AEA 309- ECONOMETRICS.

ASSIGNMENT 1.

1.

a] Required to formulate a question of interest for the prediction, as an expert model.

Question of interest: What is the effect of participating in SUA-AIC incubation training on AEA
students’ post-graduation hourly wages?

b] Formulate an economic model. Is this a formal economic model? Justify your answer

Economic model: Wage=f (incubation training, human capital, education)

Where: Wage represents hourly earnings after graduation.

Incubation represents participation in SUA-AIC program.

Human capital represents education level.

 This economic model is not formal since it does not consist mathematical questions to
describe the relationship between participation in SUA-AIC incubation training and hourly
wages to students after graduating.

c] Formulate hypothesis for the unknown parameters.

 Increase in SUA-AIC participation will increase post-graduation wages.

2.With examples discuss the following types of data sets.

d]Formulate\write an econometric model to test the hypothesis.

 W=β0+β1 training +β2 human capital+β3education+µ.

Where w
W-Wage, µ-disturbance, β0, β1 and β2 are parameters to be estimated.

e] What type of data will you use in the analysis and why

 I will use panel data because it will help me to track individuals over time that is before and
after training and the effect of trainings on the wages.

f] Comment on the causality analysis of the model.

 Establishing causality can come with challenges because students who choose to participate
in training may be systematically different and also there are unobservable factors that affect
both trainings and wages.

a] Cross sectional data set. This is the type of data set that consists sample of individuals, households,
firms, cities, states, countries or variety of other units taken at a given point in time. Sometimes the data
on all units do not correspond precisely the same time period.
  Cross sectional data are assumed to be obtained by random sampling from the underlying
population, though it is not appropriate as an assumption for analyzing sectional data
example when the sample units are large relative to the population, particularly
geographical units.
 Cross sectional data are widely used in economics and other social sciences. Example of
cross-sectional data include: Data collected during a national census which provides
population characteristics data such as income, age and education level, data collected on
working population to know their wages and education and experience.

b] Time series data set. This is the type of data set that consists of observations on variable or several
variables over time.

 A key feature of time series data that makes them more difficult to analyze than cross-
sectional data is that economic observations can rarely, if ever, be assumed to be
independent across time.
 Another feature of time series data that can require special attention is the data frequency
at which the data are collected.

Examples of time series data include data on stock prices, money supply, consumer price index, gross
domestic product, annual homicide rates, and automobile sales figures.

c] Pooled cross sectional data set. This is the type of data set that have both cross-sectional and time
series features.

 Pooling cross sections from different years is often an effective way of analyzing the effects
of various policies example a new government policy over a time and also analyze the trends
in education, health issues and households’ income.
 A pooled cross section is analyzed much like a standard cross section, except that we often
need to account for secular differences in the variables across the time.
 Examples of pooled sectional data set include data on a national education assessment
which tests different group of students in various years example 2015 and 2016, surveys on
health behaviors using different participants each year.

d] Panel data set. This is the type of data set that consists of a time series for each cross-sectional
member in the data set.

 The key feature of panel data that distinguishes them from a pooled cross section is that the
same cross-sectional units such as individuals, households and firms are followed over a
given time period.
 Panel data set allows us to control for certain unobserved characteristics of individuals, firms
and other units by having multiple observations on the same units.
 Another significance of panel data set is, it allows us to study the importance of lags in
behavior or the result of decision making. This information can be significant because many
economic policies can be expected to have an impact only after some time has passed.
 It is difficult to obtain panel data than pooled sectional data set because panel data requires
replication of the same units over time.
  Examples of panel data include data on consumer purchasing behaviors over ten years and
data on households’ income and employment status example from 2012 to 2017.

3. Briefly discuss the following key terms in econometrics

a] Economic model: Is the model consisting of mathematical questions to describe various

relationships.

 Example of an economic model is Cobb-Douglas production model which describe the

relationship between the combination of two or more inputs example labor and capital and
the total output produced.

b] Empirical analysis: Is the analysis that uses data to test a theory or to estimate a relationship.

 It involves five steps which are, formulating the question of interest, formulating econometric
model, formulating hypothesis on unknown parameters, data collection and hypothesis
testing and interpreting the results.

c]Econometric model: Is the mathematical representation of economic relationships that incorporates

statistical methods to estimate and test hypotheses of these relationships. Econometric model helps to
deal with variables that cannot reasonably be observed example a wage that a worker can get out of the
employment it can be a wage from crimes.

d]Causal effect: Is the impact that one variable has on another variable example education has an
impact on productivity of a worker.

e] Ceteris peribus: It means other relevant factors being equal.

f] Data frequency: refers to the number of times a particular value occurs within a data set. In
economics, the most common frequencies are daily, weekly, monthly, quarterly and annually.

g] Experimental data: Are data which are collected in laboratory environments in the natural sciences
but they are more difficult to obtain in the social sciences.

h] Non experimental data: Are data which are not accumulated through controlled experiments on
individuals, firms or segments of the economy. They are sometimes called observational data or
retrospective data.

i]Observational data: Are data which are collected through direct observation of subjects in their
natural setting. Observation data are sometimes called non experimental data. Example of observation
data is data collected from market and social science.

j] Random sampling: Is the method used to select a subset of individuals from a larger population, this
method gives each member an equal chance of being selected in the subset.

k] Samplin frame: Is a list that contains all the members of a population from which a sample is drawn.

4.Suppose you are asked to find a relationship between weekly hour spent studying and weekly hour
spent working. Does it make sense to characterize the problem as inferring whether study causes work
or work causes study? Explain.
 Characterizing the relationship between weekly hours spent studying and weekly hours spent
working as one causing the other that is, study causes work or work causes study is problematic
because: -

 The correlation between two variables example more study hours are associated with more
work hours, does not imply that one causes the other, there can be other factors influencing
both for example financial needs.
 There can be a direct relationship between study hours and work hours that is more study
hours could lead to work more hours to support educational expenses while more work
hours might limit the time available for studying.
 Other variables can influence study hours and working hours, example financial situation of
a person or academic pressure can affect

5.Sometimes the government reduces taxes in an attempt to spur economic growth. Suppose you are
hired by the ministry of finance to estimate the effect of corporate tax rates on the growth in per capita
gross domestic product (GDP).

a\ What kind of data would you need to collect to undertake a statistical analysis.

 Kind of data that I would need to collect is time series data on historical and current
corporate tax rates, data on per capita gross domestic product ideally over the same
periods of time with the corporate tax rates and data on other economic factors that may
affect Gross Domestic Product such as unemployment rates, investment levels and
inflation rates.
 Time series data will help to analyze the changes in Gross Domestic Product of a country
with response to changes in corporate taxes over time.

b\Is it feasible to do a controlled experiment? Why?

It is not feasible to do a controlled experiment for this analysis because: -

 Tax rate changes affect a number of people so it is impossible to isolate variables in a controlled
way.
 The Gross Domestic Product is also influenced by other factors other than the corporate tax
rates making it difficult to control all the relevant variables in an experiment setting.
 ed environment would be required so as to control external factors that influence Gross
Domestic Product example international trade and economic policies.

d\Is a correlation between GDP growth and tax rates likely to be convincing? Explain

correlation between GDP growth and tax rates may not be highly convincing because of the following: -

 Correlation does not mean causation in a fact that just because two variables are correlated
does not mean one causes the other, both GDP growth and corporate tax rates can be
influenced by other factors
 The exclusion of relevant variables can mislead the results for example GDP growth might be
driven by other relevant factors such as technological innovation rather than tax rates.