Using Data - Using Data Marie Prole “Can the workplace...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Using Data Marie Prole “Can the workplace explain can. Gender pay differences?”, Canadian public policy, May 2002, Supplement How to access:- library- data bases (JSTOR) Most research in the social sciences is trying to answer some kind of questions that interest people. - marie drolet explores how industries matter Research is typically either explanation or prediction although the boundary between them is not always totally clear. “An explanation is something that provides reasons or interpretations for something else.” We usually start with an informed guess (or hypothesis) which gives the presumed relationship between the variables. The presumed relationship usually comes from economic theory. We can then test the hypothesis by collecting and analyzing data. A prediction consists of a forecast of the outcome. It does not necessarily contain any reasons for the relationship and usually economists require an explanation as well as a prediction. When we deal with data, there are 2 types: Quantitative -- data to which number values can be assigned such as income or GDP or years of education Qualitative – data to which no numbers can be assigned such as gender or race or nationality When dealing with data we should remember that: “Every statistic must be created, and the process of creation always involves choices that affect the resulting number…No statistic is perfect, but some are less imperfect than others” Joel Best, Dammed Lies and Statistics In economics, qualitative variables usually come in 2 types: 1. Dummy variables – this is used when we believe that some factor like race or gender has a discrete effect. Usually a dummy variable is constructed to have a value of 0 or 1. For example, if we were examining the wage gap between men and women, we might assign a 0 if the worker was male and 1 if the worker was female. In this case, if gender matters, then the dummy variable would have a significant negative coefficient. Dummy variables can also be used for multiple categories such as a range of education: high school dropout, high school graduate, some college, college graduate and post-graduate. The technique is the same: the drop out category will be assigned one and others a zero, then the high school grad 1 and the others zero, and so on. It is important that we always omit one category otherwise the regression will exhibit perfect collinearity – a problem that will be discussed later. (So for example we don’t include a dummy variable for both men and women)....
View Full Document

This note was uploaded on 02/15/2011 for the course ECON 451 taught by Professor Sinclair during the Winter '11 term at Wilfred Laurier University .

Page1 / 9

Using Data - Using Data Marie Prole “Can the workplace...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online