Presentation is loading. Please wait.

Presentation is loading. Please wait.

Statistical Analysis. Null hypothesis: observed differences are due to chance (no causal relationship) Ex. If light intensity increases, then the rate.

Similar presentations


Presentation on theme: "Statistical Analysis. Null hypothesis: observed differences are due to chance (no causal relationship) Ex. If light intensity increases, then the rate."— Presentation transcript:

1 Statistical Analysis

2 Null hypothesis: observed differences are due to chance (no causal relationship) Ex. If light intensity increases, then the rate of photosynthesis will not be affected Alternative hypothesis: states that a causal relationship exists between independent variable and observed data Ex: If light intensity increases, then the rate of photosynthesis will increase In statistics, the world is null until proven alternative Null vs. Alternative Hypothesis

3 A mean is an average of all data points in a set A median is the middle value in a data set A mode is the most common value in a data set Percent difference shows the difference between the means of the experimental and control groups % difference = (│experimental – control│/ control) x 100 Standard deviation is the average measure of how much each value differs, or deviates, from the mean With 2 data sets, you could have the same mean but very different standard deviations. A small standard deviation shows more consistency Mean, Median, Mode, % Difference, & Standard Deviation

4 Formula for Standard Deviation What does this mean? Mean N = Total # of values Each individual value

5 SD example Data Set 1: 4,4,4,4,4,6,6,6,6,6,5,5,5,5,5 Data Set 2: 5,5,5,4,4,6,6,3,3,7,7,1,1,9,9 Both sets have an identical mean…which data set has a smaller standard deviation? Set 1 has less spread around the mean, which would give it a lower standard deviation

6 Mean and SD For our data sets: Set 1: Mean = 5, SD = 0.8 Set 2: Mean = 5, SD = 2.4 What these numbers really mean is that, given a normal (bell curve) distribution, 68% of data points fall within 1 SD of the mean, and 95% fall within 2 standard deviations Precision of Data- BE CONSISTENT

7

8 Which data set is more useful? Why?

9 Error Bars When we graph our data, we can use error bars to show the SD for each mean What is the approximate standard deviation of meal worms per tray in the canopy cover group at 4 m from cover?

10 Error Bars When we graph our data, we can use error bars to show the SD for each mean What is the approximate standard deviation of meal worms per tray in the canopy cover group at 4 m from cover? Answer: ~1 mealworm per tray

11 Chi-square Analysis A chi-square analysis tests the significance of results Answers the question: were the differences in the means large enough to reject the null hypothesis (and support the alternative hypothesis)? Tests the probability of observed differences being random and NOT due to the independent variable In the chi-square formula, the expected (e) values are those that you would expect if the null were true. o = observed values e= expected values

12 A p-value of.05 means there is a 5% chance that the difference between observed and expected data is random (95% chance that there is a significant difference) Critical value – predetermined value establishing boundary for rejecting/accepting null hypothesis Maximum chi-square value that would fail to reject null hypothesis (i.e., chi-square value higher than the critical value shows support for the alternative hypothesis) Critical values will be provided in a chi-square table Dependent on degrees of freedom: number of possible outcomes minus 1 (d = N – 1) Null vs. Alternative Hypothesis

13 CHI-SQUARE DISTRIBUTION TABLECritical values Accept Null Hypothesis (difference due to chance) Reject Null Hypothesis Probability (p-value) Degrees of Freedom 0.950.900.800.700.500.300.200.100.050.010.001 10.0040.020.060.150.461.071.642.713.846.6410.83 20.100.210.450.711.392.413.224.605.999.2113.82 30.350.581.011.422.373.664.646.257.8211.3416.27 40.711.061.652.203.364.885.997.789.4913.3818.47 51.141.612.343.004.356.067.299.2411.0715.0920.52 61.632.203.073.835.357.238.5610.6412.5916.8122.46 72.172.833.824.676.358.389.8012.0214.0718.4824.32 82.733.494.595.537.349.5211.0313.3615.5120.0926.12 93.324.175.386.398.3410.6612.2414.6816.9221.6727.88 103.944.866.187.279.3411.7813.4415.9918.3123.2129.59

14 Chi-square Analysis For example, using a p-value of.05 and 3 degrees of freedom, a chi-square value must be greater than __________ (the critical value) to reject the null hypothesis and support the alternative hypothesis. Put another way, a calculated chi-square value that is greater than 7.82 means there is a greater than 95% chance that there is a significant difference between the observed and expected data (less than 5% chance that the difference is random).

15 1.1.5 T-test A T-test determines whether or not there is a significant difference between 2 samples Assume we’re measuring wing span of 2 populations of eagles, 1 wild and 1 captive bred We want to know if the difference between the lengths is significant (as opposed to being due to chance)

16 1.1.5 T-test Captive: 180 cm, 187, 212, 196, 200, 204, 194, 189 Wild: 188, 205, 201, 214, 194, 189, 206, 203 Degrees of Freedom = 8 + 8 – 2 = 14 When we apply the T-test, and use a T value chart, we obtain a 66% confidence level that the differences are significant. Not enough. We need a confidence level of 95%, with a minimum sample size of 5.

17 1.1.6 Correlation and Causality Simply because data shows a correlation does not imply causation. Causation requires that one variable causes the other to occur. The number of cavities in children shows a strong positive correlation with their vocabulary level. ? We should not assume that well spoken children will have dentures by college.

18 Stats Quiz 1. Define standard deviation as required on the syllabus. (2) 2. State the usefulness of knowing a standard deviation. (2) 3. Give the minimum confidence level for results to be significant in science. (1) 4. If I told you that, based on measurements in a previous class, that blue haired people are hard of hearing, how would you respond (regarding the relationship)? (2)

19 Stats Quiz Answers 1. Summarize spread of values around mean, 68% of data lies within 1 SD of mean (95% within 2) 2. Comparing samples/ data points, large SD = bad, low SD = consistent 3. Greater than 95% 4. Just because there is correlation does not imply causation.


Download ppt "Statistical Analysis. Null hypothesis: observed differences are due to chance (no causal relationship) Ex. If light intensity increases, then the rate."

Similar presentations


Ads by Google