Baseline Forecast Research Articles

World Economic Prospects Monthly

Overview: Renewed restrictions dampen prospects ▀ The global economic recovery has now entered a second, slower growth phase. With many economies, particularly in Europe, needing to reimpose some restrictions on activity in the light of rising Covid‐19 cases, we have again nudged down our forecast for global GDP growth next year, from 5.4% to 5.2%. ▀ In response to recent GDP releases and some other timely indicators, we have edged up our growth estimates for Q2 and Q3 2020 a touch at a global level. But this improvement has been broadly offset by downward revisions to our GDP growth forecast for Q4 2020 and early next year. ▀ True, retail sales and consumer confidence data have recently been encouraging in the advanced economies as a whole. But it is unclear whether the strength of the former reflects households spending more freely or continued substitution of spending away from services towards goods as a result of restrictions to curb the spread of Covid‐19. ▀ It is also uncertain as to the extent that households and firms will adjust behaviour in response to the recent resurgence in the number of Covid‐19 cases in many parts of the world. Expectations of further curbs to come or a slower return to normal may also prompt households and firms to become more cautious. In this respect, the renewed, albeit small, fall in the global services PMI in September provides pause for thought. ▀ Overall then we have become somewhat more cautious about the pace of the expansion as we move into Q4. Growth over the next few quarters is still expected to be similar to that recorded during the post‐global financial crisis recovery. But this is conditional on very supportive fiscal and monetary policy as well as the avoidance of a widespread return to lockdown‐style conditions. Thus, risks to our baseline forecast remain firmly skewed to the downside.

Prospects for the Economic Development of the Republic of Buryatia

ABSTRACT The article analyzes the development of the economy of the Republic of Buryatia spanning 2007–2017 and provides two forecast analyses of the republic’s economic development until 2021: the baseline forecast and the optimistic forecast. To generate the forecasts the authors used a dynamic input–output model of the Buryat economy that includes fuzzy parameters. It is shown that under favorable macroeconomic conditions and a sharp increase in fixed capital investment, it is possible to significantly accelerate economic growth in Buryatia. Specific projects that will accelerate economic growth in the republic are discussed.

Demand forecasting in the presence of systematic events: Cases in capturing sales promotions

Reliable demand forecasts are critical for effective supply chain management. Several endogenous and exogenous variables can influence the dynamics of demand, and hence a single statistical model that only consists of historical sales data is often insufficient to produce accurate forecasts. In practice, the forecasts generated by baseline statistical models are often judgmentally adjusted by forecasters to incorporate factors and information that are not incorporated in the baseline models. There are however systematic events whose effect can be quantified and modeled to help minimize human intervention in adjusting the baseline forecasts. In this paper, we develop and test a novel regime-switching approach to quantify systematic information/events and objectively incorporate them into the baseline statistical model. Our simple yet practical and effective model can help limit forecast adjustments to only focus on the impact of less systematic events such as sudden climate change or dynamic market activities. The model is validated empirically using sales and promotional data from two Australian companies. The model is also benchmarked against commonly employed statistical and machine learning forecasting models. Discussions focus on thorough analysis of promotions impact and benchmarking results. We show that the proposed model can successfully improve forecast accuracy and avoid poor forecasts when compared to the current industry practice which heavily relies on human judgment to factor in all types of information/events. The proposed model also outperforms sophisticated machine learning methods by mitigating the generation of extremely poor forecasts that drastically differ from actual sales due to changes in demand states.

World Economic Prospects Monthly

Overview: Global activity starts to bounce back ▀ After a dire start to Q2 in April, the global economy has since staged a robust rebound as lockdown restrictions in many regions have eased. But despite a strong initial bounce, high unemployment and surging corporate debt will limit the scale of the revival in H2 and beyond. And the renewed rise in Covid‐19 cases in parts of the world shows that considerable downside risks remain. ▀ After persistently surprising sharply to the downside, global economic data have exceeded expectations over the past month or so. Retail sales staged a particularly sharp rebound in Europe and North America in May.▀ The sharp post‐lockdown consumer spending bounce in response to the release of pent‐up demand, along with some evidence of a revival in industrial production and global trade, is clearly encouraging. In response we have raised our mid‐year GDP forecasts for a number of economies, including the US and China, pushing up our 2020 world GDP growth forecast by about 0.5pp to −4.5%.▀ Nonetheless, the risk of a second Covid‐19 wave, the swathe of negative headlines about job redundancies and the scaling‐back of some government support measures before long in some countries suggest that the sharp rebound in activity seen so far may not persist for too long.▀ As a result, the upward revision to our forecast for global activity in the shorter‐term is offset by a more cautious assessment of growth prospects next year. We now expect the level of global GDP at end‐2021 to be a touch lower than anticipated a month ago. Overall, we have cut our world GDP growth forecast for 2021 from 6.5% to 5.8%.▀ Our baseline forecast assumes that a global second wave of Covid‐19 is avoided. But in this respect, the recent resurgence in cases in some countries (and in some US states in particular) is a clear worry. Risks to our baseline forecast remain firmly tilted to the downside.

Model-Based Globally-Consistent Risk Assessment

This paper outlines an approach to assess uncertainty around a forecast baseline as well as the impact of alternative policy rules on macro variability. The approach allows for non-Gaussian shock distributions and non-linear underlying macroeconomic models. Consequently, the resulting distributions for macroeconomic variables can exhibit skewness and fat tails. Several applications are presented that illustrate the practical implementation of the technique including confidence bands around a baseline forecast, the probabilities of global growth falling below a specified threshold, and the impact of alternative fiscal policy reactions functions on macro variability.

After the pandemic: Medium‐term growth uncertainties

▪ The coronavirus is having a very large short‐term negative impact on world growth. But the medium‐term growth outlook is more uncertain. Much depends on the policy response ‐ a strong and well‐designed response could contain the medium‐term output losses, but large and enduring damage is a risk. ▪ Growth patterns after significant GDP declines vary. Historical evidence points to large upfront effects from pandemics and natural disasters, but the medium‐term outcomes are mixed, with policy responses a crucial determinant. Longer recessions and financial crises tend to lead to weaker medium‐term growth. ▪ The coronavirus may trigger annual GDP declines among the worst seen in the last 100 years. Economies can bounce back sharply after such declines, but our analysis suggests output losses also endure in a significant number of cases. ▪ The US interwar experience shows the danger of allowing financial distress to snowball and exacerbate GDP declines. The weakness of medium‐term growth after the global financial crisis confirms the long‐term impact of such distress. ▪ A key risk for the medium term is that firms and/or households react to the coronavirus recession and disruption by raising savings, accelerating a shift toward ‘Japanification’ of major economies. ▪ Our baseline forecasts envisage moderate medium‐term output losses due to coronavirus, in part reflecting rapid and large‐scale policy interventions. But uncertainty around this forecast is significant and considerable variation is possible across economies.

Is the Taylor rule optimal? Evaluation using a wavelet-based control model

ABSTRACT This paper extends the wavelet-based control (WBC) model of Crowley and Hudgins (2015) to compare the simulated performance of jointly optimal fiscal and monetary policy, where the policymakers place emphasis on a variety of macroeconomic targets, with the case where monetary policy follows a modified Taylor rule. The results show that the Taylor rule is likely to render higher interest rates, diminished investment, and appreciated real exchange rates compared with an unconstrained baseline simulation. We therefore find that the Taylor rule is suboptimal since it results in higher fiscal deficits due to substitution by policy authorities, thus confirming recent research on the interaction of fiscal and monetary policies. The analysis also compares the baseline and Taylor rule simulated forecasts when the central bank adopts a ‘hawkish’ inflation policy compared to a more ‘dovish’ policy stance.

Long-term impact of the adoption of bedaquiline-containing regimens on the burden of drug-resistant tuberculosis in China

BackgroundCurrently available injectable agents are inadequate to address the high drug-resistant tuberculosis (DR-TB) burden in China. Regimens including the oral agent bedaquiline have been shown to be efficacious and safe, leading to its incorporation into multiple national TB treatment programs. This analysis evaluated the impact of increased adoption of bedaquiline-containing regimens on the DR-TB burden in China.MethodsA state-transition model was developed that permits movement and interaction between susceptible, latent, and active TB disease states, while distinguishing between drug-sensitive (DS) and DR-TB. Model inputs were obtained from the published literature or derived such that model metrics approximated those published by the WHO. Expected improvements in infrastructure were built into the model to forecast the epidemiology of DR-TB in China through 2040 in the absence of bedaquiline (baseline forecast). The impact of higher utilization of bedaquiline-containing regimens (85% peak share) was then assessed in two scenarios that differed with regard to treatment success rates of the regimens: 61% (reflecting findings of clinical trials) and 80% (reflecting data from observational studies), versus the 44% success rate associated with standard-of-care treatment.ResultsIn the baseline scenario, the model predicted increases in annual incidence of DR-TB by 6–8% during each five-year period between 2020 and 2040, with an increase of 30% over the entire study duration. Adoption of bedaquiline-based regimens limits the incidence increases to only 1–3% in each five-year period and to 8% over the study duration in the 61% success rate scenario. Incidence declines by 1–6% during each five-year period and by 12% over the study duration in the 80% success rate scenario. Similar effects on DR-TB prevalence (4–5% increase in baseline, 0–7% decline in scenario 1, and 4–19% decline in scenario 2) and mortality (5–7% increase in baseline, 0–16% decline in scenario 1, and 6–40% decline in scenario 2) were seen following bedaquiline adoption.ConclusionsIncorporation of bedaquiline into DR-TB treatment regimens will significantly reduce the DR-TB burden in China, helping to counter the expected increase in burden in the absence of bedaquiline. The study will provide valuable information to public health policy planners.

Learning about fiscal multipliers during the European sovereign debt crisis: evidence from a quasi-natural experiment

SUMMARY Identifying fiscal multipliers, that is, the effect of discretionary fiscal actions on growth, is challenging. It requires comparing the realization of growth after a fiscal action to a hypothetical growth path that would have prevailed in the absence of such action. Deriving the hypothetical path usually involves very strong assumptions. This paper helps to relax some of the assumptions, using a unique new data set on the European Commission’s recommendations under the so-called excessive deficit procedure (EDP). These recommendations provide information on both output growth in a no-policy-change baseline forecast and an alternative forecast of growth incorporating the size of fiscal consolidation recommended under the EDP. A comparison of these two alternative scenarios allows us to infer country-specific fiscal multipliers implicitly applied by the Commission in its EDP recommendations for a sample of 24 countries over the period 2009–2015. Our results confirm Blanchard and Leigh’s (2013, 2014) presumption that fiscal multipliers used by forecasters were adjusted upwards during the European sovereign debt crisis, albeit starting from lower than commonly assumed levels. Contrary to Blanchard and Leigh (2013, 2014), we do not find evidence that the ‘true’ ex-post fiscal multipliers systematically exceeded 1 in the early crisis years.

Analyzing the Effect of the COVID-19 on the Global Economy: A Case Study of Its Influence on Africa’s FDI and Foreign Exchange Inflows

The global economy has taken a major hit due to the grave effect of the spread of COVID-19. Developed countries are struggling to sustain their economies and this gives an indication of the current state of developing and underdeveloped nations. The closure of businesses and the laying off of some workers, coupled with the closure of some international air and sea ports indicates the stagnation of global economic growth and process with a forecasted massive recession. The local governments of various countries have collectively inputted strategic efforts to supplement the situation with diverse financial relief funds and fiscal assistance policies. The GDP of the global economy is predicted to shrink by 5.2% according to the minimum economic forecast predictions (World Bank, 2020). The severity of the pandemic will undoubtedly leave a negative and uninspiring blueprint on the face of the global economy. The pandemic like a binocular has exposed the multifaceted cracks in the various economy sectors and their unpreparedness for global storms such as this. Foreign Direct Investment and foreign exchange inflows into the continent of Africa have been stable on average over the years; however, the current state of the global economy predicts a sharp fall which will not easily recover until there has been a full recovery. This gives a baseline forecast of the adverse effect of the pandemic on the African soil as well as other developing and underdeveloped countries and regions globally. Therefore, various governments within the continent must develop and implement breakwater policies such as intra-regional integrations as well as strong international relations that will help hedge against and cushion the effect of another global storm. This paper seeks to analyze the effect of the pandemic on the global economy, a case study of its influence on Africa’s FDI and foreign exchange inflows.

The cost of complexity in forecasts of population abundances is reduced but not eliminated by borrowing information across space using a hierarchical approach

Anticipating ecological changes is paramount if we are to manage biodiversity and the services they provide to humanity. When forecasting population abundances, studies have shown that simple statistical models often have better forecast performance than complex models. These studies have evaluated forecasts of models fitted separately to data from single sites (single‐site approach). Here, we aim to contrast the forecast performance and forecast horizon between a single‐site approach and a hierarchical multi‐site approach where a single model is fitted to data from multiple‐sites, and to investigate how they vary with model complexity. We used 5273 population time series on 84 species from the Swedish breeding bird survey program, and found that simple models on average had better forecast performance and forecast horizon than complex models for both the single‐ and the multi‐site approach. However, the cost of complexity was considerably reduced under the multi‐site approach, while the proportion of species for which complex models had better forecast performance than simple models was also much larger than under the single‐site approach. This suggests that the multi‐site approach is useful for inclusion of more detailed processes which may benefit forecasts for some species and which are of importance for managers. Still, our results are in line with some previous studies suggesting that it is surprisingly difficult to construct complex models that, on average, beat trivial baseline forecasts.

Nowcasting lightning occurrence from commonly available meteorological parameters using machine learning techniques

Lightning discharges in the atmosphere owe their existence to the combination of complex dynamic and microphysical processes. Knowledge discovery and data mining methods can be used for seeking characteristics of data and their teleconnections in complex data clusters. We have used machine learning techniques to successfully hindcast nearby and distant lightning hazards by looking at single-site observations of meteorological parameters. We developed a four-parameter model based on four commonly available surface weather variables (air pressure at station level (QFE), air temperature, relative humidity, and wind speed). The produced warnings are validated using the data from lightning location systems. Evaluation results show that the model has statistically considerable predictive skill for lead times up to 30 min. Furthermore, the importance of the input parameters fits with the broad physical understanding of surface processes driving thunderstorms (e.g., the surface temperature and the relative humidity will be important factors for the instability and moisture availability of the thunderstorm environment). The model also improves upon three competitive baselines for generating lightning warnings: (i) a simple but objective baseline forecast, based on the persistence method, (ii) the widely-used method based on a threshold of the vertical electrostatic field magnitude at ground level, and, finally (iii) a scheme based on CAPE threshold. Apart from discussing the prediction skill of the model, data mining techniques are also used to compare the patterns of data distribution, both spatially and temporally among the stations. The results encourage further analysis on how mining techniques could contribute to further our understanding of lightning dependencies on atmospheric parameters.

Consumers alone shouldn't trigger the next recession

▀ If consumers in advanced economies were to hike their savings and rein in their discretionary spending in response to fears about the economy, we project global GDP growth in 2020 would slow to a subdued 2.1% (below our 2.5% baseline forecast), but the world economy would avoid a recession. ▀ The risks of rising precautionary savings aren't uniform across the advanced economies. For instance, the UK, Australia, Canada and Japan look particularly vulnerable to slowing retail sales, which could trigger a stronger downturn in those countries. ▀ Economies with the highest rates of consumer debt are also likely to be more at risk to weaker discretionary spending. In this respect, Australia, the Netherlands and Canada stand out the most.

Why we aren't predicting a global recession

▀ Fears that the global economy is heading into a recession are rising. But while we cannot ignore the risks that a recession could be brewing, our baseline assumption is still for a modest growth slowdown from here. ▀ The global economy is in a similar position to 2012 and 2015, as mounting uncertainties dampen growth. This time, trade tensions are a high‐profile culprit rather than the possible collapse of the eurozone or a China hard landing. ▀ In the previous two cases global growth fell to around 2.5% ‐ around the rates seen in Q2 this year ‐ only to then rebound. Our baseline forecasts assume a similar mini cycle, albeit with only a modest growth rebound. ▀ We also assume that further major adverse shocks won't materialise, and that insurance policy moves by central banks will stop a plunge in investment and households from panicking. ▀ Still, recession fears should be taken seriously ‐ slowdowns can become self‐perpetuating. Once annual GDP growth has fallen by over 1ppt from its peak, the eventual decline typically ends up being much larger ‐ of the seven growth slowdowns since the late 1970s where annual growth slowed by over 1ppt ‐ four resulted in either a global recession or only a narrow escape from one. ▀ With US‐China tensions unlikely to recede and factors like the US yield curve inversion adding to the air of gloom, the latest downturn could gain momentum. ▀ Although reduced macro volatility and anchored inflation have made it easier for policymakers to deliver soft landings, the effectiveness of monetary policy has waned. And with China no longer acting as spender of last resort, it's vital that governments in advanced economies stand ready to pick up the slack

World Economic Prospects Monthly

Overview: Downturn to spur monetary policy loosening ▀ We now expect global GDP growth to dip slightly below 2016's post‐crisis low of 2.6% in 2019. Moreover, despite a swathe of insurance policy loosening, we do not see a rebound in GDP growth in 2020 and have revised down our forecast from 2.7% to 2.5%. This is in contrast to the previous downturn when growth rebounded sharply in 2017. ▀ Timely global activity indicators have remained soft and while they do not point to a sharp loss of momentum in the shorter term, neither do they suggest that the economic situation is likely to get better imminently. Nonetheless, there are two key reasons why we have become more pessimistic about growth prospects next year. ▀ First, we have added further US‐China tariffs to our baseline forecast, which, despite likely more aggressive policy action by the Fed and China, is set to lower GDP growth in both economies next year, with inevitable spill‐overs to the rest of the world. ▀ Second, the ongoing uncertainty surrounding US‐China relations, coupled with growing recession fears in response to the inversion of the US yield curve, is prompting the manufacturing‐focused weakness to spread. Consumers are generally still in good health, but declining business confidence has triggered weaker hiring intentions which may weaken consumer spending growth further ahead. ▀ Our baseline assumes that insurance policy loosening prevents consumer panic and a deep economic slowdown from here. But the reduced effectiveness of monetary policy in the current environment and the small likelihood of a definitive and imminent end to US‐China tensions imply that a notable growth pick‐up, as seen in 2017, is unlikely. ▀ While our baseline assumes no end to the global expansion, we would warn against complacency over the risk of recession. For monetary policy loosening to place a floor under global growth, it will need to be augmented by more accommodative fiscal policy and perhaps a bit of luck in the form of no further major negative shocks.

Forecasting the M4 competition weekly data: Forecast Pro’s winning approach

Forecast Pro forecasted the weekly series in the M4 competition more accurately than all other entrants. Our approach was to follow the same forecasting process that we recommend to our users. This approach involves determining the Key Performance Metric (KPI), establishing baseline forecasts using our automated expert selection algorithm, reviewing those baseline forecasts and customizing forecasts where needed. This article explores why this approach worked well for weekly data, discusses the applicability of the M4 competition to business forecasting and proposes some potential improvements for future competitions to make them more relevant to business forecasting.

Informality and the Challenge of Pension Adequacy

Past reforms have put the Peruvian pension system on a largely fiscally sustainable path, but the system faces important challenges in providing adequate pension levels for a large share of the population. Using administrative microdata at the affiliate level, we project replacement rates in the defined benefit (DB) and defined contribution (DC) pillars over the next 30 years and simulate the impact of various reform scenarios on the average level and distribution of pensions. In the DB pillar, the regressive minimum contribution period should be re-thought, while in the DC pillar a broadening of the contribution base and/or an increase in contribution rates would help increase replacement rates relative to the baseline forecast of 25-33 percent. A higher net real rate of return than assumed in the baseline would also have a significant positive impact. In the medium-term, labor market reform to tackle informality, and a broad pension reform to restructure the system and avoid competition between the DB and DC pillars should be a priority. Given low pension coverage, having a strong non-contributory pillar will remain important for the foreseeable future.

On the properties of ensemble forecast sensitivity to observations

Evaluating impacts of observations on the skill of numerical weather prediction (NWP) is important. The Ensemble Forecast Sensitivity to Observation (EFSO) provides an efficient approach to diagnosing observation impacts, quantifying how much each observation improves or degrades a subsequent forecast with a given verification reference. This study investigates the sensitivity of EFSO impact estimates to the choice of the verification reference, using a global NWP system consisting of the Non‐hydrostatic Icosahedral Atmospheric Model (NICAM) and the Local Ensemble Transform Kalman Filter (LETKF). The EFSO evaluates observation impacts with the moist total energy norm and with recently proposed observation‐based verification metrics. The results show that each type of observation mainly contributes to the improvement of forecast departures of the observed variable maybe due to the limitation of localization in the EFSO. The EFSO overestimates the fraction of beneficial observations when verified with subsequent analyses, especially for shorter lead times such as 6 h. We may avoid this overestimation to some extent by verifying with observations, analyses from other data assimilation (DA) systems, or analyses of an independent run with the same DA system. In addition, this study demonstrates two important issues possibly leading to overestimating observation impacts. First, observation impacts would be overestimated if we apply relaxation‐to‐prior methods to the initial conditions of the ensemble forecasts in the EFSO; therefore, the ensemble forecasts in the EFSO should be independent of the ensemble forecasts in the DA cycle. Second, deterministic baseline forecasts of the EFSO, which represent the forecast without DA, should be initialized by the ensemble mean of the first guess at the analysis time, not by the previous analysis.

A business case for 5G mobile broadband in a dense urban area

5G networks are envisioned to provide consumers and industry with improved transmission performance and advanced communication possibilities. To deliver on this promise of ushering in faster downloads and lower latency, mobile network operators are called upon for substantial investment in network infrastructure. Investors and operators need a clear 5G business case before making such investment. So far, very little research has been published on the topic of the 5G business case. This article studies the impact of different elements driving the business case of a 5G network. The study was performed within 3 boroughs of central London, UK, for the period 2020–2030. 5G-related costs and revenues were calculated to derive the business case. The results show that the business case for a 5G network providing mobile broadband services alone is positive over the time period 2020–2030 but has some risk in the later years of this time period. The business case is also particularly sensitive to assumptions on the revenue uplift and the rate of traffic growth which are inherently challenging to forecast. The sensitivity analysis shows that the return on investment becomes negative if both traffic and costs are significantly higher and revenues increase more slowly than our baseline forecasts. Network sharing helps to substantially improve the business case. Further research is needed to understand the business case on a regional or nationwide basis, and for a network that provides additional services beyond broadband.

Not all trade wars are created equal

▀ When interpreting estimates of the economic impact of trade wars, the devil is in the detail. Our review of more than 30 institutions' trade war projections finds huge variation – much of which can be explained by differences in assumptions rather than differences in models' structures or specifications. Relative to estimates based on extreme financial or tariff assumptions, our main trade war scenario results are moderate and comparable with the IMF's latest analysis. ▀ In our baseline forecast, trade policy measures have a relatively limited overall impact on global growth. This is in line with recent experience: to date, direct effects from higher trade costs have been small, and policy action has acted to offset adverse impacts on confidence. But the risk of further escalation in US‐China trade tensions remains, even following the (fragile) Trump‐Xi truce agreed at the recent G20 summit. ▀ Our review finds that estimates of the impact of such an escalation range from negligible impacts to a deterioration in some countries’ economic conditions approaching that seen during the global financial crisis. Results in Oxford Economics’ “rising protectionism” scenario – from our latest Global Scenarios Service – are moderate in comparison. ▀ We also find that all estimates showing substantial economic effects from a trade war in our sample are predicated on extreme asset price or tariff moves. In some cases, tariffs are assumed to rise more than at the time of the Great Depression in the 1930s. ▀ Such differences in assumptions can largely account for the divergence in trade war impact estimates. This is illustrated in our very low probability “full‐blown global trade war” scenario – incorporating severe tariff and financial assumptions more in line with institutions like the Bank of England – which generates a deterioration in economic conditions that broadly matches extreme estimates in our sample.