The relationship between firm exports, size, productivity and skill/capital intensity
Firm-level exports are potentially affected by a number of factors including the size of a firm, its productivity as well as the skill and capital intensity of its production technology.
The objective of this project is to establish whether size, productivity, skill intensity and capital intensity are determinants of firm exports in a cross-section of firms.
The data below contains information, covering a sample of 60 firms, on firm exports (Exports), a commonly used measure of firm size and in particular the number of employees of the firm (Empl), a measure of the productivity of the firm (Prod), as well as a measure of the skill intensity (Skill) and capital intensity (Capit) of the firm. Exports are measured in million pounds while productivity is measured as the ratio of the value of sales to the value of inputs used. Skill intensity is measured as the average number of years of schooling of the employees while capital intensity is measured as the ratio between the capital stock of a firm in million pounds and the number of employees.
1. Describe the data, using summary statistics and graphs, as appropriate. <check the example project for what the appropriate graph is>
1. Calculate the pair-wise correlation coefficients between Exports and each of the other variables. Test the statistical significance of each correlation coefficient. (Have to clearly spell out what is a null and alternative hypothesis, what is the test statistic you’re using, how it is distributed, what is the critical value and what is the value of statistic).
1. Consider the two variables Skill and Capit. Compute the pairwise correlation of the two variables and test the significance of the correlation coefficient.
1. Consider again the two variables Skill and Capit and test the null hypothesis that the two variables have equal variance. <look at the Lecture 4/ Lecture 5 material for this> (Again, have to clearly spell out what is a null and alternative hypothesis, what is the test statistic you’re using, how it is distributed, what is the critical value and what is the value of statistic).
1. Estimate a regression model of the form:
Exportsi =α + β1Empli + β2Prodi + β3Skilli + β4Capiti +ui
where the i subscript corresponds to firm i. Provide regression table and interpret the coefficients that you obtain, and comment on their economic and statistical significance. Statistical significance with a T test. To say whether it is big or small, use elasticities.
1. Interpret the R2 statistic from the regression and test whether it is statistically significant. (Again, the same steps, have to clearly spell out what is a null and alternative hypothesis, what is the test statistic you’re using, how it is distributed, what is the critical value and what is the value of statistic).
1. Re-estimate the model excluding the Capit variable and comment on any changes to the results and goodness of fit:
Exportsi =α + β1Empli + β2Prodi + β3Skilli +ui
1. Estimate a partial log-version of the regression model of the form:
Ln(Exports)i =α + β1Ln(Empl)i + β2Ln(Prod)i + β3Skilli + β4Capiti +ui
where the i subscript corresponds to firm i and Ln is the natural logarithm. Interpret the coefficients that you obtain, and comment on their economic and statistical significance. Compare this model with the one estimated in point 6.
1. What conclusions do you draw from your analysis?
