MAT240.docx 3/19/22, 6:05 AM

Selling Price and Area Analysis for D.M. Pan National Real Estate Company ​1

Report: Selling Price and Area Analysis for D.M. Pan National Real Estate Company

[Your Name]

Southern New Hampshire University ​Median Housing Price Prediction Model for D. M. Pan NationalReal Estate Company ​9

IntroductionD. M. Pan National Real Estate Company's CEO aims to assist their real estate agents inestimating home prices based on square feet. As a junior data analyst employee, I've been askedto write a research on how square footage influences housing values in the country. According tostudies, the square footage of a home is closely proportional to its price. As a result, the biggerthe square footage, the more expensive the residence. This report uses data from all house pricesin the United States in 2019 to create a regression model that predicts home prices using squarefootage, with the goal of proving if the hypothesis is correct. Because the variables in thefrequency plots from the National Statistics and Graph Document are normally distributed, linearregression is acceptable for this study. The x and y variables are also included in the variables.The square footage is the independent or predictor variable, while the home listing prices are thedependent or predicted variable, represented by the y variable. The scatter plot should show arising trend to the right, showing a positive relationship. The response variable is a dependentvariable which is influenced by the predictor variable, whereas the predictor variable is anindependent variable which is unaffected by other variables. The predictor variable in thisscenario is square footage while the responder variable is listing prices, which are influenced bysquare footage.

Data CollectionFrom a total population of 1000 households, a sample of 50 homes was chosen to be analyzed inthe research. The sample was chosen using a simple random sampling in which 20 residenceswere chosen from the population's data received from the 2019 Real Estate County statistics. Thestudy's key variables are the listing price which is the dependent variable and square feet whichis the independent variable.Figure 1 depicts a scatter plot of home listing prices vs square footage in sample populations ofhomes sold in the United States in 2019.Figure 1.

Data Analysis

The histograms in Figures 1 and 2 are based on sample data of listing prices and square feet,respectively.Figure 2.

https://www.sweetstudy.com/files/mat240-docx-8531789 1

MAT240.docx 3/19/22, 6:05 AM

Figure 3.

The summary statistics for both the square feet and listing prices variables are shown in Table 1below.Table 1. square feet listing priceMean 2566.92 342574Standard Error 211.5122 16572.59Median 1977 333250Mode 5284 265400Standard Deviation 1495.617 117185.9Sample Variance 2236871 1.37E+10Kurtosis 0.714474 3.96408Skewness 1.471359 1.713201Range 5275 575800Minimum 1145 169700Maximum 6420 745500Sum 128346 17128700Count 50 50

The sigma curve form of the histogram on the sample data of listing prices is somewhat skewedto the left. Its shape is similar to the median listing price frequency table in the National statisticsgraphs article. The means of the population and sample data, however, diverge, as seen in thesummary statistics tables. The histogram also indicates a gap between 609700 and 719700,indicating that the listing prices in that range were either absent or relatively low. The listedprices ranged from 169,700 to 745,500 dollars.The histogram for square feet illustrates that the majority of the often occurring square feet in thesample are on the right side of the graph, with the number of square feet decreasing as thenumber of square feet increases. As shown in the National statistics graphics paper, thehistogram's shape differs from that of the population. The population data exhibits a normaldistribution with a perfect sigma curve. There is a gap between 2545 and 3945 square feet,according to the sample statistics histogram. Since the sample mean is 2566.92 and thepopulation mean is 1944, there is also a disparity between the sample mean and the populationmean.

The Regression Model

Scatter plot of square feet versus listing prices containing the trend line, r-square and regressionequation is shown in figure 4.Figure 4.

Figure 4 demonstrates that the majority of the data points do not deviate from the trend line, andthe trend line rises to the right. The data pattern indicates that the dependent variable, may beprojected, and hence a regression model for prediction can be created. This can be done byforming the equation using the trend line or by running a regression analysis.The scatter plot reveals a substantial positive relationship between home square feet and listingprices. The positive correlation indicates that when the square footage of a home increases, sodoes the listing price, indicating that the variables are directly proportionate. The trend line'sangle indicates the strength of the relationship and that the majority of data points lie around theline of best feet.The output summary of the regression analysis for the two variables is shown in Table 2.

https://www.sweetstudy.com/files/mat240-docx-8531789 2

MAT240.docx 3/19/22, 6:05 AM

Table 2.Regression StatisticsMultiple R 0.904239R Square 0.817648Adjusted R Square 0.813849Standard Error 81024.21Observations 50

The variables exhibit a high positive connection with an r-value of 0.904. This backs up thescatter plot's visualization conclusions that there is a large positive association between listingprices and the sample's square footage.

The Line of Best FitThe regression equation to be used in this study is derived from table 3 below. This is becausethe table contains the coefficients and the constant.Table 3.

CoefficientsStandard

Error t Stat P-valueIntercept 102058.7 22933.67 4.450168 5.09E-05square feet 113.5389 7.739204 14.67062 2.31E-19

Therefore, the regression equation derived is in the form;

Y = 113.5389X + 102058.7Where X = Square feet

Y = Listing priceThe slope is 113.5389. The Y-intercept, where the line of best fit crosses the Y axis, is 10258.7.The independent variable square feet explains 81.78 percent of total differences in listing pricevariables, according to R-squared of 0.8178. By substituting the value of square feet in X, theregression equation may forecast the listing price of a home using square feet. Using a squarefoot of 7000 as an example, we may forecast the following listing price:

Y = 113.5389(7000) + 102058.7Y = 794772.3 + 102058.7

Y = 896831As a result, when the square foot is 7000, the listing price is expected to be 8996831.

ConclusionsAccording to this study, square footage is directly proportional to property listing prices in theUnited States. The histogram of square feet produced unexpected results, as it was expected to becloser to normal than the population's frequency table. However, because of a strong positivecorrelation of 0.9042, which is extremely close to 1, it has a significant impact on a home'slisting price. The study raises the intriguing question of whether there are other characteristicsthat influence property listing prices and whether they may be utilized to anticipate them.

https://www.sweetstudy.com/files/mat240-docx-8531789 3