A Study About FDI in Bangladesh

Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

Hypothesis Testing: The Confidence Interval Approach

1. Why is the standard error of an estimator called as the precision of the estimator (How
precisely the estimator measures the true population value)?
2. Explain the concept of hypothesis testing.
3. Consider that for a hypothetical problem, 𝛽̂2 = 0.7240 𝑎𝑛𝑑 𝑠𝑒(𝛽̂2 ) = 0.07000, 𝑎𝑛𝑑 𝑛 =
15. Construct a 95% confidence interval for 𝛽2. If we postulate that Ho: 𝛽2 = 0.5 and H1:
𝜎 2 ≠ 0.5, would you reject the null hypothesis?
4. Consider that for a hypothetical problem, 𝜎̂ 2 = 0.8937 𝑎𝑛𝑑 𝑛 = 15. Construct a 99%
confidence interval for 𝜎 2 . If we postulate that Ho: 𝜎 2 = 0.6 and H1: 𝜎 2 ≠ 0.6, would
you reject the null hypothesis?

Hypothesis Testing: The Test of Significance Approach

1. Consider that for a hypothetical problem, 𝛽̂2 = 0.7240 𝑎𝑛𝑑 𝑠𝑒(𝛽̂2 ) = 0.07000, 𝑎𝑛𝑑 𝑛 =
15. If we postulate that Ho: 𝛽2 = 0.5 and H1: 𝜎 2 > 0.5, would you reject the null
hypothesis at 1% and 5% level of significance?

2. Consider that for a hypothetical problem, 𝜎̂ 2 = 0.8937 𝑎𝑛𝑑 𝑛 = 15. If we postulate that
Ho: 𝜎 2 = 0.6 and H1: 𝜎 2 ≠ 0.6, would you reject the null hypothesis at 1% and 5% level
of significance?
Hypothesis Testing: Some Practical Aspects
1. Explain the ‘2-t’ rule of thumb with an example.
2. Distinguish between type – 1 error and type – 2 error.
3. Explain the concept of exact level of significance (𝑝) and distinguish it with the level of
significance (𝛼).
4. What is the meaning of statistical significance?

5. Given the following regression result,


̂𝑖 = 0.7437 + 0.6416 𝑋𝑖
𝑌
𝑠𝑒 = (0.8355) (0.0669)
𝑇𝑆𝑆 = 8.3485 𝑅𝑆𝑆 = 0.8816
𝑟 2 = 0.8944 𝑛 = 13

Where, Y = Mean wage in thousands, X = Years of Education

a. Interpret the above regression result.


b. Find the calculated t value of education coefficient under the null hypothesis Ho:
𝛽2 = 0.
c. Would you reject the hypothesis that education has no effect whatsoever on wages at
1% level of significance? Which test do you use? And why? What is the p value of
your test statistic?
d. Set up the ANOVA table for this example and test the hypothesis that the slope
coefficient is zero. Which test do you use and why?
e. Suppose in the regression given above the 𝑟 2 value was not given to you. Could you
have obtained it from the other information given in the regression?

Analysis of Variance (ANOVA)

1. Explain ANOVA. Why do we use the F test instead of the t test to test the significancy of
the estimators?
2. Consider the following regression output:
̂𝑖 = 0.2033 + 0.6560 𝑋𝑖
𝑌
𝑠𝑒 = (0.0976) (0.1961)
2
𝑟 = 0.397 𝑅𝑆𝑆 = 0.0544 𝐸𝑆𝑆 = 0.0358

where Y = Labor Force Participation Rate (LFPR) of Women an X = Per Capita Income
Growth Rate (PGNP). The regression results were obtained from a sample of 19 cities in
the United States.

a. How do you interpret this regression?


b. Test the hypothesis: H0: β2 = 1 against H1: β2 > 1. Which test do you use? And why?
What are the underlying assumptions of the test(s) you use?
c. Suppose that Per Capita Income Growth Rate (PGNP) in a city was .05 (5 percent).
On the basis of the regression results given above, what is the mean LFPR in that
city?
d. Set up the ANOVA table for this example and test the hypothesis that the slope
coefficient is zero. Which test do you use and why?

Evaluating the Results of Regression Analysis


1. Consider the following regression output:

a. Interpret intercept and slope coefficient of the model.


̂1 𝑎𝑛𝑑 𝛽
b. Interpret the statistical significancy of the estimators (𝛽 ̂2 ).
c. If the null hypothesis is Ho: 𝛽2 = .50, what is the probability of obtaining a value of
0.4368? Did you reject or accept the null hypothesis and why?
d. What does p value represent?
e. Interpret the coefficient of determination (𝑟 2 ).
f. Interpret the F value at 5% level of significance.
g. Briefly explain the adequacy of the model.

Normality Test
1. Using the estimated residuals from the regression, we have the following Jarque-Bera
(JB) test result. What can we say about the probability distribution of the error term using
JB test?

2. What are the different steps to test the normality of OLS residuals according to Jarque-
Bera (JB) test? Consider that for a hypothetical OLS residual, Skewness = 0.456,
Kurtosis = 1.89 and n = 60. What can we say about the probability distribution of the
OLS residuals (ui)?
3. What are the different tests of normality of the OLS residuals? Explain any two of them.

You might also like