scholarly journals Treatment of Multivariate Outliers in Incomplete Business Survey Data

2016 ◽  
Vol 45 (1) ◽  
pp. 3-23 ◽  
Author(s):  
Marc Bill ◽  
Beat Hulliger
Keyword(s):  
Outlier Detection ◽  
Survey Data ◽  
Missing Values ◽  
R Package ◽  
Living Condition ◽  
The European Union ◽  
Multivariate Outlier Detection ◽  
Advantages And Disadvantages ◽  
Business Survey Data ◽  
Business Survey

The distribution of multivariate quantitative survey data usually is not normal. Skewed and semi-continuous distributions occur often. In addition, missing values and non-response is common. All together this mix of problems makes multivariate outlier detection difficult. Examples of surveys where these problems occur are most business surveys and some household surveys like the Survey for the Statistics of Income and Living Condition (SILC) of the European Union. Several methods for multivariate outlier detection  are collected in the R-package modi. This paper gives an overview of modi and its functions for outlier detection and corresponding imputation. The use of the methods is explained with a business survey dataset. The discussion covers pre- and post-processing  to deal with skewness and zero-inflation, advantages and disadvantages of the methods and the choice of the parameters.

Quantifying Measurement Errors in Partially Edited Business Survey Data

2017 ◽  
pp. 319-337
Author(s):  
Thomas Laitila ◽  
Karin Lindgren ◽  
Anders Norberg ◽  
Can Tongur
Keyword(s):  
Survey Data ◽  
Measurement Errors ◽  
Business Survey Data ◽  
Business Survey

The Determinants of Sticky Prices and Sticky Plans: Evidence from German Business Survey Data

2014 ◽  
Vol 15 (3) ◽  
pp. 353-373 ◽  
Author(s):  
Heike Schenkelberg
Keyword(s):  
Survey Data ◽  
State Dependence ◽  
Empirical Literature ◽  
Price Setting ◽  
Firm Level ◽  
Data Set ◽  
Price Increases ◽  
Business Survey Data ◽  
State Dependent ◽  
Business Survey

Abstract So far, there is no consensus on the price adjustment determinants in the empirical literature. Analyzing a novel firm-level business survey data set, we provide new insights on the price setting behavior of German retailers during a low inflation period. Relating the probability of both price and pricing plan adjustment to time- and state-dependent variables, we find that state-dependence is important; the macroeconomic environment as well as the firm-specific condition significantly determines the timing of both actual price changes and pricing plan adjustments. Moreover, input cost changes are important determinants of price setting. Finally, price increases respond more strongly to cost shocks compared to price decreases.

Seasonal and Cyclical Properties of Ifo Business Test Variables / Saisonale und zyklische Eigenschaften von ifo Konjunkturtest Variablen

2003 ◽  
Vol 223 (5) ◽  
Author(s):  
Gebhard Flaig
Keyword(s):  
Survey Data ◽  
Seasonal Pattern ◽  
Business Climate ◽  
Unobserved Components ◽  
Empirical Results ◽  
Business Survey Data ◽  
Unobserved Components Model ◽  
Business Survey ◽  
Working Day ◽  
Over Time

SummaryIn this paper, an Unobserved Components Model is used to decompose the balances of Ifo Business survey data into the cyclical, the seasonal and the irregular components, as well as the working day effect. The empirical results show that the total cycle consists of three subcycles with about 3, 5 and 11 years. Each subcycle of the assessment variable is “similar” to the corresponding subcycle of the expectations variable. The seasonal pattern is changing over time and the working day effect is significant for the assessment of the current business situation and for the Ifo Business Climate, but not for the expectation series.

Sign in / Sign up

Export Citation Format

Share Document