ETF2100 Chap.1 Statistical Review, Data and Econometric Questions

Statistical Review, Data and Econometric Questions

Establish the analytical object

The overview begins with empirical economic analysis because a calculation is useful only after the target is fixed. An economic model names the relationship of interest; an econometric model turns that relationship into variables and an error term that can be confronted with data.

Experimental data may support a clean intervention contrast, while non-experimental data require much more care about selection and omitted causes. Descriptive statistics then reveal centre, dispersion and linear association, but they do not on their own identify a policy or treatment effect.

The chapter objective is to translate an economic question into a population, variables, comparison and estimable relationship.

Begin by defining population at the scale used in the question. Record whom or what population describes, its period or operating state, and evidence that distinguishes population from correlation. Without that discipline, population can quietly change meaning between the opening claim and the final recommendation.

Next, make sample do explanatory work.

State the direction of sample, the process it carries and the condition that keeps its link with population credible. A useful sample note does not merely say that the relationship matters. It identifies which observation establishes population, which observation tests sample and which value of correlation would force a different account.

Use correlation as the chapter's discriminating lens.

Compare at least two feasible cases and decide whether correlation strengthens, narrows or reverses the preferred result. If it cannot alter any conclusion, it is functioning as decoration. Attach the comparison to the same unit, population or system boundary used for population and sample.

Trace the operative relationship

A complete application of population has an actor, evidence, relationship and decision.

The actor has responsibility; evidence identifies the population state; sample explains why action may work; and correlation supplies a review signal. This population–sample–correlation structure makes ETF2100 reasoning auditable without turning one definition into a universal rule.

Suppose a labour analyst samples 100 workers to study training and wages. The population must specify workers, labour market and period.

Wage is a response; education, experience and training are candidate explanatory variables. The source-supported wage model places the unobserved influences in an error term. Before estimation, inspect missingness, units, range and how training was selected. A positive wage–training correlation is a description.

It becomes causal only under a design or set of assumptions that blocks alternative paths such as motivation, employer selection or prior skill.

Now change one condition: Replace workers with firms and wage with productivity. Rebuild the population, unit, explanatory variables and unobserved influences before reusing any interpretation. Predict the direction of the result before consulting an example.

Explain whether the change affects the definition of population, the mechanism carried by sample, the comparison represented by correlation, or only the confidence attached to the conclusion.

Keep the controlling limit visible: Correlation can be exactly zero when a nonlinear relationship remains, and a strong correlation can be produced by a common cause. This correlation limit is not ceremonial.

It specifies the observation, design feature or operating condition that separates a careful use of population from a claim that outruns sample evidence.

Use the boundary as a test

For retrieval, close the explanation and reconstruct population, sample and correlation in three different sentences: a definition, a relationship and a counter-case. Then attach one concrete ETF2100 example to each.

Reopen the correlation material only to correct the first missing population–sample link; copying everything hides which analytical role failed.

For written or oral assessment, put the correlation conclusion after the reasoning. Start with the requested decision, use population to establish the object and trace sample before allowing correlation to challenge the preferred position.

Report correlation at the scale earned by population evidence, preserving uncertainty and implementation constraints around sample.

Create an error log specific to population. Record the triggering fact, mistaken population inference, repaired relationship involving sample, and evidence from correlation that distinguishes the two.

Repeat the repaired sample move on a different correlation case so feedback becomes a transferable diagnostic for population.

A strong final check asks four questions. Is population defined consistently? Does sample explain a process rather than repeat the outcome? Can correlation genuinely contradict the preferred answer?

Does the last sentence remain inside this limit: Correlation can be exactly zero when a nonlinear relationship remains, and a strong correlation can be produced by a common cause. If any population–sample–correlation answer is no, revise that defective relationship rather than adding more description.

What this chapter covers

• 01

  population

• 02

  sample

• 03

  correlation

• 04

  translate an economic question into a population, variables, comparison and estimable relationship

• 05

  Correlation can be exactly zero when a nonlinear relationship remains, and a strong correlation can be produced by a common cause.

Changed population case

Key terms

population

The well-defined group about which the analysis seeks to learn.

sample

The observed units used to estimate a feature of that population.

correlation

A standardised measure of linear co-movement, bounded between minus one and one.

Statistical Review, Data and Econometric Questions FAQ

Exam move

Retrieve population, sample and correlation; explain their relationship; apply them to the changed case; then test the result against the stated boundary.

Working through Statistical Review, Data and Econometric Questions in ETF2100? Sia is AskSia’s AI Econometrics tutor — ask any ETF2100 Statistical Review, Data and Econometric Questions question and get a clear, step-by-step explanation grounded in how ETF2100 is taught and assessed. Read this chapter free, then take your hardest questions to Sia.