For the mid-term assignment, you are tasked with undertaking a country case study, using the data visualization, data summary, and univariate and bivariate data analysis techniques covered in class.
To complete this assignment, you are requested to identify a country of interest, and undertake the following analyses:
Time Series Analysis:
For your country of interest, find, download and properly format a time-series dataset with at least four variables and at least 15 years of data [Note: it is ok if some of your variables are missing observations in some years].
Generate a table of descriptive statistics for this dataset, as well as a correlation matrix.
Based on your descriptive statistics and correlation matrix, come up with three interesting ways to visualize (i.e. plot) your time-series data. In each case, make sure you are demonstrating something essential about the distribution of and/or relationship between one or several variables in your dataset.
In 750 words or less, describe your time-series dataset, including:
Where did you obtain your data, and what challenges you have in formatting it?
What do you observe in your table of descriptive statistics, and what the correlation matrix tells you about the relationships in your data? E.g. Are there any concerns with the distribution of specific variables? Which variables are more or less strongly related to each other? What aspects of your dataset would you like to explore further?
Why did you choose the three particular plots that you have provided, and what do they convey about your data? Briefly describe what each plot is intended to illustrate, pointing out key features about the dataset that they are intended to visualize.
Cross-Section Analysis:
For your country of interest, now select a group of comparator countries and find, download and properly format a cross-section dataset with at least four variables for a particular year of your choosing. Ideally, you will select a group of at least 20 countries. Again, it is okay if some of your countries are missing observations for some of your variables. Possible suggestions for country groupings might include:
Selecting countries in the same region or on the same continent;
Selecting according to the World Bank’s Region, Income, or Lending Groups, or utilizing the UN Development Programme’s four levels of human development as defined in their 2020 Human Development Report;
Selecting by governance type (e.g. according to the Polity IV index, or by membership in groups such as the OECD or the EU;
or use some other clearly defined country grouping.
Generate a table of descriptive statistics for this dataset, as well as a correlation matrix.
Based on your descriptive statistics and correlation matrix, come up with three interesting ways to visualize (i.e. plot) your cross-section data. In each case, make sure you are demonstrating something essential about the distribution of and/or relationship between one or several variables in your dataset.
In 750 words or less, describe your cross-section dataset, including:
Where do you obtain your data, and what are any challenges you have in formatting it?
What do you observe in your table of descriptive statistics, and what the correlation matrix tells you about the relationships in your data? E.g. Are there any concerns with the distribution of specific variables? Which variables are more or less strongly related to each other? What aspects of your dataset would you like to explore further?
Why did you choose the three particular plots that you have provided, and what do they convey about your data? Briefly describe what each plot is intended to illustrate, pointing out key features about the dataset that they are intended to visualize.
To Submit Your Report: You are asked to upload three separate files on the Brightspace page for the Mid-term Assignment. These should include:
An Excel workbook for your time-series dataset. This will include a tab with your formatted dataset, separate tabs/sheets your table of descriptive statistics, your correlation matrix, and each of your three plots (your time-series workbook should therefore have 6 tabs total).
An Excel workbook for your cross-section dataset. This will include a tab with your formatted dataset, and separate tabs/sheets for your table of descriptive statistics, your correlation matrix, and each of your three plots (your cross-section workbook should therefore have 6 tabs total).
A Word (.doc or .docx) or PDF file with your reports describing your observations for each dataset.
Feel free to do your analyses in other languages such as SPSS, R or Stata. Just make sure to submit your codes.
For the mid-term assignment, you are tasked with undertaking a country case stud
By admin