Understanding Differences in Self-Reported Expenditures between Household Scanner Data and Diary Survey Data: A Comparison of Homescan and Consumer Expenditure Survey

Zhen, Chen; Taylor, Justin L.; Muth, Mary K.; Leibtag, Ephraim S.

doi:10.1111/j.1467-9353.2009.01449.x

Cited by 82 publications

(84 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2005, average weekly household spending on food and alcohol in the Worldpanel was £42.52, compared to £53.15 in the budget survey -a difference of some 20%. However, in contrast to the Zhen et al (2009) study, they found little difference across commodities in these expenditure gaps and thus very similar patterns of spending in the two surveys. The exception was alcohol, where Worldpanel spending was just 58% of LCF levels compared to 71% to 86% across other food groups.…”

Section: Previous Researchcontrasting

confidence: 43%

“…If there were clear 'modal' effects of scanner technology we might expect the results to be quite similar across countries; instead, it seems that the particular features of each dataset might be most crucial in driving findings in different countries. Of course, the comparison we make here is not identical to that made in Zhen et al (2009) in terms of the covariates for which we can control or the selection of households, for example. One area for future work might be to explore cross country comparisons of scanner and budget survey data using, as far as possible, identical methods.…”

Section: Distributions Of Spending and Budget Sharesmentioning

confidence: 99%

“…One issue raised by a number of papers and commentators relates to quota sampling methods used in scanner data (Tucker, 2011;Zhen et al, 2009;USDA, 2009;Harris, 2005). National budget surveys use random probability or stratified sampling instead.…”

Section: Previous Researchmentioning

confidence: 99%

“…Alcohol and tobacco spending was only half that reported in the CE. Zhen et al (2009) also compare Homescan and CE data, this time for 2002-2005. They map expenditures into 18 categories.…”

Section: Previous Researchmentioning

confidence: 99%

“…Interestingly, results from the US and UK reach different conclusions about the extent to which demographics account for the differences in spending. Zhen et al (2009) use a regression model to strip out observable demographic differences between datasets and argue that, in combination with the random weight issue, this largely accounts for the spending differences. Leicester and Oldfield (2009) conclude that demographic differences accentuate the gaps between datasets.…”

Section: Previous Researchmentioning

confidence: 99%

See 4 more Smart Citations

How might in-home scanner technology be used in budget surveys?

Leicester¹

2012

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. We find that levels of spending are significantly lower in scanner data. A large part (but not all) of the gap is explained by weeks in which no spending at all is recorded in scanner data. Demographic differences between the surveys accentuate rather than close the gap. We also demonstrate that patterns of expenditure across the surveys are much more similar, as are Engel curves relating food commodity budget shares to total food expenditures. A key finding is that the period over which we observe households in the scanner data significantly alters the distribution, but not the average, of weekly food expenditures and budget shares, which has important implications for whether two-week spending diaries common to budget surveys are giving a truly accurate reflection of a household's typical spending patterns. A second, more involved use of scanner data would be to impute detailed commodity-level expenditure patterns given only information on total expenditures, as a way of reducing respondent burden in budget surveys. We find that observable demographics in the scanner data explain little of the variation in store-specific expenditure patterns, and so caution against relying too heavily on imputation. Terms of use: Documents inJEL Classifications: C81, C83, D12

show abstract

Section: Previous Researchcontrasting

confidence: 43%

Section: Distributions Of Spending and Budget Sharesmentioning

confidence: 99%

Section: Previous Researchmentioning

confidence: 99%

“…Alcohol and tobacco spending was only half that reported in the CE. Zhen et al (2009) also compare Homescan and CE data, this time for 2002-2005. They map expenditures into 18 categories.…”

Section: Previous Researchmentioning

confidence: 99%

Section: Previous Researchmentioning

confidence: 99%

See 3 more Smart Citations

How might in-home scanner technology be used in budget surveys?

Leicester¹

2012

View full text Add to dashboard Cite

show abstract

Improving Survey Measurement of Household Finances: A Review of New Data Sources and Technologies

Jäckle

Couper

Gaia

et al. 2021

Advances in Longitudinal Survey Methodology

View full text Add to dashboard Cite

Did state‐mandated restrictions on sugar‐sweetened drinks in California high schools increase soda purchases in school neighborhoods?

Kiesel¹,

2021

Applied Eco Perspectives Pol

View full text Add to dashboard Cite

This paper evaluates the effectiveness of restrictions on sugar‐sweetened beverages (SSBs) in schools as a policy approach aimed at reversing the upward trend in obesity among adolescents. Specifically, we test if the implementation of SB 965 in California high schools led to detectable compensation effects outside of school by estimating changes in soda purchases observed in store‐level scanner data. Our unique data and identification strategy address data limitations of previously published studies, and our reported results strengthen the notion that preferences for unhealthy foods will persist even after their availability is restricted in select environments.

show abstract

Understanding Differences in Self-Reported Expenditures between Household Scanner Data and Diary Survey Data: A Comparison of Homescan and Consumer Expenditure Survey

Cited by 82 publications

References 36 publications

How might in-home scanner technology be used in budget surveys?

How might in-home scanner technology be used in budget surveys?

Improving Survey Measurement of Household Finances: A Review of New Data Sources and Technologies

Did state‐mandated restrictions on sugar‐sweetened drinks in California high schools increase soda purchases in school neighborhoods?

Contact Info

Product

Resources

About