Skip to main content
ARS Home » Research » Publications at this Location » Publication #165791
Title: PRICING MISSING DATA IN THE MISSISSIPPI DELTA.

Author
item YADRICK, KATHY - DELTA NIRI
item CONNELL, CAROL - DELTA NIRI
item GOSSETT, JEFF - DELTA NIRI
item SIMPSON, PIPPA - DELTA NIRI
item JO, CHAN-HEE - DELTA NIRI
item HUANG, EMMA - UNIV NORTH CAROLINA, BIOS
item Bogle, Margaret

Submitted to: Meeting Proceedings
Publication Type: Abstract Only
Publication Acceptance Date: 4/23/2004
Publication Date: 6/10/2004
Citation: Gossett, J., Simpson, P., Jo, C.H., Huang, B.E., Bogle, M., Yadrick, K., Connell, C. 2004. Pricing missing data in the Mississippi Delta [abstract]. Third Annual Conference of the International Society of Behavioral Nutrition and Physical Activity. p. 23.

Interpretive Summary:

Technical Abstract: Purpose: To use multiple imputation of missing prices so that prices of a market basket of food items in types of stores can be estimated and compared. Without imputation, even one missing food item would result in the exclusion of the entire store. Background: To assess the accessibility, availability, and cost of food items necessary for a healthy diet, a survey of food stores was conducted by the Lower Mississippi Delta Nutrition Intervention Research Initiative (Delta NIRI*) in rural Delta counties of Arkansas, Mississippi, and Louisiana. In this paper we address the estimation of the cost of a market basket of food items such as the Thrifty Food Plan basket. Basket items, and therefore prices, are not available at all stores. We discuss some approaches to the imputation of missing food item prices. Methods: Since we are sampling from a finite population, most commonly used procedures are not appropriate for the estimation of correct standard errors. We show how this may be done using existing software. For each of 5 sets of imputed data, we estimate the mean cost of the market basket and then use multiple imputation methods developed by Rubin and others to combine mean price and variance estimates. Conclusion: Imputing data may give additional useful information for pricing food baskets, and indeed for nutrition surveys. Methods are now available to do this correctly and relatively easily. Acknowledgements: This work was funded under the Lower Mississippi Delta Nutrition Intervention Research Initiative, USDA ARS grant #6251-53000-003-00D.