Experimental Design B/C

[mnstrviola]

Thanks nejanimb for your explanation! I should like to personally exalt you. So just to confirm, the data analysis analyzes data statistically, while the conclusion only analyzes the data that will connect back to whether the hypothesis was supported?

Yes, this sounds right. Make sure the conclusion has already been supported by the data analysis and not by what you write in the conclusion.

and thanks @ siciscio for the links!

[kittybug65]

How do you operationally define a varible?

This was the most common error I saw when I supervised this event last week, and not one team got any points for it.

To operationally define something is to explain what PRECISELY you mean when you identify the variable. So say you're doing the "height of ball being dropped vs. bounce height" experiment. Your IV is "the height of the ball when it is first dropped." You operationally define that as "the shortest distance, as measured with a meter stick in centimeters, between the surface of the ball and the floor." That has a low enough level of ambiguity, at least in my opinion. An operational definition like "the height of the ball above the floor in centimeters" leaves huge room for interpretation: do you measure from the top of the ball? From the center? From the bottom? What do you use to measure? Do you measure straight down? Sometimes it can be difficult to come up with a good operational definition, even when the intuitive version is very clear. An operational definition is not "the time it takes for something to drop," it's "the time, measured in seconds (to 0.01s) using a stopwatch, between when the object is released by the experimenter's fingers and when the outer surface of the object first comes into contact with the floor"

Other common problems I saw:

- Zero teams did regression analysis.
- Zero teams broke out their tables into multiple categories.
- Many teams confuse what should go in the "analysis" section and what should go in the "Conclusion"
- Many teams gave me a "mode" for the entire table of results. That is not a particularly meaningful statistic, since that's not the purpose of the mode. Really, the mode is almost never relevant for this event.
- Many teams were tricked into doing experiments with categorical variables, which almost always results in a worse lab.

Thank you so much!!!!!! this really helped at competition! We got 1st at regionals!

[nejanimb]

Glad you found it helpful!

Supervised VA's second regional yesterday, and was much more impressed by the work people did. The event was:

"Flight"
5 sheets of different kinds of paper
5 paper clips
Water
Pipettes
Scissors
Meter stick

So if you've been wanting for ideas for practice, you can use that one.

Like I said, teams were much better, but still people had a lot of trouble with those same issues. I got hardly any proper operational definitions of variables. Only one team (the winning team) did regression analysis. Several other teams did "regression analysis" and just did a point to point line of best fit. That was okay for middle school, but in C division, you've gotta learn to do it the right way. An unbelievable number of teams made bar graphs, even for quantitative data, which is painful to look at. One team claimed their data showed exponential decay, but didn't actually do any transformations or analysis to show that. And still, no one got full credit for their "analysis" section.

95% of the time, the right answer is to use two quantitative variables, make a scatter plot, do regression analysis, and analyze their correlation. I'm guessing most of you already know that, though!

[awesome90220]

This has been a discussion among my fellow team mates and I for quite some time. If you are given alka seltzer tablets and water, and your testing how something affects the rate at which water dissolves, what would you do? ( another would be for proving Yeast is alive )

My team came up with breaking the alka seltzer in to different portions and using the amount of alka seltzer used as the independent variable. However, we weren't quite sure what we could do for the Standard of Comparison. We thought about using "zero' alka seltzer tablets, but would that give us infinite seconds or zero seconds since the alka seltzer neither began nor stop dissolving. We also thought about using 1 whole tablet as the standard of comparison, but that really isn't a base line... So does any one have any thoughts on this? Or how we could do this experiment differently so that we could avoid this problem? Thanks in advance

I say that would count as zero seconds.

You say testing "how something affects the rate at which water dissolves", which I don't really understand. But I'd probably do something with how the surface area of an alka seltzer (same mass, just one pill whole or one pill crushed kinda thing) affects the rate of dissolving.

OUr experiment last year was how the height of a wooden dowel effected its weight WE placed second

[tangentline]

"j. Statistics Division B&C– (2 points)
_____ Average (mean), median, mode, range,
or drawn in line best of-fit
Division C only (4 more points)
_____ Measure of central tendency
_____ Measure of variation
_____ Regression analysis
_____ Other appropriate statistic used"

What is the difference between the first 2 points and the measure of central tendency/regression analysis?... And can the other appropriate statistic be a second one of those already listed above?
--One of them is probably going to be the correlation coefficient which is annoying to do by Scientific Calculator

[mnstrviola]

"j. Statistics Division B&C– (2 points)
_____ Average (mean), median, mode, range,
or drawn in line best of-fit
Division C only (4 more points)
_____ Measure of central tendency
_____ Measure of variation
_____ Regression analysis
_____ Other appropriate statistic used"

What is the difference between the first 2 points and the measure of central tendency/regression analysis?... And can the other appropriate statistic be a second one of those already listed above?
--One of them is probably going to be the correlation coefficient which is annoying to do by Scientific Calculator

I believe measure of central tendency is picking one of them (mean median mode) as the statistic that best describes your data.
Regression analysis is finding r/r^2 value with some fancy formula.
Your other appropriate statistic will have to be something other than the above. Correlation coefficient could work.

[awesome90220]

state competition's next week, wasn't in it for regs so really rusty. Any tips?

[CulturallyScientific]

Practice. And practice. And practice. Practice, practice, practice, practice, practice, practice, practice, practice, practice, practice, practice, practice, practice, practice, practice, practice, practice, practice, practice, and practice.....not sure what else to really say... oh, and taking a good look at the rubric might be helpful, too.

[Bozongle]

Can someone give me some advice for Errors? It seems to be the only one I'm consistently doing bad on in our practices.

[fourLoko]

Could you guys give me some input on this?

So I was thinking about a practice my team did about reaction rate with alka seltzer tablets. Our instinct was to test surface area vs reaction rate, so we divided up the tablets, calculated surface area, dissolved them, etc etc. The thing is though, for a larger tablet, wouldn't the reaction rate be influenced by both the increased surface area and an increased volume? I was thinking about trying to determine the relationship between the Surface Area/Volume ratio to time instead so it would account for both the surface area and volume. Am I overthinking this? Would a simple SA v time experiment have been sufficient?