Notes on the use of data transformations.

By Jason W. Osborne. 2002

733 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Epidemiology

View Paper: https://www.semanticscholar.org/paper/e7500414ed6006a2e7e93efe0db80b3e5e3e6d99

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Epidemiology

Citations in the corpus

Mothers' Acculturation and Beliefs About Emotions, Mother–Child Emotion Discourse, and Children's Emotion Understanding in Latino Families (2011, methodology): “Therefore, a reflected square root transformation was used to normalize the distribution of enculturation scores (Osborne, 2002 ).”
Effective Analysis of Reaction Time Data (2008, background): “…researchers should be careful about transforming data, however, because it is possible to eliminate significant effects by transformation. there are also issues of interpretation after transformation of a variable, because the relationship among the variables has been changed (osborne, 2002).”
Assessing the long‐term impact of Ranavirus infection in wild common frog populations (2010, methodology): “This transformed data was then log10 transformed so that the residuals would follow a normal distribution (after log10 transformation the greatest population size loss was 0) (for a similar approach, see Osborne, 2002).”
The effect of distributed monitoring exercises and feedback on performance, monitoring accuracy, and self-efficacy (2006, methodology): “The scores were then returned to their original direction (following the procedure suggested in Osborne, 2002).”
Improving your data transformations: Applying the Box-Cox transformation (2010, methodology): “Thus a distribution to be transformed via this method should be anchored at 1.00 (the recommendation in Osborne, 2002) or higher.”
The Complexity of Public Attitudes Toward Sex Crimes (2017, unknown): “In order to account for this, these variables were transformed into their natural logarithm (Osborne, 2002).”
The Impact of Outliers on Cronbach’s Coefficient Alpha Estimate of Reliability: Ordinal/Rating Scale Item Responses (2010, background): “…to interpret because we would have to consider the natural log (or square root) of efficiency, which is not understood in the statistical mathematics literature—in short, the transformed variable needs to make sense in the research literature and is not just a statistical nicety (Osborne, 2002).”
Dyadic military conflict, security alliances, and bilateral FDI flows (2010, methodology): “…we follow the recommendation and practice of applied researchers in other Journal of International Business Studies fields (e.g., McDonald, 2008; Osborne, 2002): that is, to add some constant value that is just large enough to turn zero and negative values into positive ones before…”
Perceptions of Negative Workplace Gossip: A Self-Consistency Theory Framework (2018, result): “Fourth, although further analyses revealed that our results were not significantly affected (see Osborne, 2002), the distribution of perceived negative workplace gossip was positively skewed.”
Relation between language experiences in preschool classrooms and children's kindergarten and fourth-grade language and reading abilities. (2011, methodology): “We checked variable distributions for assumptions of normality, and subsequently used a log 10 transformation (Osborne, 2002) for the following variables: percentage teacher attention utterances in large group and large group percentage teacher utterance correcting.”
The power of outliers (and why researchers should ALWAYS check for them) (2004, background): “Osborne and Amy Overbay North Carolina State University There has been much debate in the literature regarding what to do with extreme or influential data points. The goal of this paper is to summarize the various potential causes of extreme scores in a data set (e.g., data recording or entry errors”
Modelos de equações estruturais em psicologia: conceitos e aplicações (2007, background): “Caso o pressuposto da normalidade não seja atingido, mesmo após a aplicação de procedimentos de transformação das variáveis (e.g. Osborne, 2002), o pesquisador pode optar por utilizar outros métodos de estimação, como o ADF.”
Too Much of a Good Thing? The Relationship Between Number of Friends and Interpersonal Impressions on Facebook (2008, methodology): “The similarity effect was examined post hoc through a multiple regression analysis in which social attractiveness scores were regressed on a term representing the interaction of the number of friends in the stimuli by respondents’ number of friends (adjusting the respondents’ friends count with a lo”