Training programme (60 min)

This programme lets you learn the main MacroLens functions on your own in one hour. Each module consists of a short explanation with a link to the user guide and a practical exercise. You only need a MacroLens account for the exercises; the Excel module is optional.

If you have questions during the training, contact support.

Module 1. Signing in and the environment (5 min)

Read: Getting started.

Exercise 1.

1. Sign in to MacroLens (password and authenticator app code).
2. Switch the interface language to EN and back to LT.
3. Look through the items of the left-hand menu. Open Help & training and find this page with the help search (type “training”).
4. (Optional) Install MacroLens as an app on your computer.

Module 2. Search, filters and the series page (10 min)

Read: Searching and filtering, Series page.

Exercise 2.

1. Find Lithuania's quarterly gross domestic product at constant prices: type gross domestic product, choose the region Lithuania, the frequency Quarterly and the source Eurostat.
2. Repeat the search with the source State Data Agency. Compare the titles and periods.
3. Open one of the series. Find: the unit, whether the data is seasonally adjusted, the source publication date, when the series changed in MacroLens, and the series key.
4. Try a phrase search: "harmonised index of consumer prices" and the filter Region → euro-area members.

Check yourself: what is the difference between the country group “euro-area members” and the region “euro area”? (Answer: the group shows the series of the individual members, the region is one aggregated series for the euro area as a whole.)

Module 3. First analysis: operations and chart (15 min)

Read: Analyses, Operations, Charts, Tables.

Exercise 3 — inflation in Lithuania and the euro area.

1. Find the harmonised index of consumer prices for Lithuania and the euro area (monthly, Eurostat; search harmonised index of consumer prices and choose the index level, not the rate of change).
2. Add both series to a new analysis.
3. Apply the operation Year-on-year change, % (yoy) to each series.
4. In the chart, set the displayed period to start at 2015-01, enter the title “Annual inflation, %” and move the legend to the bottom.
5. Switch to the table view: show 1 decimal and turn on “Newest first”.

Exercise 4 — GDP growth and trend.

1. Add Lithuania's quarterly GDP at constant prices (seasonally adjusted) to a new analysis.
2. Add the same series a second time and apply Trend → Hodrick–Prescott (λ = 1600).
3. Add a third copy and apply Cycle → HP with the result in per cent (output = pct). Move this series to the right axis and change its type to column.
4. Add the operation Frequency conversion → annual (sum) to the first series and watch how the result changes.

Check yourself: why should you choose the sum rather than the average when calculating annual GDP from quarterly data? (Answer: GDP is a flow — annual GDP equals the sum of the quarters.)

Module 4. Formulas and value edits (10 min)

Read: Formula language, Editing values.

Exercise 5 — inflation differential. In the analysis of exercise 3, add a formula series s1 - s2 (use the names from your analysis) and label it “Inflation differential, pp”.

Exercise 6 — a forecast.

1. In the analysis of exercise 4, choose the action Edit values for the GDP series.
2. Add future values for the next four quarters (e.g. each quarter 0.5 % higher than the previous one).
3. Apply Year-on-year change, % to the series and check that the change is also calculated for the forecast periods.
4. Save the series (Save as my series) with the code gdp_forecast.

Check yourself: does editing values in an analysis change the database data? (Answer: no — the edits apply only to your analysis and user series.)

Module 5. Statistical analysis (10 min)

Read: Statistical analysis.

Exercise 7.

1. In the analysis of exercise 3, open the Statistics tab and run a correlation analysis between annual inflation in Lithuania and in the euro area. Note the correlation coefficient and the p-value.
2. Run descriptive statistics: compare the standard deviations of both series. Which inflation fluctuated more?
3. Run a simple linear regression: dependent variable — Lithuanian inflation, explanatory variable — euro-area inflation. Read the coefficient, R² and the Durbin–Watson statistic.
4. Run a unit root test (ADF) on the level of Lithuanian GDP and on its year-on-year change. Compare the conclusions.

Check yourself: what does an ADF p-value of 0.01 mean? (Answer: the unit-root hypothesis is rejected — the series is stationary.)

Module 6. Saving, a report and export (5 min)

Read: Library, Reports and presentations.

Exercise 8.

1. Save the analysis of exercise 3 as a chart named “Inflation LT and EA” and create a folder “Training” in the library.
2. Create a report: a heading, a short text and the chart “Inflation LT and EA”. Download it as DOCX.
3. Download the chart as PNG and the table as XLSX. Print (or save as PDF) the table view.

Module 7. Excel and support (5 min, optional)

Read: Excel add-in and Power Query, Support and service levels.

Exercise 9.

1. On the My account page create a personal access token named “Training”.
2. If the Excel add-in is installed: sign in with your MacroLens account (or the token), find the Lithuanian unemployment rate, insert it into a workbook and refresh it. If the add-in is not installed, create a Power Query query from the link on the Excel page.
3. When finished, revoke the training token if you no longer need it.
4. Open the support page and see how to report a problem or send a data request.

What next?

• Print the quick-reference card.
• Browse the function reference — it describes every operation with its parameters.
• Questions? Write to us.