How Do You Estimate Free Throw Percentage and Construct a Confidence Interval?

In summary: X = 10", since this is a probability that only counts as one of the 51 possible figures that must sum to 1 in order to be accurate. However, when speaking informally, most people would say that if you are 95% confident that the true value of p is within the bounds of the confidence interval, then you can say that the probability that X = 10 is also within the bounds of the confidence interval.
  • #1
Mentallic
Homework Helper
3,802
95

Homework Statement


Take 50 free throws in basketball, and record the number of successful shots.

1) Use this data to estimate your free throw percentage.
2) Construct a 95% confidence interval for this estimated quantity.

Homework Equations



X ~ Binomial(n,p)

The Attempt at a Solution



I don't quite understand this. I would've guessed that given the data, my free throw percentage should be pretty obviously k/50 where k is the number of shots I landed. Maybe this means I should set the problem up as such?

X ~ Binomial(50,k/50)

But then it wants me to construct a confidence interval, so that can't be it, because I've taken the probability of landing a shot to be known.

edit: Hang on, I think I need to assume they're normally distributed.
 
Last edited:
Physics news on Phys.org
  • #2
Mentallic said:

Homework Statement


Take 50 free throws in basketball, and record the number of successful shots.

1) Use this data to estimate your free throw percentage.
2) Construct a 95% confidence interval for this estimated quantity.


Homework Equations



X ~ Binomial(n,p)

The Attempt at a Solution



I don't quite understand this. I would've guessed that given the data, my free throw percentage should be pretty obviously k/50 where k is the number of shots I landed. Maybe this means I should set the problem up as such?

X ~ Binomial(50,k/50)

But then it wants me to construct a confidence interval, so that can't be it, because I've taken the probability of landing a shot to be known.

edit: Hang on, I think I need to assume they're normally distributed.

If X = number of shots landed, X ~ Binomial(50,p) for some unknown constant p, and the success fraction is f = X/50. After observing X (or f) you want to infer something about the value of p. Normal distributions have not much to do with the problem, except maybe as an approximation to make computations easier. (Nowadays, with readily-available powerful software such approximations are less important than they used to be.)
 
  • #3
Ray Vickson said:
If X = number of shots landed, X ~ Binomial(50,p) for some unknown constant p, and the success fraction is f = X/50. After observing X (or f) you want to infer something about the value of p. Normal distributions have not much to do with the problem, except maybe as an approximation to make computations easier. (Nowadays, with readily-available powerful software such approximations are less important than they used to be.)

What kind of inference for p would I make? I only have the data of shooting k successful throws out of 50 total, so all I can imagine doing with this is to falsely assume that my true average p is k/50.
 
  • #4
Mentallic said:
What kind of inference for p would I make? I only have the data of shooting k successful throws out of 50 total, so all I can imagine doing with this is to falsely assume that my true average p is k/50.

Nothing false about it as a probable approximation; you would not be surprised to find the true value of p being close to f= k/50.

Let's cook up some simple numbers: say you observe f = 0.2, so k = 10. How surprised would you be by this result if you knew p = 0.9? Well, how probable is it that you would observe X as small as 10 (i.e., X <= 10) when X~Bin(50,0.9)? How surprised would you be to observe X as large as 10 when X~Bin(50, 0.001); that is, what would be the probability of observing X >= 10 in such a case? Note that we do not necessarily ask the probability that X = 10 exactly, since this will likely always be small for any p; it is just one of 51 separate probability figures that must all sum to 1.

A confidence interval [a,b] is a kind of "not too surprised" interval, so that if p ε [a,b] the probability of observing X = 10 is not "too small". In your case you do not want to be more surprised than 5%, so you would typically (and usually) choose upper and lower limits giving 2.5% probability each. So, you would choose the upper limit 'b' to give P(X <= 10) = 0.025 for X~Bin(50,b) and the lower limit 'a' to give P(X >= 10) = 0.025 for X ~ Bin(50,a). Of course, we could choose upper and lower probabilities different from 0.025, just as long as the two of them sum to 0.05, but choosing the symmetrical case is customary.

Modern software can handle such problems pretty easily, but you might, nevertheless, choose instead to use a normal approximation to the binomial.

Formally: a 95% confidence interval [a,b] is a random interval whose chance of overlapping the true value of p is 95%. (The interval is random because it is constructed from the observed data, which is itself random.) Classical statisticians would say it is incorrect to speak of "the probability that p lies in the interval is 95%"; rather, they would insist that it is the interval itself to which the probability is attached. This concept can be tricky to grasp.

A Bayesian (which I almost am) would find it a lot easier: he/she would start with a "prior" probability distribution f0(p) of the parameter, and would then just look at the posterior distribution f1(p) of p, after observing the data. That is, f1(r) = P{r < p < r + dr|X=k}/dr = P{X=k|p=r} * f0(r) /P{X=k}. For a uniform prior f0 = 1, we get
[tex] f_1(r) = \frac{r^k (1-r)^{50-k}}{B(k+1,50-k+1)},[/tex]
where ##B(u,v)## is the so=called Beta function:
[tex] B(u,v) = \int_0^1 x^{u-1}(1-x)^{v-1} \, dx.[/tex]
Anyway, p would now be regarded as having a probability density f1, and the confidence interval [a,b] would be truly an interval in which p was 95% likely to fall.

The classical and Bayesian confidence intervals would be sightly different, since the classical method looks at {X <= 10} and {X >= 10}, while the Baseyian looks at {X = 10}.
 

Related to How Do You Estimate Free Throw Percentage and Construct a Confidence Interval?

What is probability approximation?

Probability approximation is a method used to estimate the likelihood of an event occurring based on available data. It involves using mathematical and statistical techniques to make predictions about the probability of an event.

Why is probability approximation important in science?

Probability approximation is important in science because it allows researchers to make predictions and draw conclusions based on data. It is used in various fields such as physics, biology, and psychology to understand and explain complex systems and phenomena.

What are some common techniques used for probability approximation?

Some common techniques used for probability approximation include Monte Carlo simulations, Bayes theorem, and Markov chain Monte Carlo methods. These techniques involve using mathematical models and algorithms to estimate probabilities based on available data.

How accurate are probability approximations?

The accuracy of probability approximations depends on the quality and quantity of the available data, as well as the chosen method of approximation. In general, the more data that is available, the more accurate the approximation will be.

What are the limitations of probability approximation?

Probability approximation is based on assumptions and simplifications, so it may not always accurately reflect real-world situations. It also relies on the quality of the data used, so if the data is biased or incomplete, the approximation may be inaccurate. Additionally, probability approximation cannot account for all factors that may affect the likelihood of an event occurring.

Similar threads

  • Set Theory, Logic, Probability, Statistics
Replies
5
Views
281
  • Set Theory, Logic, Probability, Statistics
Replies
1
Views
732
  • Calculus and Beyond Homework Help
Replies
5
Views
2K
Replies
1
Views
1K
  • Calculus and Beyond Homework Help
Replies
7
Views
2K
  • Set Theory, Logic, Probability, Statistics
Replies
2
Views
1K
  • Set Theory, Logic, Probability, Statistics
Replies
3
Views
531
  • Set Theory, Logic, Probability, Statistics
Replies
6
Views
3K
  • Calculus and Beyond Homework Help
Replies
10
Views
4K
Replies
1
Views
2K
Back
Top