Attached is the file to answer. I already did much of the work. I need someone to correct it and make it perfect using STATA program focusing especially on 1_c and 2_b,c,d,e,f,g. Data set PS2 is for Number 2.

Spring 2015 Department of Finance Finance 6279: Real Estate Problem Set 1 (Due Feb 7, 2015) 1. Consider a multifamily real estate market with following; = 1 1 2 = = 2 3 4 (Space Market) = (Long Run Equilibrium) (Asset Market) (New Construction) where is demand for multifamily space, is the number of households in the area, is rent per square foot, is price of multifamily space per square foot, is an interest rate, is amount of new construction, is construction cost in multifamily housing construction and is supply of multifamily space. A careful analysis of data on this market yields the following estimates for parameter values; 1 = 45 2 = 0.8 1 = 0.65 2 = 0.4 3 = 1.2 4 = 0.75 = 5% = 2.5% = 300 = 150 a. Calculate the equilibrium amount of multifamily space (in 1000's unit) and rent (in $1000's). b. If the number of household increases by 10% in the future, calculate the effect on the equilibrium price. c. Suppose the interest rate drops from 5% to 4%. What is the effect on the market price in the short run? What is the effect on the price in the long run? 2. PS2_data.xls is an Excel file that contains housing transaction records of a town for 76 quarters (19 years). Each observation corresponds to a transaction, and one house can appear in multiple observations. The dataset has 22 variables, and brief variable description is provided in the worksheet \"Variable Description.\" a. Calculate mean, median and standard deviation of each variable except for House_ID and Quarter. b. Estimate a hedonic regression of log house price on all the variables in the dataset (except for House_id and quarter). There should be 19 variables. Before running a regression, make sure you also create a set of quarterly dummy variables and include them in the regression. There are 76 quarters covered in the data, and you need to create 75 dummy variables from 2nd quarter to 76th quarter. For example, if a transaction took place in 10th quarter, a dummy variable for 10th quarter will have a value of one, but all the other quarterly dummy variables are zeros. If a transaction took place in the first quarter, all the quarter dummy variables will be zeros. c. Using estimated coefficients on quarterly dummy variables, construct a house price index (with 1st quarter as base quarter) and draw a graph (quarter on the horizontal axis and index on the vertical axis). d. Construct a subsample of houses transacted more than once from PS2_data.xls, and repeat the part (a) for this sample. e. Compare characteristics of the whole dataset and the repeat sample. f. Estimate a repeat sales regression of log house price differences on quarterly dummy variables. g. Construct a repeat sales index based on estimated coefficients from the part (f), and compare with the index from the part (c). d. Repeated Sample First, I chose houses that at least have two observations, which results in 32373 observations. Then, I take the first difference of log(price) and calculate the main statistics of this subsample, which results in 18515 observations. Table 9 Variable Obs Mean Price Near_Park Living_area Detached Sewage 18515 18515 18515 18515 18515 388010.7 .0071294 123.1284 .6006481 .9935188 ISO1 ISO2 Extwall Roof1 Roof2 18515 18515 18515 18515 18515 Bathing Tiledbath Laundry Kitchen1 Kitchen2 Min Max 191058.4 .0841363 39.94731 .4897784 .0802469 70000 0 22 0 0 4422000 1 481 1 1 .1557656 .8387254 .2170672 .0147988 .7606265 .3626428 .367794 .4122599 .1207501 .4267126 0 0 0 0 0 1 1 1 1 1 18515 18515 18515 18515 18515 .9884418 .1957332 .7466379 .1531731 .8401836 .1068888 .3967748 .4349483 .360164 .3664456 0 0 0 0 0 1 1 1 1 1 Fireplace Recroom Sauna Garage2 Garage1 18515 18515 18515 18515 18515 .4017283 .1567378 .236943 .0444504 .6311639 .4902608 .3635632 .4252185 .2060992 .4825024 0 0 0 0 0 1 1 1 1 1 Garage1 lprice dlprice iobs iobsn 18515 18515 18515 18515 18515 .6311639 12.77335 .102923 2.313476 2.626951 .4825024 .4266817 .4500304 .6002497 .8180063 0 11.15625 -1.602612 2 2 1 15.3021 2.060849 7 7 obs 18515 38101.32 14692.29 962 61688 Table 9 Variables Price Median $347000 Near_Park 0 Living_area 120 Detached 1 Sewage 1 ISO1 0 ISO2 1 Extwall 0 Roof1 0 Std. Dev. Roof2 1 Bathing 1 Tiledbath 0 Laundry 1 Kitchen1 0 Kitchen2 1 Fireplace 0 Recroom 0 Sauna 0 Garage2 0 Garage 1 1 e. Compare characteristics of the whole dataset and the repeat sample. Table 9 Number of Observations Mean Price Median Price Price Range Standard Deviation Whole dataset 62,297 $374,683 $335,000 $59000 - $13,100,000 $193,820 Repeat sample 18515 $388011 $347,000 $59000 - $4,422,000 $191058 The main difference with the original data is the number of observations, 62297 versus 18515. The mean of the price increase from $374,683 to $388011 and its median also rise from $335000 to $347000. Moreover, the standard deviation is lower while the range is much smaller. This give us a clue that the index in the repeated subsample is probably less than that of the original sample. f. Estimate a repeat sales regression of log house price differences on quarterly dummy variables. Once considered dummies for houses that have two or more transactions, R 2 and AdjustedR2 values are less than the first case (See Annex 1). Also, Root Mean Square Error was higher (0.3 vs. 0.44). The main reason is that we are not considering other explanatory variables than dummies. Notice that the number of observations considered in this regression is just 18515. g. Compare both indices. Figure 3 90 Repeated Index 100 110 120 130 Repeated Index Price 0 20 40 obs 60 80 Figure 3 90 100 110 120 130 140 House Indices Price 0 20 40 Quarter Repeated Index 60 80 Hedonic Index Statistics for Repeated Index (Table 4) depict us that annual percentage (var_index_r) variation is between -11.80% and 10.34%, with 3.79% as standard deviation. As can be seen from figure 3, repeated index drop more than the hedonic index at the beginning then both show similar pattern though the quarters. Because of that drop, and since both starts with a 100 benchmark for the 1 st quarter, the repeated Index is always lower afterwards. It reached maximum of 130.33 while the hedonic index was higher and reached its peak at 137.03 and this was between the 45th and 55th quarter. Table 9: Repeated Index Statistics Variable Obs Mean index_r var_index_r 76 72 109.7048 1.570273 Std. Dev. 12.91069 3.794789 Min Max 86.71415 -11.80373 130.3319 10.33563 Comparing both indices (Table 5) in annual percentage change, we can see that repeated index has more volatility than hedonic index (3.79 vs. 2.64), because it includes the change in price, which adds more volatility in terms of the mean. Table 9: Annual Percentage Variation Variable Obs Mean var_index_h var_index_r 72 72 1.355249 1.570273 Std. Dev. 2.63566 3.794789 Min Max -4.71142 -11.80373 9.018629 10.33563