Making sense of consumers’ inflation perceptions and expectations – the role of (un)certainty

1 Introduction

Prepared by Aidan Meyler and Lovisa Reiche

Published as part of the ECB Economic Bulletin, Issue 2/2021.

Inflation expectations play a key role in the monetary transmission mechanism. Other things being equal, when economic agents anticipate that inflation will increase, they perceive the real interest rate to fall. As a result, they spend more and save less to optimise their consumption and investment over a long horizon. Inflation expectations also play an important role in the wage and price-setting process and are thus an important determinant of future inflation. Therefore, understanding the nature of economic agents’ inflation expectations and how they are formed is crucial for monetary policymakers.^[1]

This article analyses consumers’ inflation expectations using data available from the European Commission Consumer Survey (ECCS). There are several ways of measuring inflation expectations: they can be derived from financial market instruments, surveys of professional forecasters and business or household surveys. This article focuses on consumer inflation perceptions and expectations taken from the harmonised ECCS.^[2] These data go back to 1985. However, up to 2004 the data only provide qualitative information on respondents’ perceptions and expectations on the direction and speed of price changes. Quantitative data on the magnitude of inflation were collected systematically in the ECCS from 2004 onwards.^[3] This analysis helps address some of the more puzzling stylised facts of these inflation expectations, namely that: (a) the average perception/expectation has tended to be systematically above, although co-moving with, actual inflation; (b) there is an apparent negative correlation between inflation expectations and economic sentiment; (c) there is substantial heterogeneity both across countries and across individuals in terms of the levels of inflation expectations.

Some of the stylised facts of consumer inflation expectations can be explained by sociodemographic characteristics and economic sentiment. Our analysis confirms previous findings in the literature that consumers are likely to have higher inflation perceptions and expectations if they are younger, female, have lower levels of formal education and belong to lower income groups.^[4] Furthermore, we confirm that consumers that report being in a better financial situation and who have positive expectations about the economy as a whole are associated with lower inflation expectations, and that this also holds when controlling for sociodemographic factors.^[5]

We also offer explanations for both the bias in quantitative inflation expectations vis-à-vis actual inflation and their negative relationship with economic sentiment. The bias seems to be related to the fact that agents who are more uncertain typically report their inflation expectations using round figures (in multiples of five). Furthermore, those who have a negative attitude about the economy as a whole also tend to be more uncertain about the inflation outlook and to report higher inflation expectations. This explains why reported inflation expectations might increase in periods of economic uncertainty.

In exploring these issues, this article is structured as follows. Section 2 provides an overview of aggregate euro area consumers’ inflation perceptions and expectations. Section 3 describes the framework for looking at inflation expectations through the lens of uncertainty. Section 4 examines the impact of specific sociodemographic characteristics and economic sentiment variables on the likelihood that individuals are uncertain about inflation and thus report rounded expectations. Section 5 discusses how the (un)certainty framework helps explain reported inflation expectations, and Section 6 concludes.

2 The nature of consumers’ inflation expectations

Consumers’ qualitative inflation perceptions and expectations have tended to broadly co-move with actual inflation. The qualitative responses to the questions on inflation perceptions and expectations are summarised using a balance statistic.^[6] The broad upswings and downswings in inflation and their turning points are relatively well matched by the balance statistics (Chart 1). The most noticeable divergence is in consumers’ inflation perceptions following the introduction of the euro notes and coins. More recently, in March and April 2020, as the first wave of the coronavirus (COVID-19) pandemic and related lockdowns impacted European economies, there was an unprecedented divergence between consumers’ inflation perceptions and their expectations, with the former falling, but the latter rising (Box 1). However, a significant drawback of these qualitative measures is that there is no direct way of mapping these onto quantitative perceptions and expectations.

When asked to quantify their inflation perceptions and expectations, consumers, on average, tend to report significantly higher figures than actual inflation. Chart 2 presents the quantitative inflation perceptions and expectations reported by euro area consumers in the ECCS. For perceptions, the mean since 2004, at 8.7%, is substantially above the average HICP inflation over the same period (1.5%).^[7] The lower quartile (i.e. the 25th percentile) averaged 3.6%, which is also substantially above actual inflation. While the degree of over-quantification is lower for expectations, it is still substantial. The mean since 2004 has been 5.7% (3.8% for the median). The lower quartile has averaged 2.0%, which indicates that approximately 75% of consumers reported inflation expectations higher than 2%.

The peak correlation with actual inflation has tended to be slightly lagging for inflation perceptions and broadly contemporaneous for inflation expectations. While this should be the case for perceptions, in the case of expectations, if consumers were able to anticipate inflation, one would expect to see the peak correlation with some lead (i.e. the peak correlation of expectations would be with inflation some months ahead). Table 1 shows that the contemporaneous correlation of quantitative expectations with different measures of HICP inflation over the period 2004-2020 is somewhat higher than for quantitative perceptions, while the reverse holds for the qualitative figures. Overall, however, no single expectation or perception measure correlates more than the others with actual inflation across all HICP measures and time periods. Over the most recent five-year period (the figures in brackets in Table 1), the correlation of the quantitative estimates with actual inflation is relatively low, except for food price inflation. This reflects in part a structural break in the data for Germany in May 2019 (owing to a change to the survey mode – see footnote 16), as well as the impact of the coronavirus pandemic in 2020 (Box 1).

3 Looking at consumers’ inflation expectations through the lens of uncertainty

The apparent rounding observed in consumers’ quantitative inflation expectations points to uncertainty in reported inflation expectations. A considerable share of euro area consumers reports their quantitative expectations (and perceptions) using round numbers (most notably multiples of 5 and 10), while other consumers report to single digits or even to decimals. Chart 3 shows noticeable peaks at 0%, 5%, 10%, 15% and 20%, with a smaller distribution of respondents reporting to single digits. The modal responses of this latter group are around 2%-3% and thus not as biased as the aggregate numbers.^[8] According to communications and linguistics theory, round numbers –typically multiples of five or of ten, depending on the context – are frequently used to convey that a quantitative expression should be interpreted as imprecise. We use the “round numbers suggest round interpretations” principle to identify the existence of an uncertainty channel which may influence reported inflation expectations.^[9]

The uncertainty framework is flexible enough to help provide an understanding of average inflation expectations over the period 2004-2020, as well as in specific periods when inflation has been relatively high and relatively low respectively. For instance, the left panel of Chart 4 shows the distribution of quantitative inflation expectations in July 2008 (when overall HICP inflation was 4.1%). At this time, there were noticeable peaks at multiples of 10 as high as 50%, while the share of respondents reporting 0% inflation was relatively low. Among those who reported to single digits or even more precisely, the modal answer was 3%-4%. One year later, in July 2009, when overall HICP inflation had declined to -0.6%, the overall distribution shifted significantly to the left and there was a very strong peak in those reporting 0%, as well as some reporting negative values.

The uncertainty framework (and in particular rounding behaviour) allows the share of uncertain consumers in every month to be calculated. The overall distribution of quantitative expectations is seen as a composite of three categories of reporting, namely in (i) digits and decimals, which are not multiples of five or ten, (ii) multiples of five, which are not multiples of ten, and (iii) multiples of ten. Those reporting in digits and decimals can, on average, be considered more “certain”, whereas those reporting in multiples of five and ten can be considered “uncertain”. The respective shares of each group in the overall survey population can be derived for each survey month.^[10] On average, approximately one-third of respondents are more certain, while two-thirds are more uncertain (report to multiples of 5 or 10). These weights fluctuate but show notable increases in the share of uncertain respondents around the time of the global financial crisis and, more recently, since the onset of the coronavirus pandemic (Chart 5).

While uncertain respondents may not precisely quantify inflation, they appear able to capture the broad developments in inflation. The upper panel of Chart 6 shows that the modal expectations of certain consumers are not too far off, and evolve broadly along with, actual inflation. The lower panel shows that, although the modal expectations of consumers who are more uncertain are substantially higher than those who are certain (shown on different axes), they co-move very closely.^[11] This suggests that, while less certain consumers may find it hard to precisely articulate their inflation expectations, they are able to distinguish low and high inflation just as well as more certain consumers. Thus, even if their level of expected inflation is biased with respect to actual inflation, the changes over time correlate closely.

4 What determines whether individuals are (un)certain?

Whether a consumer is certain about price developments can depend on sociodemographic characteristics and economic sentiment. To analyse this, we look at the “probability that a consumer is certain” about inflation and try to explain this using a range of sociodemographic and economic sentiment variables.^[14] The sociodemographic variables include characteristics, such as age, level of formal education, gender and income quartile. In addition, sentiment indicators are used, which take the form of expressed economic opinions on the expected personal financial and general economic situation, a qualitative inflation assessment about inflation in the next 12 months and opinions on unemployment development, as well as on the timing of purchases and savings. Selected results are displayed in Chart 7 and Chart 8. On average, and other things being equal, a higher income and higher level of formal education contribute positively to an individual’s estimated probability of being certain. Certainty increases further with age and if respondents are male. At the same time, respondents tend to be less certain if they are more negative about their personal finances, the general economic situation including unemployment and their ability to purchase and save.^[15] These patterns hold robustly across most time periods and euro area countries in our sample.

The probability that an individual is certain about inflation expectations differs significantly across euro area countries. The upper panel of Chart 9 shows that those countries where consumers are estimated to be more certain also have a lower mean inflation expectation across the time periods. While there is also some correlation between the mean inflation expectation and the average rate of actual inflation (see the lower panel of Chart 9), it is much lower. This suggests that the certainty channel plays an important role in explaining the differences in reported inflation expectations across countries in our sample.^[16] However, thus far, the analysis has simply identified sociodemographic characteristics and economic sentiment indicators that suggest whether consumers may be more or less uncertain about their inflation expectations. How much these factors contribute to reported inflation expectations is considered below.

5 Does this (un)certainty framework help explain and foster greater understanding of inflation expectations?

The role of (un)certainty in consumers’ quantitative inflation expectations is estimated with a model. First, the linear effects of sociodemographic and economic sentiment variables on quantitative inflation expectations are estimated.^[17] Moreover, to control for potentially different macroeconomic environments, actual inflation (HICP), inflation forecasts by Consensus Economics and GDP growth by country and time are incorporated. The (un)certainty framework is then used to split the sample. This makes it possible to show whether the effect of these sociodemographic and economic opinion variables differs between more and less certain consumers.

At the aggregate level, this model replicates stylised facts on the impact of sociodemographics and economic sentiment on inflation expectations.^[18] This study finds that the same characteristics described in the previous section as contributing to greater uncertainty (for example, lower age, lower income group and lower formal education or a worse economic sentiment and a lower ability to save) also contribute to higher expectations. This appears intuitive, given that rounded numbers (i.e. 5, 10 and 15) are typically a lot higher than the reported digits with a median of 2 over the reference period. The fitted values from the model closely match the actual measured inflation expectations. Using this model to estimate the inflation expectation of an “average” person (i.e. mean values in all categories) and averaging across countries for the whole sample period yields a value close to the measured mean expectations (Chart 10, Panel a).

Dividing the sample into the “certain” and “uncertain” groups explains a large part of the so-called inflation expectation conundrum, i.e. the overestimation of inflation in consumer surveys.^[19] Applying the above model to each group separately shows that sociodemographic and sentiment variables have a smaller impact on the inflation expectations of the “certain” group (Table 2). The difference in inflation expectations between the “certain” and “uncertain” groups is visualised in Chart 10, panel b and estimated over all time periods separately. It suggests that the differential in inflation estimates observed between socioeconomic groups and respondents of diverging economic assessments can at least in part be explained by the different levels of certainty these groups of respondents have. These results also hold in a model version that controls for perceptions, given their strong link with expectations.^[20] However, it should be noted that even consumers who are certain overestimate inflation. Therefore, the certainty channel should not be considered in isolation from other hypothesised reasons, including psychological aspects of loss aversion, seasonality and the idea that consumers might have in mind different and very heterogeneous baskets (including house prices, for instance) when estimating inflation.^[21]

6 Conclusion

Inflation (un)certainty is a channel that sheds light on some of the more puzzling aspects of reported quantitative inflation expectations. First, the (un)certainty lens helps explain why we can observe high estimated aggregates despite rather low inflation. This is because in conditions of uncertainty many consumers report rounded numbers, whereby they often quantitatively overestimate inflation. Second, since rounding is more prevalent in some sociodemographic groups, it also helps explain why we observe higher levels of inflation perceptions and expectations for specific population characteristics. However, it should be borne in mind that, although consumers who are less certain may not precisely quantify future inflation, their expectations identify relatively low and high inflation in a similar manner to more consumers who are more certain and in broad alignment with the actual inflation cycle.

Furthermore, the uncertainty channel is also a possible explanation for the negative correlation sometimes observed between the economic outlook and inflation expectations. It thus offers an alternative perspective to the view that this negative correlation is a so-called supply-side interpretation of inflation, whereby individuals interpret an increase in expected inflation as unambiguously adverse.^[22] We show that this correlation could reflect increased uncertainty, which, in turn, increases reported inflation expectations.

However, there remain aspects of consumers’ inflation expectations that cannot be addressed using the data considered in this article. For instance, as we do not observe the same individual over time, it is challenging to understand how expectations are formed and the extent of their economic impact. In the future, the ECB’s Consumer Expectations Survey (CES), which was launched as a pilot in 2020 and has a genuine panel structure, could offer a more in-depth view of consumer expectations over time, their formation and how consumers understand and react to monetary policy.^[23]