QnQ Data Analysis for HSF Fellows

Zahid Asghar, Professor, School of Economics, QAU

03-08-2023

Mixed Methods Research

Precise research question and research design is the key. A wrong question will not have right or wrong answer.

• What is mixed methods research?

• Qualitative data analysis

• Quantitative data analysis

• How these two complement each other?

• • Taxonomy of data

Sources

• Pakistan Election data sets
• Colin Cookman Paper on Pakistan elections
• R for political science
• Steven V. Miller
• Learn qualitative data interactively World Politics Data Lab
• NTI Nuclear Security Index
• Google trends
• APIs for social scientists

Softwares

• Nvivo for qualitative data , easy to learn

• Voyant tools

• MsExcel , basic daily tool

• SPSS, STATA for quantitative data analysis

• R : open community software, have a relatively steep learning curve but awesome and most widely used by political scientists both for qualitative and quantitative analysis

• Python: open community software, very comprehensive ranging from computer scientists to engineering

• R or Python are highly recommend for long term

Why my choice is R

R Markdown is a file format for making dynamic documents with R. However, you need to call it from R to use it, and it was depedentn on knitr. If you’re a Python user, it means you need to install R to use R Markdown. Quarto is a tool that you can call from the terminal or command line, and is independent from the computational systems. Quarto supports knitr, and can support others. So, you can think of Quarto as the next generation R Markdown that is fundamentally multilanguage and multiengine.

What is mixed-methods research?

Mixed methods research

offers a process of discovery through rigorous qualitative analysis,

and then empirically investigate it through quantitative analysis.

It is often used misleadingly and

used as a jargon instead of utilising it.

King, Keohane and Verba (KKV) in their classic book, Designing Social Inquiry, argue that both qualitative and quantitative research should abide by the same standards of logical inference. This is true that qualitative research should be conducted rigorously but valid for inference or not is contestable. Yuen Yuen Ang, author of China’s Gilded Age, pointed out that “before one jumps to causal arguments, one must discover an interesting problem and/ or possible solutions. For example, in cancer studies, medical scientists must first have discovered the ailment of cancer, described its manifestations, and speculated about its possible causes, before future generations of scientists could test a particular cause of cancer using statistical data and regressions. In social sciences,discovery, through observation and immersion is indispensable. Without rigorous analysis , discovery of the issue is not possible and if the issue is not well understood, how can it be tested? But unfortunately, most of the qualitative research is descriptive and there is no connection between the two approaches.” ` As per my understanding if someone is using : DISCOVERY through rigorous qualitative research and then testing using a quantitative approach. Unfortunately, most of the research studies simply mention some interviews and then there is neither rigorous analysis nor any problem identification.”

How many Russian soldiers died in Ukraine-Russia war?

• Russia reports around 6000

• If you challenge it, how will you proceed

• Interviews, FGD for some information

Once some clues of under-reporting through rigrous exploration, how will you assess the actual number?

Data shows what Moscow hides

for details click her

• Visit cemeteries for deaths under 50 yrs

• Adjustment for covid deaths

• Get data on new inheritance accounts opened

• Started with interviewing, discussion, anecdotes, personal interviews and discovered underreporting by Russia, collected quantitative data and analyzed whether its really the case. This is one of the objectives of mixed-method research approach .

Qualitative Data Analysis

Industry Application of Text Analysis

• Google trends

• Text Analysis

• Sentimental Analysis

• Taxonomy of data

• Metadata

Data formats

• [.csv, .txt, .dta , .sav, .xlsx, .RData, …]{style=“color:red;”“}

• Reading and saving/writing each …

• parameterized reports cricket_batting data analytics reposity

• Toshakhana data cleaning

• tidy vs untidy data

Inspecting data frames

Size:

• dim(df) - returns a vector with the number of rows as the first element, and the number of columns as the second element (the dimensions of the object)

• nrow(df) - returns the number of rows

• ncol(df) - returns the number of columns

Content:

• head(df) - shows the first 6 rows

• tail(df) - shows the last 6 rows

Names:

• names(df) - returns the column names (synonym of colnames() for data.frame objects)

Summary:

• str(df) - structure of the object and information about the class, length and content of each column

• summary(df) - summary statistics for each column

• glimpse(df) - returns the number of columns and rows of the tibble, the names and class of each column, and previews as many values will fit on the screen.

80% data dealing with these commands

We’re going to learn some of the most common dplyr functions:

• select(): subset columns

• filter(): subset rows on conditions

• mutate(): create new columns by using information from other columns

• group_by() and summarize(): create summary statistics on grouped data

• arrange(): sort results

• count(): count discrete values

Numbers and numbers which matter are different.

Time-line data

Finance Ministers Approach

Economic Policy uncertainty

Economic Policy Uncertainty Index