Ryan Cummings and Ernie Tedeschi have a really attention-grabbing article in BriefingBook right now which casts new gentle on the disjuncture between measured sentiment and standard macroeconomic indicators. Cummings and Tedeschi doc how the transfer to on-line sampling has altered the traits of the College of Michigan Financial Sentiment sequence.
…we imagine on-line respondents are ensuing within the degree of the general sentiment and present circumstances indices being meaningfully decrease, making newer UMich knowledge factors inconsistent with pre-April 2024 knowledge factors. Particularly, we use a easy statistical mannequin to estimate that the impact of the methodological change from telephone to on-line is at present leading to sentiment being 8.9 index factors –or greater than 11 p.c–decrease than it might be if interviews have been nonetheless collected via the telephone.
To exhibit that the change to on-line surveying has imparted a structural break within the UMich sequence, they examine towards the Morning Seek the advice of sequence.
Supply: Cummings and Tedeschi (2024).
Â
The Morning Seek the advice of survey has been on-line, so it serves as a management. Therefore, the important thing cause for the shift in measured sentiment.
A cursory have a look at the weighted age distribution of telephone and on-line assignments means that, no, they weren’t random in apply. For instance, on-line respondents have been extra more likely to be older in these transition months, which could have an effect on their sentiment responses. …
A extra formal multilevel logit mannequin–which measures the chance of a person being in a sure age cohort after accounting for different demographic components–confirms this distinction. Respondents 65+ for instance had a 52 p.c probability of being within the on-line group in April-June, which is greater than twice as doubtless as respondents 18-24, and this distinction is statistically important …
I don’t understand how the larger presence of older respondents interacts with the partisan divide examined in this publish (are Republican/lean Republican voters older than corresponding Democratic/lean Democratic respondents?)
What I can say is that the adjusted Cummings-Tedeschi sequence displays much less proof of a structural break than the official UMichigan sequence, when utilizing as regressors unemployment, y/y CPI inflation and the SF Fed information sentiment index.
Take into account these two regressions, first with the official sequence, and the second with the Cummings-Tedeschi adjusted sequence:
Now contemplate the respective recursive 1-step forward Chow exams for stability.
Be aware that whereas each regressions exhibit instability round 2020 and 2023, the Cummings-Tedeschi adjusted sequence displays no structural break in 2024 across the change to on-line polling.
That being mentioned, the change in survey strategies doesn’t absolutely clarify absolutely the hole between observables and sentiment. I estimate the regression over the 2016-2024M03 interval, and predict out of pattern for 2024M04-M10.
Determine 1: College of Michigan Shopper Sentiment (daring black), Cummings-Tedeschi adjusted sequence (gentle blue), fitted (purple), +/- one customary error (grey strains). NBER outlined peak-to-trough recession dates shaded grey. Supply: U.Michigan through FRED, BriefingBook, NBER and writer’s calculations.
So probably lower than half of the hole is accounted for by the change in survey strategies.
Â
