Error Bars and significance

One of the more frustrating things to me as young scientist is error bars and how to determine how may times I need to repeat an experiment. Towards this end, a great paper was recently published in the Journal of Cell Biology

Error Bars in Experimental Biology, Cummings, G., Fidler, F., and Vaux D.L. JCB, 2007, 177 (1) pg 7-11.

I would say that this article is a must read for all of us. It includes solid information on how to interpret other peoples data based on the error in the measurments shown. This is especially relevant to mouse and tissue culture studies.

If you want to discuss this paper please respond

In good taste

Rb

Nice find

I think this thread should be expanded if people could find and post nice articles on choosing the appropriate statistical tests for your data and when to apply each type.

I agree. Apparently my PI sent out this article to us saying it to be one of the best for biologists who have to deal with statistics. Should say a must.

Here are a few nice references that I run across:

For Microbiology....


D Kirchman, J Sigda, R Kapuscinski and R Mitchell
Statistical analysis of the direct count method for enumerating bacteria. Appl Environ Microbiol. 1982 August; 44(2): 376-382

ABSTRACT

The direct count method for enumerating bacteria in natural environments is widely used. This paper analyzes the sources of variation contributed by the various levels of the method: subsamples, filters, and microscope fields. Based on a nested analysis of variance, we show that most of the variance (less than 80%) is caused by the fields and that the filters contributed nearly all of the remaining variance. The replication at each of the levels determines the total cost and error of a measurement. We compared several sampling schemes, including an optimal strategy which gives the lowest possible variance for a given cost. We recommend that preparing one filter from one subsample is adequate only if the samples are closely spaced in time or distance; otherwise, one filter should be prepared from two or preferably three subsamples. This sampling scheme emphasizes the importance of the highest level of replication. Our analysis shows that the accuracy of the direct count method can be substantially improved (by 20 to 50%) without a large increase in cost when the proper degree of replication at each level is performed.

N. Fromin, J. Hamelin, S. Tarnawski, D. Roesti, K. Jourdain-Miserez, N. Forestier, S. Teyssier-Cuvelle, F. Gillet, M. Aragno, P. Rossi. Statistical analysis of denaturing gel electrophoresis (DGE) fingerprinting patterns. Environmental Microbiology 4 (11), 634643

Summary

Technical developments in molecular biology have found extensive applications in the field of microbial ecology. Among these techniques, fingerprinting methods such as denaturing gel electrophoresis (DGE, including the three options: DGGE, TGGE and TTGE) has been applied to environmental samples over this last decade. Microbial ecologists took advantage of this technique, originally developed for the detection of single mutations, for the analysis of whole bacterial communities. However, until recently, the results of these high quality fingerprinting patterns were restricted to a visual interpretation, neglecting the analytical potential of the method in terms of statistical significance and ecological interpretation. A brief recall is presented here about the principles and limitations of DGE fingerprinting analysis, with an emphasis on the need of standardization of the whole analytical process. The main content focuses on statistical strategies for analysing the gel patterns, from single band examination to the analysis of whole fingerprinting profiles. Applying statistical method make the DGE fingerprinting technique a promising tool. Numerous samples can be analysed simultaneously, permitting the monitoring of microbial communities or simply bacterial groups for which occurrence and relative frequency are affected by any environmental parameter. As previously applied in the fields of plant and animal ecology, the use of statistics provides a significant advantage for the non-ambiguous interpretation of the spatial and temporal functioning of microbial communities.

And for Molecular Biology...


V Brendel, P Bucher, IR Nourbakhsh, BE Blaisdell and S Karlin. Methods and Algorithms for Statistical Analysis of Protein Sequences. Proceedings of the National Academy of Sciences, Vol 89, 2002-2006.

Abstract:

We describe several protein sequence statistics designed to evaluate distinctive attributes of residue content and arrangement in primary structure. Considered are global compositional biases, local clustering of different residue types (e.g., charged residues, hydrophobic residues, Ser/Thr), long runs of charged or uncharged residues, periodic patterns, counts and distribution of homooligopeptides, and unusual spacings between particular residue types. The computer program SAPS (statistical analysis of protein sequences) calculates all the statistics for any individual protein sequence input and is available for the UNIX environment through electronic mail on request to V.B. (volker@gnomic.stanford.edu).



M. Kathleen Kerr and Gary A Churchill.
Statistical design and the analysis of gene expression microarray data. Genetical Research (2001), 77: 123-128.

Abstract:

Gene expression microarrays are an innovative technology with enormous promise to help geneticists explore and understand the genome. Although the potential of this technology has been clearly demonstrated, many important and interesting statistical questions persist. We relate certain features of microarrays to other kinds of experimental data and argue that classical statistical techniques are appropriate and useful. We advocate greater attention to experimental design issues and a more prominent role for the ideas of statistical inference in microarray studies.

And for design of experiments...

Robert O. Kuehl (ed). Design of Experiments: Statistical Principles of Research Design and Analysis, 2nd Ed. Brooks/Cole, 2000.

he second edition of Design of Experiments: Statistical Principles of Research Design and Analysis by Robert O. Kuehl is an excellent introduction to the methods of research design. The book emphasizes application but provides sufficient theory for a basic understanding of the statistical principles involved. College algebra and basic probability and statistics are sufficient mathematical background for readers of this book.

Chapter 1 emphasizes performing good science through proper planning and research design. Kuehl explains the importance of starting with your research hypothesis, understanding sources of variation, understanding the difference between experimental units and observational units, and the benefits from using replication, randomization, blocking, controls, and covariates.

Chapter 2 goes through all the nuts and bolts of ANOVA clearly and precisely. Chapter 3 covers multiple treatment comparisons. Chapter 4 discusses diagnostic methods for testing model assumptions. Chapters 57 explain factorial and nested treatments designs for fixed, random, and mixed models. The remaining chapters (817) are devoted to more complicated experimental designs: complete block, incomplete block, fractional factorial, split plot, repeated measures, crossover, and ANCOVA.

Throughout the text, examples and exercises come from research in life sciences, agriculture, engineering, industry, and chemistry. This book is ideal for research professionals learning research design and ANOVA. Unlike with many texts, the goal of providing answers to real research hypotheses does not get lost in presenting the mathematical details.



Wu JC, Hamada M, Joseph V. A Review of: Experiments: Planning, Analysis, and Parameter Design Optimization. IIE Transactions, Volume 38, Number 6, June 2006, pp. 521-522(2).

Dear all, I was going through a validation protocol for bioassy, i have come across a statistical measurement of % RE or absolute mean bias. The parer says %RE ( Absolute mean bias) should be less than 10% as an acceptance criteria for Precision and accuracy. Kindly provide me more details into this and help me with the formula to calculate the same Thanx n regds jith

Jith sn

can you start a new topic with your question and give it a good title please. Its hard for other to see your question in a long thread such as this one.

Rb