Analysis of Las Vegas Housing Market Essay Example

When one is in the market for a home, a question, albeit an important one that they must quarrel with is “what are the driver(s) of housing value?” From a broker’s standpoint, the popular answer to this query is something to the tune of “location, location, location!” In this study, we will delve into this exact topic, and in doing so will attempt to uncover the most influential drivers of prices in a housing market. We are using housing data specific to the Las Vegas market in this analysis. The various factors that we believe to influence price include changes in housing square footage, the number of bedrooms in a house, the number of bathrooms, the presence of a pool, and finally, 4 location factors (Summerlin, Green Valley, Northwest, and East). Our goal here is to discover which of these factors bare the most weight in influence housing prices in the Las Vegas area, and as a result may be good predictors of price. 

We will first begin by examining a table that illustrates what we believe will be the signs of our beta coefficients when we run our regression analysis. We make basic assumptions here of which direction our various independent variables will pull our dependent variable (price), and any deviations from our predictions here will be closely examined in the regression portions of this study. We next compile and examine a table of basic descriptive statistics (min., max., mean, std.) for all the variables in our analysis, with the purpose of uncovering basic trends in our data that could provide foresight to our more intense analysis later. We also will look at a correlation matrix table, of which shows us both the direction, as well as the strength of the relationship between our dependent variable (price) and our potential predictor variables ((sqft, bed, bath, pool, Summerlin, Green Valley, and Northwest (using East as a base)). We next attempt to visualize some of the relationships by way of scatterplots. We examine 3 scatter plots between variables price to sqft, price to number of bedrooms, and finally price to the number of bathrooms present. We look to these visualizations for evidence of linearity between our dependent variable price to the mentioned independent variables. Finally, we will construct and examine 2 regression tables whose beta coefficients will give us the best overall idea of which independent factors, in particular, are the greatest influences on housing valuation. Our first model will be a “reduced” model, regressing our independent variable price against variables: sqft, bed, bath, and pool, in order to view how effective these variables alone are at predicting housing prices. Our second regression will be our “full” model that will introduce our four location variables to our reduced model (Summerlin, Green Valley, Northwest, and East). This analysis should give us a good idea of exactly how important location is in regard to housing value. We will then determine the statistical significance of our regression betas through the p-value approach and will conclude the analysis by examining our R^2 factor and testing the overall power of our model to confidently predict housing prices.