Exercise Lab 6 Graphing and Data_Excel Steps-1

docx

School

Michigan State University *

*We aren’t endorsed by this school

Course

65.105

Subject

Statistics

Date

Feb 20, 2024

Type

docx

Pages

Uploaded by ChefKnowledgeOstrich33

Lab 6: Graphing and Data Analysis EXERCISE Exercise 1: Analyzing the Data For today’s lab, you will examine data from actual experiments conducted in the Fisher lab here at UNC. The hypothesis for the experiment is that the older life cycle stages will be more resistant to the effects of the pesticide cypermethrin. This pesticide is commonly used in agriculture to kill a wide variety of insect (arthropod) pests. However, it is a non-specific pesticide and, therefore, kills many different arthropods including copepods. Although it is a pesticide approved for use on land, much of it can run off into the oceans, and there has been very little testing to determine its effects on aquatic species. Therefore, this study was conducted to look at these effects, especially on the younger, and therefore potentially more vulnerable, life cycle stages. The life cycle stages examined were the naupliar and adult stages. For the experiment, nauplii were placed individually into wells of a 24 well plate. This means that each plate had 24 nauplii and each Nauplius was placed in its own well. The wells were filled with a mixture of seawater and cypermethrin, and the survival of each Nauplius was recorded after 48 hours. This was repeated for each life cycle stage, and then the entire experiment was repeated three times. The raw data are shown below (0 = dead, 1 = live): Naupliu s Experiment 1 Experiment 2 Experiment 3 Experiment 4 Well # Alive or Dead Alive or Dead Alive or Dead Alive or Dead 1 1 1 0 0 2 0 0 0 1 3 1 0 0 0 4 1 1 1 0 5 0 0 1 0 6 0 0 1 1 7 0 0 1 0 8 1 0 0 0 9 0 1 0 1 10 0 1 1 0 11 0 0 0 1 12 1 0 1 0 13 1 0 0 0 14 1 0 0 0 15 0 1 0 1 16 0 1 1 0 17 0 1 0 0 18 0 0 0 0 19 0 0 0 0 20 0 0 1 1 21 0 0 0 0 22 1 1 0 0 23 0 1 0 0 24 1 0 0 1

Adult Experiment 1 Experiment 2 Experiment 3 Experiment 4 Well # Alive or Dead Alive or Dead Alive or Dead Alive or Dead 1 1 0 0 0 2 1 1 0 1 3 1 1 1 1 4 0 0 1 1 5 0 0 1 1 6 0 1 1 0 7 1 1 1 1 8 1 1 1 1 9 1 1 0 1 10 1 0 1 1 11 1 1 1 0 12 0 1 1 1 13 1 1 0 1 14 1 0 1 1 15 0 1 0 1 16 1 1 1 0 17 1 1 1 0 18 0 1 0 1 19 1 0 0 1 20 1 1 1 0 21 1 0 1 0 22 0 1 1 1 23 1 1 1 1 24 0 1 1 1 *There are a couple more things to consider before you process any of the data. The first is copy errors . You could go line by line for each of the above tables and enter them into Excel by hand. However, you are a human being, and we all make mistakes. Even if you only make a mistake in entering one out of a hundred boxes, there are 288 data points above so that means that 2 or 3 of the above data points would be wrong. That doesn’t sound like a lot, but it could be enough to change the results of your statistical analysis. If your error rate were only to go up to three out of a hundred than 8 or 9 of them would be recorded wrong. So whenever possible use a computer to copy raw data points like that, Excel will get that data copied correctly 100% of the time. The second thing to consider is to use your RAW data for all your calculations. We’ve discussed the importance of large sample sizes. If you were to calculate the proportions, averages or standard error of each experiment (like you will below) then run a t-test on those instead of your raw data; then you just reduced your sample size from 96 for each group to 4. That kind of systemic error virtually ensures that your results will not be statistically significant. Finally, use Excel to perform all these calculations. You could use a calculator for some of this but then you’re entering data by hand (remember copy errors?). In addition, Excel is a very common program that you will use

over and over again. You may not know all the ins and outs of it right now, but the more contact you have with it the sooner you will. It’s like when you first started using Word or any other program; until you had a certain amount of experience with it some things were difficult. When you get used to using Excel these things will be much easier, make it do all the hard work for you! Step 1: Enter your data into an Excel File/Google Sheets *This can be done by hand OR you can download the word document, highlight the table, and copy and paste it into Excel. Do this for the adult copepod data and the nauplii data. I would recommend putting each table on two different “Sheets” To make a new “sheet” in Excel, look at the bottom left where it says “Sheet 1” There is a + next to that. Click on the + to make a new sheet. Step 2: Calculate the proportion (or fraction) of organisms that survive in each experiment. This can also be thought of as the Average rate of survival. If you were to do this by hand you would add up all of the numbers in the column (1’s and 0’s) and then divide by the total number of wells in a column (in this case 24) to give you your average. Excel makes it easier for us! In an empty cell below a column, enter the equation =AVERAGE(highlight the column you want to find the average of) . This does the same thing. Repeat this equation at the bottom of each column. *Caution – these cells say L3:L26 – yours will be different depending on where you put your table in Excel. Also, make sure you close the parentheses. You should now have an average or proportion for each column of data .

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

If you haven’t done so already create two tables in Excel for proportion survival of Naup. and proportion survival of Adults. It may look something like this. Using the function we just learned of =AVERAGE(), now calculate the average of the averages, or the overall average for the Nauplii survival and the overall average for Adult survival . Step 3. Calculate averages and standard error for each age group N = your sample size In ecology, each well plate is considered as 1 sample , even though there are multiple wells. This is because they are all in the same environment and so considered as one. If each well plate is 1 sample, what is the total “n” for Nauplii? For adults? To calculate standard error in excel: There is no formula for standard error in excel, so you must create it. Essentially, you use the standard deviation formula and then divide this by the square root of the sample size (n).

a. In a cell below your data, type =(STDEV(B2:E2))/SQRT(n) and hit Enter. (*Your N=the number you found earlier for the sample size.) *** Your cell numbers may be different than B2:E2 if you have your data in different cell. b. CAUTION: The equation above will work if your data are in cells B2 to E2. Be sure to change the cells to fit where you typed your data!! c. Do this procedure for both Nauplii data and then Adult data. Remember to label your answers so you know which is which ! d. Now create a table with your Overall average and your Standard error Nauplius Adult Average Standard Error Step 4: Conduct a t-test to compare each life cycle stage to the other. To do this, go to the following link http://www.graphpad.com/quickcalcs/ttest1.cfm . Select mean, SEM, and n. The mean is your overall average, the SEM is your standard error, and “n” is your sample size that you calculated earlier. (Remember one well plate is one sample, not each individual well.) Enter your data, then click on Enter Now.

Record your T-statistic and p-value. Nauplius vs. adult T-statistic 38.5524 p- value 46 Significant difference (yes or no) 0.009 Does your t-test indicate a significant difference between the two life cycle stages? Yes, the t-test indicates a significant difference between the Nauplius and adult life cycle stages. How do you know the difference is (or is not) significant? The p-value associated with the t-test is 0.009. Since this p-value is less than the conventional significance level of 0.05. Therefore, there is evidence to suggest a significant difference between the two life cycle stages.

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Putting it all together now: First, restate the original hypothesis for this experiment. Null Hypothesis (H0): There is NO statistically significant difference between the Nauplius and adult life cycle stages. Alternative Hypothesis (H1): There IS a statistically significant difference between the Nauplius and adult life cycle stages. Now, do the results of the t-test support your hypothesis? If yes, why do you think this is so? If not, why not? Yes, the results of the t-test support the hypothesis. The p-value is below the significance level, indicating that the observed difference between Nauplius and adult life cycle stages is unlikely to have occurred by random chance. Therefore, we reject the null hypothesis in favor of the alternative hypothesis. When conducting research, you can have a t-test that shows a significant difference and still NOT support your hypothesis? Explain how this could occur. Yes, even if the t-test shows a statistically significant difference, it may not support the hypothesis if the observed difference is not practically significant or relevant. Practical significance considers whether the difference, although statistically significant, is meaningful in the real-world context. Additionally, issues such as sample size, study design, or confounding variables can affect the interpretation of results. Step 4: Present your data in graphical form. (Hint: Look over the introduction for this lab to decide what type of graph might best represent your data.) You can also check out these links: https://towardsdatascience.com/data-visualization-101-how-to-choose-a-chart-type-9b8830e558d6 https://www.skillsyouneed.com/num/graphs-charts.html#:~:text=There%20are%20several%20different %20types,pie%20charts%2C%20and%20Cartesian%20graphs .

1 2 3 4 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 Chart Title Nauplius Adult Exercise 2 Sam is examining the effects of gasoline on copepod survival. He hypothesizes that increased levels of gasoline will lead to high rates of mortality. He has a control group and two experimental groups. Sam conducts 6 trials (6 well-plates) for each group. He then calculates the individual proportions for each trial. Use his data to answer the following: 1. What is the average proportion for the control group? For the 0.01 group? For the 0.001 group? Control Gr 0,886666667 0.01 0,77 0.001 0,68 2. Looking at the averages, can you tell if there is a significant difference between the groups? Why or why not? there is a significant difference, and the decreasing trend aligns with the statistical findings. Sam’s Data Proportion of Copepods living after 1 week

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Trial # Control (No gasoline) 0.01 ppt gasoline 0.001 ppt gasoline 1 0.95 0.83 0.73 2 0.97 0.79 0.63 3 0.83 0.71 0.71 4 0.85 0.85 0.53 5 0.79 0.69 0.69 6 0.93 0.77 0.78 3. Now calculate the standard error for each group. (You will need to refer to STEP 3 from the first exercise) What is the standard err for the control group? For 0.01? For 0.001 Control Group 0,029851484 0.01 0,026034166 0.001 0,035815887 4. Using the t-test website, compare the control with each of the test groups. link http://www.graphpad.com/quickcalcs/ttest1.cfm Record the p-value and t-statistic for each comparison. Is it significant? How do you know? Control vs 0.01 Control vs 0.001 p-value:10 p-value: 10 t-statistic: 2.9732 t-statistic: 0.6939 Significant? 0.040 Significant? 0.303 Exercise 3

Shani is investigating how often meadowlarks sing in urban (city) vs rural (country) environments. She hypothesizes that urban birds will sing more often than rural birds because they will need to communicate more frequently. Shani puts a summary of her data in a table. Are her results statistically significant? How do you know? Is Shani’s hypothesis correct? How do you know?