Zebrafish Research Data Analysis Choices Data Analysis Statistical
Zebrafish Research Data Analysis Choices
Data Analysis • Statistical Analysis Dealing With Population Frequency and Proportions (Percentages) – Two-proportion z-test – comparison of two population proportions (percentages) Value as (%) of total population • Calculator http: //www. socscistatistics. com/tests/ztest/ • Example 6 -OHDA+DETA 100 90 80 70 60 50 40 30 20 10 0 24 h 48 h Treatment Time lapsed 2
Data Analysis • Statistical Analysis Dealing With Population Frequency and Proportions (Percentages) – Comparison of multiple population proportions (percentages) – a two-step process • Step 1: Contingency tables, chi-square approach - Use Chi. Square (χ2) analysis of contingency tables to compare the numbers of individuals of two or more groups that fall into two or more different categories. – See 7. 3 Chi-square Analysis of Contingency Tables for more information. – This step will tell you if there are significant differences among the various population proportions but not between specific pairs of proportions – Chi-square contingency tables calculator http: //graphpad. com/quickcalcs/chisquared 1. cfm 3
Data Analysis • Step 2: Marascuilo's post hoc analysis following the chi-square test • The Marascuilo procedure allows for the simultaneous testing the differences between all pairs of proportions when there are several populations under investigation (more than two). – Marascuilo's Post Hoc Analysis description » http: //itl. nist. gov/div 898/handboo k/prc/section 4/prc 474. htm 120 % Response to Probing • Statistical Analysis Dealing With Population Frequency and Proportions (Percentages) – Comparison of multiple population proportions (percentages) – a twostep process p>0. 05 p<0. 05 100 80 60 40 48 hours 20 0 ERS Control 10 m. M L 50 µM DOPA n. NOSI Treatment L-DOPA + n. NOSI 4
Z Test Calculator for Multiple Proportions • Z test calculator for multiple proportions - https: //www. mccallum-layton. co. uk/tools/statisticcalculators/z-test-for-proportions-independent-groupscalculator/
Data Analysis • Statistical Analysis Dealing With Two or more data sets (non-percentages/proportions) – T - test – compares the means of two groups of numerical values (not proportions/percentages). • Calculator - http: //www. graphpad. com/quickcalcs/ttest 1. cfm • Example 35 Pod Length (cm) 30 25 20 15 10 5 0 Brazil Country Mexico 6
Data Analysis • Statistical Analysis Dealing With Two or more data sets (non-percentages/proportions) – Step 1 ANOVA - compares three or more group means to determine if there is a significance among group means • Calculator - http: //danielsoper. com/statcalc 3/calc. aspx? id=43 – Step 2 – a post hoc test must then be run to determine the differences between all pairs of means (Tukey test) • Calculator – http: //faculty. vassar. edu/lowry/hsd. html - four means – http: //graphpad. com/quickcalcs/posttest 1. cfm - multiple means 7
Data Analysis • Statistical Analysis Dealing With Two or more data sets (non-percentages/proportions) – ANOVA + Tukey post hoc test- compares three or more group means, a two step process – http: //faculty. vassar. edu/lowry/hsd. html calculator - four means • Example 8
Data Analysis • Standard error of the mean – The Standard Error is the term used in statistics to refer to an estimate of that standard deviation, derived from a particular sample used to compute the estimate. Represented as ±SEM – Every statistic has a standard error associated with it. A measure of the accuracy of the statistic can be derived that the standard error of 0 represents that the statistic has no random error and the bigger represents less accuracy of the statistics. – SEM calculator http: //ncalculators. com/statistics/standard-errorcalculator. htm
Standard Deviation Calculator • http: //www. calculator. net/standard-deviation -calculator. html • For Z test https: //www. easycalculation. com/standarddeviation-of-percentages. php
Data Analysis • How to place error bars on figures using Excel – Tutorial http: //www. extendoffice. com/documents/excel/86 3 -excel-add-remove-error-bars. html
Data Analysis Statement • Writing a data analysis section for material and methods analyzing population proportions/percentages and numerical values (example): – Statistical analysis was performed using Sigma. Stat 3. 5 software, Microsoft Excel, and Vasser. Stats analysis website. Heart rate and blood vessel data was entered into either an ANOVA one-way paired t-test or ANOVA Single Factor tests. For the ANOVA analysis a Holm–Sidak post hoc method was also run to determine significant differences between the various treatment groups. Percent survival and arrhythmic heart rate data were analyzed using either by a z-test for two population proportions or for multiple proportions using a chi-square contingency table test, followed by a Marascuilo’s post hoc analysis. Sample sizes for all n = 30. All experiments were repeated in triplicate. 12
- Slides: 12