Scribd
Upload
26 views4 pages

Assignment Econometrics II

This document reports on an analysis of the relationship between per capita income and an index of political freedom/democracy using panel data from multiple countries over several years. Key findings include: - Regressing the democracy index on the log of per capita GDP found a statistically significant coefficient of 0.235, indicating that a 20% increase in per capita income is associated with a 4.7% increase in the democracy index. - Including country fixed effects in the regression reduced the estimated effect of income on democracy slightly. - Including time fixed effects and controlling for log population attenuated the relationship further, providing evidence of omitted variable bias. - Based on the analyses, the author concludes that higher per

Uploaded by

Drishti Wadhwani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
26 views4 pages

Assignment Econometrics II

This document reports on an analysis of the relationship between per capita income and an index of political freedom/democracy using panel data from multiple countries over several years. Key findings include: - Regressing the democracy index on the log of per capita GDP found a statistically significant coefficient of 0.235, indicating that a 20% increase in per capita income is associated with a 4.7% increase in the democracy index. - Including country fixed effects in the regression reduced the estimated effect of income on democracy slightly. - Including time fixed effects and controlling for log population attenuated the relationship further, providing evidence of omitted variable bias. - Based on the analyses, the author concludes that higher per

Uploaded by

Drishti Wadhwani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Riya Wadhwani

1571501

Assignment Econometrics II
- Group: 08

1. (2 points) Regarding the dataset.


(a) (0.5 points) Is the dataset a balanced panel? Explain.

No, the dataset is unbalanced because in a balanced panel all members (N) have been
observed each year (T periods), it’s necessary to form the following n=NxT. Therefore,
in this case the dataset will be unbalanced, since they don’t provide data of all countries
in all the years studied.

(b) (0.5 points) What are the minimum and maximum values of the in-
dex of political freedom/democracy (Dem ind)? What are the mean and standard
deviation of Dem ind?

The minimum value of index Dem_ind is 0.0, its maximum value is 1.0. And the mean of
the index is 0,49907 with its standard deviation being 0,37134.

(c) (0.5 points) What is the value of Dem ind for the United States for
the year 2000? Averaged over all the years in the dataset?

The value of Dem_ind is 1.0 for the year 2000 in the United States and averaged over all
years is 0,9856.

(d) (0.5 points) What is the value of Dem ind for Libya for the year
2000? Averaged over all the years in the dataset?

The value of Dem_ind is 0.0 for the year 2000 in Libya and averaged for all years is
0,10925.

2. (3 points) Regress Dem ind on the logarithm of per capita income (Log GDPPC ).
Use the robust standard errors by Arellano.
(a) (1 points) How large is the estimated coefficient on Log GDPPC ? Is the
coefficient statistically significant? Explain.

Yes, the coefficient will be considered significant since its p-value is way lower than
0,0001. Significant in p=1%, 5%, 10%. With the coefficient on Log_GDPPC being
0,235673.
Riya Wadhwani
1571501

(b) (1 points) If per capita income in a country increases by 20%, by how much is
Dem ind predicted to increase? What is the 95% confidence interval for the
prediction?

If per capita income is increased by 20%, then the Dem_ind will rise by 0.235673*0.2=
4,71346%. The 95% confidence interval is {0.212283, 0.259063}.

(c) (1 points) Why is it important to use robust standard errors for this
regression? Do the results change if you do not use robust standard
errors?

Robust standard errors are used to account for heteroscedasticity in the regression. If
observations in a dataset are related the standard error is smaller than the OLS standard
error. The smaller the confidence interval, more misleading p-value and larger T-statistic.

3. (5 points) Fixed Effects model. Use the robust standard errors by Arellano
for all the regressions.

(a) (1 points) Suggest a variable that varies across countries but plau-
sibility varies little, or not at all, over time and that could cause omitted variable
bias in the regression in (2). Estimate the regression in (2) allowing for country
fixed effects. How do your answers for (2)(a) and (2)(b) change?
The variable that could lead to omitted variable bias is the average years of education for
adults. With the fixed effect, we get the coefficient is 0.0837410, which is significant
because the p-value = 0.0088 when the log_gdp increases by 20% , the dem_ind will
increase by 0.0167.

(b) (1 points) Exclude the data for Azerbaijan and re-run the regression. Do results
change? Why or why not?
Riya Wadhwani
1571501

Post removal of the data for Azerbaijan, we re-run the regression and we see that the
result doesn’t change. Since the data of Azerbaijan influences only the intercept of this
country A(azerbaijan), the slope will remain unchanged (coefficient estimated).

(c) (1 points) Suggest a variable that varies over time but plausibility varies little, or
not at all, across countries and that could cause omitted variable bias in the
regression in (2). Estimate the regression in (2) allowing for time and country fixed
effects. How do your answers for (2)(a) and (2)(b) change?

I will suggest the variable which varies over time, but plausibly varies over the country is
log_population. We can observe the changes in the result of 2a and 2b due to making the
time and country fixed.

(d) (1 points) There are additional demographic controls in the dataset. Should
these variables be included in the regression? Provide a detailed analysis
justifying your answer. If so, how do the results change when they are included?
Riya Wadhwani
1571501

By restricting the data set in the year 2000 and making the regression, we observe that
the log-population has a negative effect on the democracy degree. And that the average
years of education is not significant to democracy and policy freedom.

(e) (1 points) Based on your analysis, what conclusion do you draw about
the effects of income on democracy?
Thanks to the observed data we can conclude that the effect of income of a country ( log_GDP)
affects the democracy and policy freedom in that country positively. Even so, such an effect is
small. One could say it doesn’t affect it since the p-value is too high.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy