Assignment 2: LASA: Research Proposal Project

Haukoos, J. S., & Lewis, R. J. (2015). Advanced statistics: bootstrapping confidence intervals for statistics with “difficult” distributions. Academic emergency medicine, 12(4), 360-365.

This article by Haukoos and Lewis describe how to use confidence intervals in reporting research results which the authors acknowledge to have increased in use and as a requirement for scientific journal editors. The article explores a number of resources that describe methods of computing statistical confidence intervals for descriptive statistics that have descriptions that are not easy to mathematically represent which is a challenging task. The article is relevant to the topic matter in that it describes the methods along with how the resources availed describing the computing methods for descriptive statistics. The authors propose the use of bootstrap technique which they argue allows a researcher to make inferences from data without making strong assumptions about distribution of the data or the statistics under calculation. The strengths of the article include the fact that it describes the bootstrapping concept and demonstrates how to estimate confidence intervals for the median and the spearman rank correlation coefficient for data not normally distributed. the weakness of this resource is the fact that it does not generally describe how to compute descriptive statistics but narrows down to describing how to compute descriptive statistics confidence intervals. The article used a qualitative research method on a clinical study that used two commonly used statistical software packages of strata and SAS in its discussion of limitations of the bootstrap.

Team, R. C. (2013). R: A language and environment for statistical computing.

The document by Andy Bunn and Mikko Korpela describes the basic features of dendrologists program library in R, which is in itself a package used by dendrologists to handle the processing and analysis of data. The document follows the basic steps an analyst follows when working with a new tree-ring data set. This document is a vignette commences by describing how to read in ring widths and how to plot them. The vignette is relevant in this study as it describes a number of methods available for trending and detrending and shows how to extract basic descriptive statistics. It also shows how to build and plot a simple chronology of the mean value. The building of the mean-value chronology is shown in the vignette using the expressed signal; of the population from the detrended ring widths as a way of doing complicated computing by the use of The Dendrochronology Program Library in R (dplR). The vignette highlights how to work with most basic activities in tree-ring data and the steps followed including data reading, detrending, building chronology and using descriptive statistics ploratory data analysis. The document strength of the paper includes the fact that it explores one way of computing descriptive statistics and avails for information on computing and analyzing descriptive statistics in the help files and in the literature sections. The weakness of the paper is approaching only one method of descriptive data computing rather than directly addressing the research problem. The vignette uses literature review to address its research problem.

Norušis, M. J. (2016). SPSS 14.0 guide to data analysis. Upper Saddle River, NJ: Prentice Hall.

This book by Norusis is a guide to the analysis of data and SPSS. The book gives a jump-start to readers on how to describe data, test hypotheses and examine relationships though SPSS. The book provides an introduction to the data computing and to SPSS focusing on topics that interest modern-day students and the use of the internet in today’s society. The book uses SPSS 14.0 and includes the student version and data CD. The book is relevant to the study in that it not also serves to introduce learners to data analysis and its methods but also incorporate a plethora of data including internet usage studies, general social survey, criminal justice system opinions, marathon running times, the importance of manners and library patronage. The strength of the book in relation to this research is that it generally describes methods of computing descriptive data and also incorporates and guides in using SPSS to compute descriptive data.

McKinney, W. (2010, June). Data structures for statistical computing in python. In Proceedings of the 9th Python in Science Conference (Vol. 445, pp. 51-56).

The paper goes through the practical issues around working with data sets common to statistics and finance and other related fields. The book facilitates working with these data sets and therefore provides a set of building blocks fundamental to implementing statistical models. It also discusses specific design issues that researchers and analysts are likely to encounter when developing scientific applications such as python. It concludes by discussing possible future directions for computing statistical data suing python and other means relevant to descriptive statistics. The relevance of the paper to the research question lies on the fact that it approaches ways to compute descriptive data. The biggest strength in relation to this research is that it addresses methods of descriptive data computing. The weaknesses include the fact that it enjoins methods of computing descriptive data among other types of data. The paper uses literature review in its pursuit to explore data computing.