Dashboard Week – Day 2: Wage vs. Inflation

5 min read

 

As Data Schoolers, towards the end of our 16-week intensive training, we all take on an ambitious challenge — creating one dashboard, one blog and one presentation on a fresh dataset every day for a week! Today marks the second day of this challenge. In this blog, I would like to share my approach to today’s challenge and showcase my finished dashboard.

You can also find all my dashboard week blogs here:

Day 1: Global Power Plants

Day 2: Wages vs. Inflation

Day 3: Star Wars

Day 4: 2021 Australian Census

Day 5: AFL Data

 

 

The Data

Today’s dataset is the Australian CPI and WPI data from the Australian Bureau of Statistics. The data and its documentation can be found here.

 

 

The Plan

Step 1: Data Understanding

It always pays off to start the analytical process by understanding our data. At this stage, it is often not necessary to develop a comprehensive knowledge of the data, but just enough so that you can start exploring relevant business questions and hypotheses. 

For our Australian CPI and WPI, I have noticed that:

1. The Wage Price Index (Table 6345.02b) data is of quarterly frequency, and is at the state level (e.g. each row represents a year-quarter and state level of granularity). The data contains quarterly index, percentage change from previous quarter, and percentage change from corresponding quarter of the previous quarter. According to the documentation, the quarterly index should not be used to compare across states, and should only be compared over time.
2. The CPI (Table 6401.09) data is of quarterly frequency, and is at the capital city level (e.g. each row represents a year-quarter and capital city level of granularity). The data contains only percentage change from the previous quarter. 

 

Step 2: Business Understanding

In this part, we try to understand why we are performing our analytics project. This is also where we begin to pose hypotheses or goals. It is often argued by certain economists and policy makers that wages should not be allowed to rise in response to inflation, even if people’s standard of living suffers from reduced buying power. My aim is to explore this hypothesis and more specifically, investigate whether or not wage growth is associated with or even cause inflation.

 

Step 3: Planning

There are often two kinds of relationships between variables, correlation and causal relationships. Correlation is when two variables tend to move together, and causal relationships is when one variable tends to cause or determines the other variable. In order to investigate our hypothesis of whether or not wage growth is associated with or even cause inflation, we need to consider both of these relationships.

Correlation is relatively straightforward to explore. Some common chart types for analysing correlation include scatterplots, density plots and heatmaps. Causality is often much harder to establish, one common approach is temporal relation, for example if A happens before B and B then happens, then it is likely that A caused B rather than the other way around. In order to establish temporal relation we will need to perform some time period or table calculations in Tableau. It would also be useful to create parameters that allow us to adjust the time periods for more flexible comparison.

 

Step 4: Data Cleaning and Pre-processing

I’ve used Alteryx to clean the dataset. More specifically, I:

1. Cleaned up the irrelevant headers.
2. Transposed fields into from wide to long.
3. Performed additional cleaning steps to make the data easier to work with in Tableau.

 

 

The Dashboard

Below is a screenshot of my finished dashboard. The dashboard seeks to understand Australia’s wage/inflation relationship using three approaches:

1. Lagged Time Period Approach: CPI and WPI are compared based on the previous Nth period, where N can be chosen using a Tableau parameter. This approach helps us address causality using temporal relations.
2. Moving Average Approach: CPI and WPI are compared based on N period moving averages, where N can be adjusted using a Tableau parameter. This approach helps us address seasonality, as short-term fluctuations can be noisy, and therefore a smoothened chart may reveal more insights.
3. The Real Wage Approach: Real wage growth takes into account of both inflation and wage growth, and therefore simplifies our basis for comparison reducing two measures into a single measure.

Of course, Tableau dashboards are meant to be interactive and should allow the user to explore their own questions and answers, so please follow this link to go to my Tableau Public and have fun with my dashboard there!

 

 

The Insights

Some highlights from my dashboard include:

• There is no strong evidence to suggest that inflation is caused or at least not strongly caused by wages based on both moving average and lagged period approaches.
• In recent quarters, it is evident that wage growth have in fact fallen behind inflation significantly, as indicated in the real wage growth vs. inflation chart.
• There is some evidence that wages tend to follow inflation around 4 quarters later, as organizations and individuals tend to renegotiate their contracts on a yearly basis (or indexed to inflation, which is updated on an annual basis.