Stats test
Download as PPTX, PDF0 likes470 views
This document discusses the 6BIO8 biology exam paper and provides guidance on statistical tests that may be covered. It outlines the three questions on the exam: 1) based on practical experiments, 2) statistical tests like correlation, t-test, chi-square, Mann-Whitney U, and Wilcoxon, 3) planning an investigation. It then explains how to perform and interpret the statistical tests of correlation, t-test, chi-square, Mann-Whitney U, and Wilcoxon paired test. Guidance is provided on null hypotheses, critical values, and interpreting results for each test.
Stats test
- 1. WELCOME 6BIO8 – paper code 6B Paper discussion By.J.Sharmila Christy Biology Teacher , Villa International High School, Male’ Republic of Maldives
- 2. 6 B PAPER HAS 3 QUESTIONS Q1, Based on AS &A2 practical experiments Be thorough in doing these practical's , procedure, precautionary methods Q2. Statistical test 5 tests for calculating mean , median, mode & differences Q3. Planning an Investigation steps of doing, analysis & interpretation of data
- 3. STATISTICAL TESTS USED 1.Correlation Spearman Rank Test 3.Chi2 – Test Correlate between Goodness to fit factors 2.T – Test MEAN 4.Wilcoxon paired Match Test( W Test) For paired data 5.Mann Whitney ( U– Test ) MEDIAN
- 4. CORRELATION COEFFICIENT SIGNIFICANCE OF RELATIONSHIP BETWEEN 2 VARIABLES (DV & IDV ) EG: TEMPERATURE AND RATE OF ENZYME ACTION . SCATTERED GRAPH Null Hypothesis – There is no significant relationship between the independent and dependent variable If calculated value, at p = 0.05 , 5% significance level, is greater than critical value , REJECT Ho Degree of freedom = n-1 , n= no of measurements
- 5. GRAPH DV IDV
- 7. T-TEST USED IN CALCULATING MEAN VALUES DATA IS SHOWN IN NORMAL DISTRIBUTION GRAPH EG: TEMPERATURE AND RATE OF ENZYME ACTION . SCATTERED GRAPH Null Hypothesis : There is no significance difference between the mean value of set one and set two If calculated value > Critical value ,at p =0.05 (5%) REJECT Ho Degree of freedom = n-2
- 9. MANN WHITNEY ( U TEST ) Forcomparing the MEDIAN VALUE Data is not normally distributed , it is skewed Null Hypothesis : There is no significant difference between the median values of sample 1 & sample 2 There will be two values – U1 and U2 The smaller U value is the calculated value If calculated value > Critical value ,at p =0.05 (5%) ACCEPT Ho Degree of freedom = n-2
- 10. Median Factor/ unit
- 11. WILCOXON MATCHED PAIRED TEST W TEST Used to determine if the difference between two sets of data measuring the same variable Data must be matched in pairs Single unique way to link data from one set to another Eg, pulse rate before & after exercise Usually bar graphs , with bars in pairs
- 12. CHI 2 TEST Used to measure goodness of fit Used to test whether the difference between the observed values are significantly different from the expected value Usually bar graph in pairs Eg A rat is placed in such a cage probability of rat chosing the open door Exp ratio : N S E W 1 :1 :1:1 Obser ratio 9:11:8:12 Mostly used in genetic questions
- 13. NULL HYPOTHESIS : THERE IS NO SIGNIFICANT DIFFERENCE BETWEEN THE OBSERVED & EXPECTED VALUES After doing the chi2 test If calculated value > Critical value ,at p =0.05 (5%) REJECT Ho Conclusion : There is a significant difference between the observed and the expected value If calculated value < Critical value ,at p =0.05 (5%) ACCEPT Ho Conclusion : There is no significant difference between the observed and the expected value, any difference is due to chance alone
- 14. RULES TO REMEMBER FOR W U For T,Chi2, Corr Calculated Calculated Value >critical Value >critical value value ACCEPT Ho REJECT Ho