Question

The consumption function is one of the key relationships in economics, where consumption y depends on disposable income x. Consider the quarterly data for these seasonally adjusted variables, measured in billions of dollars. A portion of the data is shown in the accompanying table.

DATE	Consumption	Disposable Income
2006:01	9149.80	9705.18
2006:04	9261.70	9863.79
2006:07	9263.20	9982.53
2006:10	9481.80	10111.17
2007:01	9635.90	10255.49
2007:04	9753.90	10358.59
2007:07	9852.00	10456.90
2007:10	9989.00	10623.38
2008:01	10097.40	10764.65
2008:04	10179.50	11129.30
2008:07	10256.10	11004.75
2008:10	9965.20	10913.25
2009:01	9915.40	10879.76
2009:04	9922.50	11090.93
2009:07	10018.10	11046.98
2009:10	10120.40	11121.75
2010:01	10253.60	11215.55
2010:04	10202.90	11367.95
2010:07	10355.60	11415.07
2010:10	10588.50	11514.72

a-1. Estimate Consumption = β₀ + β₁ Disposable Income + ε. (Round your answers to 2 decimal places.)

Consumption= __________ + ______________ Disposable Income

a-2. Using the above plot, determine if there is a possibility of correlated observations.

• There is a possibility of positive serial correlation.

• There is a possibility of negative serial correlation.

• Serial correlation is unlikely.

b. Discuss the consequences of serial correlation (correlated observations).

• OLS estimators and their standard errors are both biased.

• OLS estimators are biased but their standard errors are unbiased.

• OLS estimators are unbiased but their standard errors are biased.

Answer 1

Using Excel

data -> data analysis -> regression

a1)

y^ = -2495.43 + 1.34 Income

b)

Consequences of Serial Correlation. Serial correlation will not affect the unbiasedness or consistency of OLS estimators, but it does affect their efficiency. With positive serial correlation, the OLS estimates of the standard errors will be smaller than the true standard errors

option C) is correct

OLS estimators are unbiased but their standard errors are biased.