No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Forecasts of US housing starts: assessing the usefulness of nowcast data
Abstract
This study focuses on the current-quarter and one – through four-quarter-ahead Federal Reserve forecasts of housing starts. The aim is to assess the usefulness of nowcast data (measured by the current-quarter forecasts) for predicting housing starts one through four quarters ahead. Specifically, we use the nowcast data to generate the one – through four-quarter-ahead nowcast-based forecasts. For 1985–2016, the Federal Reserve and nowcast-based forecasts (while outperforming the naïve forecasts) contain useful and distinct predictive information. Combining these forecasts yields reductions in forecast errors that are larger at longer horizons. In addition, the Federal Reserve (nowcast-based) forecasts imply symmetric (asymmetric) loss. The nowcast-based forecasts, in particular, are of value to a user who assigns high (low) cost to incorrect downward (upward) moves and, thus, offer useful information for policymaking, when downward moves in housing starts are considered as early-warning signs of overall economic downturns.
... Forecast combinations are effective at improving the predictive ability of a set of models. Chikamatsu et al. (2021) and Baghestani (2022) also identify the advantages of combining model forecasts and professional survey forecasts. Combinations of models usually work better than just one model, but this is not always the case. ...
This paper presents a systematic review of research papers on nowcasting economic activity. The study summarizes the state‐of‐the‐art nowcasting approaches and methods, describes the indicators used in this analysis, highlights the existing gaps, and proposes future research directions. Based on an analysis of 193 articles on nowcasting in economics that were published in the journals indexed in the Web of Science Core Collection database, future research directions in nowcasting are described in this paper. This research indicates that the focus of economic activity nowcasting should rely on the use of real‐time data and alternative indicators in order to enhance the predictive ability.
Moving beyond the crossroads of Earth Sciences and Environmental Studies, nowcasting has captured the interest of Central Bank researchers in the domain of Economics and Finance. Nowcasting offers a viable solution to the common challenges in forecasting, like delayed access to macroeconomic data, uneven timing of official data releases, structural shifts in the data generating process, and mismeasurement due to data gaps and revisions. The strength of nowcasts lies in their ability to update themselves based on the new information arriving regularly. However, a trade-off exists between the frequency of data arrival and the stability of nowcasts. This study examines the extant literature using a Structured Literature Review, with a special focus on Economics and Finance. The study highlights the needs and challenges in nowcasting and conducts a bibliometric analysis to identify the clustering patterns in keywords pertaining to nowcasting literature and their evolution over time, indicating the direction in which nowcasting research is heading. The study then identifies various models used in the literature, classifying them into a few overarching categories. The study finds that the principal advantage of standard statistical nowcasting models lies in their ability to handle the data issues such as high dimensionality, unavailability/lagged availability, non-synchronicity, non-linearity and frequent revisions in data. However, these models may not be appropriate for big data which witness exponential rise in hyperparameters. Machine learning models provide a complementing tool because they deal with big data and enable better cross-validation for efficient hyperparameter selection. Finally, this study undertakes an empirical exercise wherein Factor Augmented Mixed Data Sampling Model has been utilised to nowcast the United Kingdom’s inflation using high frequency indicators from December, 2021 to March, 2024—a period of turbulence when the country witnessed the worst bout of inflation. Nowcasts seem to perform better in predicting UK inflation during this period.
This study evaluates the accuracy of the US Energy Information Administration (EIA) monthly forecasts of gasoline prices for 2005–2021. Our findings indicate that the 1-, 3-, 6-, 9-, and 12-month-ahead EIA forecasts do not, on average, significantly over- or under-predict gasoline prices, and they generally outperform the random walk and the nowcast-based benchmarks in terms of both the mean squared forecast error and the predictive information content. We further show that the shorter-horizon (longer-horizon) EIA forecasts predict directional change under asymmetric (symmetric) loss. Additional results indicate that the 1-, 3-, 6-, 9-, and 12-month-ahead EIA forecast errors are all orthogonal to consumer expected change in gasoline prices, actual change in core consumer price index, consumer vehicle-buying attitudes, and consumer sentiments. However, the 1-month-ahead (1- through 12-month-ahead) EIA forecast errors fail to be orthogonal to crude oil price changes (consumer expected inflation), meaning that these indicators can potentially help improve the accuracy of the EIA forecasts of gasoline prices.
Problem
How to help practitioners, academics, and decision makers use experimental research findings to substantially reduce forecast errors for all types of forecasting problems.
Methods
Findings from our review of forecasting experiments were used to identify methods and principles that lead to accurate forecasts. Cited authors were contacted to verify that summaries of their research were correct. Checklists to help forecasters and their clients undertake and commission studies that adhere to principles and use valid methods were developed. Leading researchers were asked to identify errors of omission or commission in the analyses and summaries of research findings.
Findings
Forecast accuracy can be improved by using one of 15 relatively simple evidence-based forecasting methods. One of those methods, knowledge models, provides substantial improvements in accuracy when causal knowledge is good. On the other hand, data models – developed using multiple regression, data mining, neural nets, and “big data analytics” – are unsuited for forecasting.
Originality
Three new checklists for choosing validated methods, developing knowledge models, and assessing uncertainty are presented. A fourth checklist, based on the Golden Rule of Forecasting, was improved.
Usefulness
Combining forecasts within individual methods and across different methods can reduce forecast errors by as much as 50%. Forecasts errors from currently used methods can be reduced by increasing their compliance with the principles of conservatism (Golden Rule of Forecasting) and simplicity (Occam’s Razor). Clients and other interested parties can use the checklists to determine whether forecasts were derived using evidence-based procedures and can, therefore, be trusted for making decisions. Scientists can use the checklists to devise tests of the predictive validity of their findings.
This study investigates the directional predictability of financial indicators for home sales across tranquil (1984–2005) and volatile (1972–1983 and 2006–2013) periods. We find that the mortgage rate has directional predictability for both existing and newly built home sales for up to 2005. The federal funds rate generally has directional predictability for existing (newly built) home sales in 1984–2005 (1972–1983). The term spread has directional predictability for home sales in 1972–1983 but generally not in the tranquil period of 1984–2005. Further, unlike mortgage and federal funds rates, the term spread has directional predictability for home sales in 2006–2013 and thus can help the Fed with useful information (assuming that this trend continues).
The usual procedure for developing linear models to predict any kind of target variable is to identify a subset of most important predictors and to estimate weights that provide the best possible solution for a given sample. The resulting “optimally” weighted linear composite is then used when predicting new data. This approach is useful in situations with large and reliable datasets and few predictor variables. However, a large body of analytical and empirical evidence since the 1970s shows that such optimal variable weights are of little, if any, value in situations with small and noisy datasets and a large number of predictor variables. In such situations, which are common for social science problems, including all relevant variables is more important than their weighting. These findings have yet to impact many fields. This study uses data from nine U.S. election-forecasting models whose vote-share forecasts are regularly published in academic journals to demonstrate the value of (a) weighting all predictors equally and (b) including all relevant variables in the model. Across the ten elections from 1976 to 2012, equally weighted predictors yielded a lower forecast error than regression weights for six of the nine models. On average, the error of the equal-weights models was 5% lower than the error of the original regression models. An equal-weights model that uses all 27 variables that are included in the nine models missed the final vote-share results of the ten elections on average by only 1.3 percentage points. This error is 48% lower than the error of the typical, and 29% lower than the error of the most accurate, regression model.
Many studies have undertaken separate analyses of the Fed's forecasts of real Gross Domestic Product (GDP) growth and inflation. This article presents a method for jointly evaluating the direction of change predictions of these variables. We conclude that some of the inflation forecasts, examined separately, were not valuable. However, the joint pattern of GDP and inflation projections was generally in accord with the economy's movements. '… directional forecasting … is now an increasingly popular metric for forecasting performance….' (Pesaran and Timmermann, 2004, 414)
This study focuses on the Federal Reserve and private forecasts of growth in real residential investment. The aim is to improve predictive accuracy by first evaluating these forecasts. The results for 1984–2015 reveal that the Federal Reserve and private forecasts are generally free of systematic bias, superior to the naïve benchmark, and predict directional change with high accuracy rates. However, these forecasts do not contain detailed information in consumer home-buying attitudes and expectations. Using a subset of such information and real-time data on residential investment, a knowledge model (KM) is constructed to produce comparable forecasts. The test results indicate that the KM forecasts of growth in residential investment contain distinct and useful predictive information, and the combined Federal Reserve, private, and KM forecasts show reductions in forecast errors that are more significant at longer horizons. As such, we conclude that consumer survey responses help improve forecast accuracy. Given that accurate forecasts contribute to the success of policy, more transparency in Federal Reserve Open Market Committee (FOMC) decisions is encouraged. With more transparency and clear communication, consumers are able to provide more informative responses, which can then be employed to produce more accurate forecasts of growth in residential investment.
This article asks whether consumers’ home buying attitudes explain the behaviour of home sales by focusing on two tranquil and two uncertain periods within 1978–2015. We utilize monthly data to formulate and estimate four augmented autoregressive models with the results indicating that improvements (deteriorations) in consumers’ home buying attitudes lead to higher (lower) home sales. This conclusion remains unchanged when controlling for economic and financial indicators often cited as determinants of home sales. Overall, our article has key implications for future studies aiming to forecast home sales using attitudinal measures.