Welcome to our community

Be a part of something great, join today!

Visualizing Data, Significance Level, T-test, Level of Measurement

mmatusevici1

New member
May 7, 2013
2
Hello. I was just wandering if anyone could help. I've been doing a couple of statistics questions, and when they ask for some questions, I am not sure if I have an appropriate understanding of what the right answer should be. I would really like to understand this material, so what I want to know is your opinions which are the right answers and why? Thank you.

0. Which one of these graphs is NOT an appropriate way of visualising the distribution of your data?

A. A box plot
B. A cumulative frequency curve
C. A scatter plot
D. A frequency histogram


1. When setting the significance level at which to test your hypothesis, what does a probability level of 0.05 mean?

A.There is a 0.05% probability that your result could have occurred by chance
B.There is a 5% probability that your result could have occurred by chance
C. There is a 0.95% probability that your result could have occurred by chance
D. There is a 95% probability that your result could have occurred by chance

2. You have a dataset containing 10 values and conducted a one-sample t test against an expected mean value. Your test statistic (t) was 2.23 and the critical value of t at the 0.05 level with 9 degrees of freedom is 2.26. How would you interpret this result?

A. The difference is significant at the 0.05 level so do not reject the H0.
B. The difference is significant at the 0.05 level so reject the H0.
C. The difference is not significant at the 0.05 level so do not reject the H0.
D. The difference is not significant at the 0.05 level so reject H0.

3.You have measure the suspended sediment of water samples taken from a variety of sites along a stream. What TYPE of data is this?

A. Nominal
B.Ordinal
C.Interval
D.Ratio

Thank you. I would really appreciate your help.
 
Last edited by a moderator:

Bacterius

Well-known member
MHB Math Helper
Jan 26, 2012
644
Re: Statistics

0. They're all appropriate depending on what you want to learn on the distribution :confused:

- A is useful for visualizing mean and quartiles as well as outliers.
- B is useful if you want to work out the median or other related quantities.
- C is useful for graphically observing patterns in data.
- D is useful when you want to compare data points.

1. I believe B is the right answer. First, 0.05 is on a scale of 0 to 1, so it's not going to be A nor C. But I've generally seen this worded a bit more differently (since definitions are important here) as "In the long term, 95% of all measured [quantity you are measuring according to given distribution] will fall into [your confidence interval]".

2. Too rusty :confused:

3. Presumably you can measure these data points, and compare them to one another, so it can't be nominal. Now the difference between two measurements is meaningful, I suppose, so it can't be ordinal data. And, of course, this type of data has a natural zero point (measuring 0 means "no sediment"). Therefore this is ratio data.

That said I don't really know what is meant by "suspended sediment", so I assume it is some form of measurement (like rainfall in mm). If it isn't, the answer could be different.
 

mmatusevici1

New member
May 7, 2013
2
Re: Statistics

Thank you, Bacterius, it was very helpful.

Question 0 is very tricky, as all choices look appropriate for me as well :confused: Probably I would choose 'A box plot' because you have to read it, whereas in curves, scatter plots, and frequency histograms you can "see" the information, it's kind of "visualization". what do you think about my interpretation of answer? which answer would you choose?

In regards to Question 1, thank you, my answer would be the same as yours. I still can't solve the Question 2..

Thank you very much for Question 3, after your answer I did a further research on ratio data (before I thought it was ordinal), and I agree with you. Thanks. (flower)

There are two more things I would like to discuss to go through with statistics. Would you (or someone else) mind to help me to come up with solutions together?

4. In what situation are two groups most likely to have significant differences in their means?

A.When within-group variability is high and between-group variability is high
B.When within-group variability is high and between-group variability is low
C.When within-group variability is low and between-group variability is low
D.When within-group variability is low and between-group variability is high

5.You think that there total amount of precipitaton in a storm will influence the peak discharge in a river during the associated storm flow event. How would you plot this relationship on a scatter graph?

A.Peak discharge is the dependent variable so should be on the x axis, total precipitation is the independent variable so should be on the y axis.
B.Peak discharge is the dependent variable so shold be on the y axis, total precipitation is the independent variable so should be on the x axis
C.Peak discharge is the independent variable so should be on the y axis, total precipitation is the dependent variable so should be on the x axis.
D.Peak discharge is the independent variable so should be on the x axis, total precipitation is the dependent variable so should be on the y axis.