Econometrics is the use of statistical methods to answer economic questions by using analysis of
economic data.
It tests/attempts to distinguish between economic theories and allows for evaluation of both
government and business policy
Data
Data are a set of measurements taken on an individual unit, stored and presented in a dataset
Categorical Data
Data that are recorded as belonging to one or more groups
Can be recorded as numbers but these numbers have no inherent meaning
E.g. Gender, religion, Birthplace
Panel Data
Data on different entities(e.g. individuals) with each entity observed at multiple points in time
Mixture of cross section and time series data
E.g. Earnings of USYD graduates over time, life expectancy by country over time
Univariate data
Single data series containing ovservations of only one variable
E.g. Earnings of uni graduates in 2012
Bivariate Data
Data composed of two potentially related data series
E.g. Education and earnings of individuals, inflation and unemployment rates over time
Multivariate Data
Data composed of three or more potentially related data series
Interested in how x relates to k
E.g. Education,experience,gender and income for a cross section of individuals
Data Summary
Typically use a combination of visual represeentations of the data and statistics
Variety of tables, graphs and charts (scatterpplots, histograms,maps)
Use statistics to measure characteristics of
Single variable (mean, median, variance)
Relationships between multiple variables (covariance, correlation, liner regression)
Our choice of sumarry statistics and graphs is dependent on both the type of data available and
what the researcher is interested in
Statistical Inference
Basic idea of statistical inference is to draw conclusions about a relationship we cannot observe
Typically we cannot reach definitive conclusions because we only observe a sample rather than
the population
Statistical Inference
Using what we know about the sample and about the probabilities of reaching certain
conclusions to make a statement about the probable characteristics ofvariables and likely
relationships between them at the population level
Interpretation :
Statistics and Data Analysis
Statistics essentiall is using data to figure out as much as we can about a parameter we cannot
observe
Our statistical model describes a population we cannot observe, as describing whole population
is tedious
e.g. Education and salary of every person on earth
We then assume that our dataset is a sample taken from the population
From this dataset we calculate an estimater for the true but unknown parameter
e.g. Sample correlation between education and salary
We then conduct inference, where the estimator is not equal to the parameter but allows us to
say something about how close or far off it is likely to be, where CI and hypothesis testing works.
Measure of central tendency describes the center of the distribution in the data
Quartiles, deciles, percentiles : Pth percentile is the value for which p percent of the observed
Measures of