Experimental error: Under "Analytical resources," review "error analysis and significant figures" and "error representation and curvefiting."
Statistical tests: [Unpaired (independent) t test] [paired t test] [Chi-squared test] [sample problems] [solutions to sample problems]
Tables: ['Student's' t distribution] [Chi-squared critical values]

Selected Statistical Methods for the Biosciences Errors using inadequate data are much less than those using no data at all. --- Charles Babbage (1792-1871) Statistics are designed to draw conclusions from data that are subject to experimental error. When replicate sampling is necessary, a carefully chosen statistical analysis can save the investigator the trouble of performing unnecessary experiments, or the embarrassment of drawing a premature or inappropriate conclusion. Statistics generally yield a probability value for a particular outcome. As a rule, scientists accept a probability of 0.05 or less as convincing evidence that a particular outcome is unlikely. Information on selected types of statistical analysis is presented on these pages. Do not expect a rigorous explanation of the theory behind each type of analysis. The articles will focus on an understanding of the principles behind the analyses, and on their proper use.