Scribd
Upload
71 views

Answer Chapter 4 - Basic Estimation Techniques

1. The document summarizes the results of statistical significance tests for several regression models. It reports the test statistics and p-values and interprets whether the regression coefficients are statistically significant at given significance levels. 2. It provides details on estimating regression equations for different data sets, including the t-statistics and p-values for individual regression coefficients, the F-statistic and p-value for the overall model significance, and the R-squared value measuring the proportion of variation explained. 3. Key results discussed include whether coefficients are statistically significant based on the critical t and F values, the exact significance levels of individual coefficients, and the proportion of variation explained by different regression models.

Uploaded by

dylla ningsih
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
71 views

Answer Chapter 4 - Basic Estimation Techniques

1. The document summarizes the results of statistical significance tests for several regression models. It reports the test statistics and p-values and interprets whether the regression coefficients are statistically significant at given significance levels. 2. It provides details on estimating regression equations for different data sets, including the t-statistics and p-values for individual regression coefficients, the F-statistic and p-value for the overall model significance, and the R-squared value measuring the proportion of variation explained. 3. Key results discussed include whether coefficients are statistically significant based on the critical t and F values, the exact significance levels of individual coefficients, and the proportion of variation explained by different regression models.

Uploaded by

dylla ningsih
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Answer for Chapter 4: Basic Estimation Techniques

1. a. 60
b. –2.39 (= –21.749/9.10); 2.000
–2.39 > 2.000
c. Yes: , thus the estimate of b, b̂ , is statistically significant at the 5
percent level.
d. 0.02 (2.000 is the critical t for a 0.05 significance level with 60 degrees of freedom);
b = 0; zero; 95 percent.
e. The hypothesis that b = 0 can be rejected with only a 5 percent chance of being wrong
(i.e., making a Type I error).
f. You can be 95 percent sure that if b is actually zero, the t-test will not reject the
hypothesis that b = 0 (i.e., will not make a Type I error).
g. The significance level gives the probability of making a Type I error, while the
confidence level gives the probability of not making a Type I error. They mean the
same thing since knowing one gives the same information as knowing the other.
2. a. F = 350.0 – 14.75M
b. The critical t for n – k = 28 – 2 = 26 degrees of freedom at the 0.01 level of
significance is 2.779.
The t-tests are:
For â: t = 3.79 > 2.779; â is statistically significant.

For b̂ : t = –3.17. Since t is negative, | t | = |–3.17| > 2.779; b̂ is also statistically


significant.
c. For â the exact level of significance is 0.0008, which means there is only a 0.08
percent chance that a = 0 with a t-ratio as large as 3.79.

For b̂ the exact significance is 0.0039, which means there is only a 0.39 percent
chance that b = 0 with a t-ratio as large as –3.17 (in absolute value since t is negative).
d. The critical F-statistic with 1 (= k – 1) and 26 (= n – k) degrees of freedom at the 5
percent significance level is 4.225. Since the F-statistic 47.215 is larger than 4.225,
the overall equation is statistically significant at the 5 percent level of significance.
The p-value for the F-statistic, 0.0001, shows that the equation is statistically
significant at better than the 1 percent level.

e. F̂ =350.0 - 14.75(25) =- 18.75


f. R2 = 0.6449, so 64.49 percent of the total variation in F is explained by the regression
equation; i.e., by variation in M.
3. a. 20 (= n – k = 22 – 2)
b. 2.086

c. For â: t = 3.51 > 2.086  statistically significant. For b̂ : t = 4.80 > 2.086 
statistically significant.

d. The exact significance level for â is 0.0022, and the exact significance level for b̂ is
0.0001. The exact confidence levels are 0.9978 (99.8 percent) and 0.9999 (99.9
percent), respectively. A t-test at the 95 percent confidence level understates the
degree of confidence associated with â and b̂ .
e. R2 = 0.6803 tells us that 68 percent of the total variation in Y is explained by the
regression equation (i.e., by variation in X); and 32 percent of the variation in Y is
unexplained.
f. k – 1 = 2 – 1 = 1 and n – k = 20, so at a 95 percent confidence level, the critical value
of F is 4.35. The regression equation is statistically significant because the F-ratio
(42.561) is greater than the critical value of F. The p-value on the F-statistic is less
than 0.0001, so there is virtually no chance that the F-test is mistakenly indicating
significance for the equation as a whole.
g. 1,260.28; 1,234.45

4. a. Take logarithms: ln Q = ln a + b ln L + c ln K.
b. The critical t for 120 (= 123 – 3) degrees of freedom and a 10 percent level of
significance is 1.658.
For ln â: t = 5.66 > 1.658; statistically significant; exact significance = .01 percent.

For b̂ : t = 2.20 > 1.658; statistically significant; exact significance = 2.95 percent.
For ĉ : t = 2.41 > 1.658; statistically significant; exact significance = 1.73 percent.
c. The critical F for k – 1 = 2 and n – k = 120 degrees of freedom and a 5 percent level
of significance is 3.07 (approximately). The F-ratio of 184.56 is greater than 3.07, so
the overall equation is statistically significant at the 5 percent level. Since the p-value
is less than 0.001 percent, the equation as a whole is extremely significant.
d. The model fits the data well, as 75.47 percent of the total variation in ln Q is
explained by the model. Only 24.53 percent of the variation is not explained by the
model.
e. Since ln a is estimated to be 5.5215, a is equal to eâ = e 5.5215 = 250.0.

f. Q̂ =250.0 L0.65 K 0.35 =250.0(3,000)0.65 (450)0.35 =386,094


g. Estimated elasticity of L = 0.65.
Estimated elasticity of K = 0.35.

You might also like