10.45 Sales price versus assessed value. Real estate is typically reassessed annually for property tax purposes. This assessed value, however, is not necessarily the same as the fair market value of the property. Table 10.3 summarizes an SRS of 35 homes recently sold in a midwestern city.¹⁹ Both variables are measured in thousands of dollars.

(a) Inspect the data. How many homes have a sales price greater than the assessed value? Do you think this trend would be true for the larger population of all homes recently sold? Explain your answer.
(b) Make a scatterplot with assessed value on the horizontal axis. Briefly describe the relationship between assessed value and sales price.

(c) Based on the scatterplot, there is one distinctly unusual observation. State which property it is, and describe the impact you expect this observation has on the least-squares line.

TABLE 10.3: Sales Price and Assessed Value (in Thousands of $) of 35 Homes in a Midwestern City

Property	Sales price	Assessed value	Property	Sales price	Assessed value	Property	Sales price	Assessed value
1	83.0	87.0	13	249.9	192.0	25	146.0	121.1
2	129.9	103.8	14	112.0	117.4	26	230.5	212.1
3	125.0	111.0	15	133.0	117.2	27	360.0	167.9
4	245.0	157.4	16	177.5	116.6	28	127.9	110.2
5	100.0	127.5	17	162.5	143.7	29	205.0	183.2
6	134.7	127.7	18	238.0	198.2	30	163.5	93.6
7	106.0	110.9	19	120.9	93.4	31	225.0	156.2
8	91.5	90.8	20	142.5	92.3	32	335.0	278.1
9	170.0	160.7	21	299.0	279.0	33	192.0	151.0
10	295.0	250.5	22	82.5	90.4	34	232.0	178.8
11	179.0	160.9	23	152.5	103.2	35	197.9	172.4
12	230.0	213.2	24	139.9	114.9

(d) Report the least-squares regression line for predicting selling price from assessed value using all 35 properties. What is the estimated model standard error?
(e) Now remove the unusual observation and fit the data again. Report the least-squares regression line and estimated model standard error.
(f) Compare the two sets of results. Describe the impact this unusual observation has on the results.
(g) Do you think it is more appropriate to consider all 35 properties for linear regression analysis or just consider the 34 properties? Explain your decision.