • Prepare a 1-page summary
      • Regression output
      • y-hat equation
      • 4 property Selling Price estimates
    • Due Wed in class
More

Lesson 4: Intro to Multiple Regression

Review:

  • Simple Regression
  • Submit Assignment

Presentation:

  • Intro to Multiple Regression
  • Regression Output Interpretation
    • t-statistic
    • p-value
    • R² measures “goodness of fit” (explains % of variance)
    • p-value measures “significance” (probability of result by chance)
    • rank by significance

Assignment:

  • Use “Statistics” or “XL Miner” Add-on, your choice
  • Complete Problems 1 and 2 using Sheets data
    • Prob 1: Use “y” as dependent variable, use “x1”, “x2” and “x3” as independent variables
    • Prob 2: Use “Dividend Payout” as dependent variable, use “Insider Ownership” and “Debt Ratio” as independent variables
    • Highlight R-squared, coefficients, t-statistics and p-values
    • Write the linear equation for y-hat by hand
    • List, in rank order, the variables from most significant to least significant
  • Run Multiple Regression using East Pueblo RE Sales 2014-2016
    • Use “Selg Pr” (selling price) as dependent (y) variable, use “Bd”, “Ba”, “TtlGrSF”, and “DOM” as independent (x) variables
    • Highlight R-squared, coefficients, t-statistics and p-values
    • Write the linear equation for y-hat by hand
    • List, in rank order, the variables from most significant to least significant
  • Prepare a 1-page summary
    • Include regression output with highlights
    • y-hat equation (typed or hand-written)
    • ranked list of independent variables from most to least significant
  • Submit in class on Monday
More

Lesson 3: Simple Linear Regression

Review:

  • Scatterplots
  • Correlation
  • Slack … okay, fine

Presentation:

  • Simple (bivariate…that means 2 variables) Linear Regression

Assignment:

  • Background
  • Use Snowpack n Runoff (source: National Water and Climate Center, USDA) data in Sheets
    • Snowpack (H2O equivalent) = the “x”, “independent”, “explanatory” variable
    • Runoff (Stream volume) = the “y”, “dependent”, “response” variable
    • Generate Scatterplot
      • Fit Trendline
      • Label with Equation and R²
    • Use XL Miner Add-On to run Linear Regression
    • Use Statistics Add-On to run Linear Regression
  • Prepare summary page
    • Copy regression outputs
      • Scatterplot (with labels)
      • Output from XL Miner
      • Output from Statistics Add-On
    • Paste into Google Slides
    • Arrange and label for clarity
    • Add your name and section (11:15 or 1:00)
    • Print 1 page (yes, ONLY 1 page … with everything on it)
  • Bring summary page to submit in class on Wed
More

Lesson 2: Scatterplots and Correlation

Review:

  • Syllabus
  • Join Slack
  • Sheets
    • Filters
    • Line plots (time series)
    • Scatter Plots
    • Trendlines
    • Regression Equation
    • R²

Presentation:

Activity:

  • Correlation analysis
    • Use this data set: Pueblo RE 2014 – 100 rows
    • Find correlations for Beds, Baths, Total SqFt and Selling Price
    • Identify the variable with the strongest correlation to Selling Price (y)
    • Create a scatterplot for the identified variable (x) and Selling Price (y)
    • Add a trendline and label with equation and R-squared
    • Generate regression output (using XL Miner) for the identified variable (x) and Selling Price (y) and then highlight R-Squared and Coefficients (do these values match the scatterplot labels?)
    • Save your file and then upload an image of the regression output (with highlights) to the #lesson02 channel in Slack.
More

Lesson 1: Syllabus, Sheets and Trendlines

Introduction:

Presentation:

Assignment:

Using the Pueblo RE Sales 2014 data file…

  • Open in Google Sheets
  • Select a neighborhood and filter so only properties in that neighborhood are visible
  • Highlight the “Total SqFt” and “Selling Price” columns (Shift-Ctl-Down Arrow helps)
  • Go to “Insert > Chart” to produce a scatter plot
  • Fit a “Trendline” to the data and display the equation and the R² value.
  • Record (on a sheet of paper) the neighborhood name, linear equation and R² value
  • Repeat until you’ve recorded data for 5 separate neighborhoods (you may choose any set of 5 neighborhoods)
  • Hand in the paper with data recorded before leaving class

 

More