All submissions of the EM system will be redirected to Online Manuscript Submission System. Authors are requested to submit articles directly to Online Manuscript Submission System of respective journal.

Statistics for food production

Stacy Miller

1Editorial office, Statistics and Mathematics, India

Corresponding Author:
Stacy Miller
Editorial office, Statistics and Mathematics, India.
E-mail: mathematicsstat@scholarlymed.com

 

Visit for more related articles at Research & Reviews: Journal of Statistics and Mathematical Sciences

Abstract

Researchers can employ statistical tools at any stage of their research, from planning through publication. We must keep in mind, however, that statistics are meaningless if the study is poorly organized. Incorrect use of statistical methods, on the other hand, results in erroneous results. The consistency of the experiment design and statistical analysis of the results determines the quality of the investigation's findings and conclusions. Better quality inquiry planning, conducting, and reporting is usually attained at research institutions where scientists and experienced statisticians collaborate. In the vast majority of cases, nevertheless, researchers use statistical methodologies based on their expertise and intuition. Up to 70% of study articles used or interpreted statistics incorrectly, according to assessments of biological and agricultural journals published around the turn of the century.

Introduction

We can expect the situation to have improved in recent years. From 2013 to 2017, I analyzed my comments on research articles for various agricultural publications and discovered that 55 percent of the manuscripts could be improved if statistics results of the analysis were used and interpreted differently. The conclusions of the investigation are comparable. In a few volumes of the Journal of the American Society for Horticultural Science (JASHS), they looked at publications. Almost half of the papers looked at had problems with the use of experimental statistics. Mistakes in experiment design and the application of statistical methods can also be found in articles from other domains. Only 59 percent of papers published in the United Kingdom and the United States that report animal research data stated the hypotheses or objectives, 87 percent did not use randomization, and only 70% of the publications had information on measures of error or variability, according to the findings of a survey of papers published in the United Kingdom and the United States that report animal research data.

During the planning stage of an inquiry, several errors are common. Statistical methods are routinely applied in ways that are not in accordance with the experimental design. In other cases, authors focus an excessive emphasis on statistical approaches while failing to describe the biological importance of the research findings. Frequently, there isn't enough information provided about how the statistical analyses were conducted. The goal of this research is to emphasize the most significant parts of regularly used statistical methods in plant and crop research, as well as make advice for how to apply them effectively at all stages of the investigation.

In-plant and crop research, proper application of experimental statistics is critical. The results of surveys of research papers published in agricultural and biological journals demonstrate that writers frequently misuse or misinterpret statistics. In most cases, researchers do not pay enough attention to the proper application of statistics. Throughout the investigation, the purpose of this study is to highlight the most important aspects of commonly used statistical approaches in the study of plants and crops. The study covers the research design and statistical analysis, as well as basic assumptions and transformations, ANOVA application, regression and correlation analyses, and research findings presentation. There are suggestions about how to use statistical approaches properly at all levels of crop research. This document does not discuss statistical methods other than ANOVA and regression, which require more advanced computer packages to implement.