I have two related question on population statistics. I'm not a statistician, but would appreciate pointers to learn more.
I have a process that results from flipping a three sided coin (results: A, B, C) and I compute the statistic t=(A-C)/(A+B+C). In my problem, I have a set that randomly divides itself into sets X and Y, maybe uniformly, maybe not. I compute t for X and Y. I want to know whether the difference I observe in those two t values is likely due to chance or not.
Now if this were a simple binomial distribution (i.e., I'm just counting who ends up in X or Y), I'd know what to do: I compute n=|X|+|Y|, σ=sqrt(np(1-p)) (and I assume my p=.5), and then I compare to the normal distribution. So, for example, if I observed |X|=45 and |Y|=55, I'd say σ=5 and so I expect to have this variation from the mean μ=50 by chance 68.27% of the time. Alternately, I expect greater deviation from the mean 31.73% of the time.
There's an intermediate problem, which also interests me and which I think may help me understand the main problem, where I measure some property of members of A and B. Let's say 25% in A measure positive and 66% in B measure positive. (A and B aren't the same cardinality -- the selection process isn't uniform.) I would like to know if I expect this difference by chance.
As a first draft, I computed t as though it were measuring coin flips, but I'm pretty sure that's not actually right.
Any pointers on what the correct way to model this is?
First problem
For the three-sided coin problem, have a look at the multinomial distribution. It's the distribution to use for a "binomial" problem with more then 2 outcomes.
Here is the example from Wikipedia (https://en.wikipedia.org/wiki/Multinomial_distribution):
Suppose that in a three-way election for a large country, candidate A received 20% of the votes, candidate B received 30% of the votes, and candidate C received 50% of the votes. If six voters are selected randomly, what is the probability that there will be exactly one supporter for candidate A, two supporters for candidate B and three supporters for candidate C in the sample?
Note: Since we’re assuming that the voting population is large, it is reasonable and permissible to think of the probabilities as unchanging once a voter is selected for the sample. Technically speaking this is sampling without replacement, so the correct distribution is the multivariate hypergeometric distribution, but the distributions converge as the population grows large.
Second problem
The second problem seems to be a problem for cross-tabs. Then use the "Chi-squared test for association" to test whether there is a significant association between your variables. And use the "standardized residuals" of your cross-tab to identify which of the assiciations is more likely to occur and which is less likely.
Related
I am learning statistics, and have some basic yet core questions on SD:
s = sample size
n = total number of observations
xi = ith observation
μ = arithmetic mean of all observations
σ = the usual definition of SD, i.e. ((1/(n-1))*sum([(xi-μ)**2 for xi in s])**(1/2) in Python lingo
f = frequency of an observation value
I do understand that (1/n)*sum([xi-μ for xi in s]) would be useless (= 0), but would not (1/n)*sum([abs(xi-μ) for xi in s]) have been a measure of variation?
Why stop at power of 1 or 2? Would ((1/(n-1))*sum([abs((xi-μ)**3) for xi in s])**(1/3) or ((1/(n-1))*sum([(xi-μ)**4 for xi in s])**(1/4) and so on have made any sense?
My notion of squaring is that it 'amplifies' the measure of variation from the arithmetic mean while the simple absolute difference is somewhat a linear scale notionally. Would it not amplify it even more if I cubed it (and made absolute value of course) or quad it?
I do agree computationally cubes and quads would have been more expensive. But with the same argument, the absolute values would have been less expensive... So why squares?
Why is the Normal Distribution like it is, i.e. f = (1/(σ*math.sqrt(2*pi)))*e**((-1/2)*((xi-μ)/σ))?
What impact would it have on the normal distribution formula above if I calculated SD as described in (1) and (2) above?
Is it only a matter of our 'getting used to the squares', it could well have been linear, cubed or quad, and we would have trained our minds likewise?
(I may not have been 100% accurate in my number of opening and closing brackets above, but you will get the idea.)
So, if you are looking for an index of dispersion, you actually don't have to use the standard deviation. You can indeed report mean absolute deviation, the summary statistic you suggested. You merely need to be aware of how each summary statistic behaves, for example the SD assigns more weight to outlying variables. You should also consider how each one can be interpreted. For example, with a normal distribution, we know how much of the distribution lies between ±2SD from the mean. For some discussion of mean absolute deviation (and other measures of average absolute deviation, such as the median average deviation) and their uses see here.
Beyond its use as a measure of spread though, SD is related to variance and this is related to some of the other reasons it's popular, because the variance has some nice mathematical properties. A mathematician or statistician would be able to provide a more informed answer here, but squared difference is a smooth function and is differentiable everywhere, allowing one to analytically identify a minimum, which helps when fitting functions to data using least squares estimation. For more detail and for a comparison with least absolute deviations see here. Another major area where variance shines is that it can be easily decomposed and summed, which is useful for example in ANOVA and regression models generally. See here for a discussion.
As to your questions about raising to higher powers, they actually do have uses in statistics! In general, the mean (which is related to average absolute mean), the variance (related to standard deviation), skewness (related to the third power) and kurtosis (related to the fourth power) are all related to the moments of a distribution. Taking differences raised to those powers and standardizing them provides useful information about the shape of a distribution. The video I linked provides some easy intuition.
For some other answers and a larger discussion of why SD is so popular, See here.
Regarding the relationship of sigma and the normal distribution, sigma is simply a parameter that stretches the standard normal distribution, just like the mean changes its location. This is simply a result of the way the standard normal distribution (a normal distribution with mean=0 and SD=variance=1) is mathematically defined, and note that all normal distributions can be derived from the standard normal distribution. This answer illustrates this. Now, you can parameterize a normal distribution in other ways as well, but I believe you do need to provide sigma, whether using the SD or precisions. I don't think you can even parametrize a normal distribution using just the mean and the mean absolute difference. Now, a deeper question is why normal distributions are so incredibly useful in representing widely different phenomena and crop up everywhere. I think this is related to the Central Limit Theorem, but I do not understand the proofs of the theorem well enough to comment further.
I am new to using linear mixed-effects models. I have a dataset where participants (ID, N = 7973) completed two experimental conditions (A and B). A subset of participants are siblings and thus nested in families (famID, N = 6908).
omnibus_model <- lmer(Outcome ~ Var1*Var2*Cond + (Cond|ID) + (1|famID), data=df)
The omnibus model converges and indicates a significant three way interaction between Var1, Var2 and Cond. As a post-hoc, to better understand what is driving the omnibus model effect, I subsetted the data so that there is only one observation per ID.
condA <- df[which(df$condition=='A'),]
condA_model <- lmer(Outcome ~ Var1*Var2 + (1|famID), data=condA)
condB <- df[which(df$condition=='B'),]
condB_model <- lmer(Outcome ~ Var1*Var2 + (1|famID), data=condB)
condA_model converges; condB_model does not. In condB_model "famID (Intercept)" variance is estimated at 0. In the condA_model, I get a small, but non-zero estimate (variance=0.001479). I know I could get an estimate of the fixed effect of interest in condition A versus B by a different method(such as randomly selecting one sibling per family for the analysis and not using random effects), but I am concerned that this differential convergence pattern may indicate differences between the conditions that would influence the interpretation of the omnibus model effect.
What difference in the two conditions could causing the model in one subset not to converge? How would I test for the possible differences in my data? Shouldn't the random effect of famID be identical in both subsets and thus equally able to be estimated in both post-hoc models?
As a post-hoc, to better understand what is driving the omnibus model effect, I subsetted the data so that there is only one observation per ID.
This procedure does not make sense.
What difference in the two conditions could causing the model in one subset not to converge?
There are many reasons. For one thing, these reduced datasets are, well, reduced, ie smaller, so there is far less statistical power to detect the "effects" that you are interested in, such as a variance of a random effect. In such cases, it may be estimated as zero and result in a singular fit.
Shouldn't the random effect of famID be identical in both subsets and thus equally able to be estimated in both post-hoc models?
No, these are completely different models, since the underlying data are different. There is no reason to expect the same estimates from both models.
I'm trying to work out how to solve what seems like a simple problem, but I can't convince myself of the correct method.
I have time-series data that represents the pdf of a Power output (P), varying over time, also the cdf and quantile functions - f(P,t), F(P,t) and q(p,t). I need to find the pdf, cdf and quantile function for the Energy in a given time interval [t1,t2] from this data - say e(), E(), and qe().
Clearly energy is the integral of the power over [t1,t2], but how do I best calculate e, E and qe ?
My best guess is that since q(p,t) is a power, I should generate qe by integrating q over the time interval, and then calculate the other distributions from that.
Is it as simple as that, or do I need to get to grips with stochastic calculus ?
Additional details for clarification
The data we're getting is a time-series of 'black-box' forecasts for f(P), F(P),q(P) for each time t, where P is the instantaneous power and there will be around 100 forecasts for the interval I'd like to get the e(P) for. By 'Black-box' I mean that there will be a function I can call to evaluate f,F,q for P, but I don't know the underlying distribution.
The black-box functions are almost certainly interpolating output data from the model that produces the power forecasts, but we don't have access to that. I would guess that it won't be anything straightforward, since it comes from a chain of non-linear transformations. It's actually wind farm production forecasts: the wind speeds may be normally distributed, but multiple terrain and turbine transformations will change that.
Further clarification
(I've edited the original text to remove confusing variable names in the energy distribution functions.)
The forecasts will be provided as follows:
The interval [t1,t2] that we need e, E and qe for is sub-divided into 100 (say) sub-intervals k=1...100. For each k we are given a distinct f(P), call them f_k(P). We need to calculate the energy distributions for the interval from this set of f_k(P).
Thanks for the clarification. From what I can tell, you don't have enough information to solve this problem properly. Specifically, you need to have some estimate of the dependence of power from one time step to the next. The longer the time step, the less the dependence; if the steps are long enough, power might be approximately independent from one step to the next, which would be good news because that would simplify the analysis quite a bit. So, how long are the time steps? An hour? A minute? A day?
If the time steps are long enough to be independent, the distribution of energy is the distribution of 100 variables, which will be very nearly normally distributed by the central limit theorem. It's easy to work out the mean and variance of the total energy in this case.
Otherwise, the distribution will be some more complicated result. My guess is that the variance as estimated by the independent-steps approach will be too big -- the actual variance would be somewhat less, I believe.
From what you say, you don't have any information about temporal dependence. Maybe you can find or derive from some other source or sources an estimate the autocorrelation function -- I wouldn't be surprised if that question has already been studied for wind power. I also wouldn't be surprised if a general version of this problem has already been studied -- perhaps you can search for something like "distribution of a sum of autocorrelated variables." You might get some interest in that question on stats.stackexchange.com.
Generally speaking when you are numerically evaluating and integral, say in MATLAB do I just pick a large number for the bounds or is there a way to tell MATLAB to "take the limit?"
I am assuming that you just use the large number because different machines would be able to handle numbers of different magnitudes.
I am just wondering if their is a way to improve my code. I am doing lots of expected value calculations via Monte Carlo and often use the trapezoid method to check my self of my degrees of freedom are small enough.
Strictly speaking, it's impossible to evaluate a numerical integral out to infinity. In most cases, if the integral in question is finite, you can simply integrate over a reasonably large range. To converge at a stable value, the integral of the normal error has to be less than 10 sigma -- this value is, for better or worse, as equal as you are going to get to evaluating the same integral all the way out to infinity.
It depends very much on what type of function you want to integrate. If it is "smooth" (no jumps - preferably not in any derivatives either, but that becomes progressively less important) and finite, that you have two main choices (limiting myself to the simplest approach):
1. if it is periodic, here meaning: could you put the left and right ends together and the also there have no jumps in value (and derivatives...): distribute your points evenly over the interval and just sample the functionvalues to get the estimated average, and than multiply by the length of the interval to get your integral.
2. if not periodic: use Legendre-integration.
Monte-carlo is almost invariably a poor method: it progresses very slow towards (machine-)precision: for any additional significant digit you need to apply 100 times more points!
The two methods above, for periodic and non-periodic "nice" (smooth etcetera) functions gives fair results already with a very small number of sample-points and then progresses very rapidly towards more precision: 1 of 2 points more usually adds several digits to your precision! This far outweighs the burden that you have to throw away all parts of the previous result when you want to apply a next effort with more sample points: you REPLACE the previous set of points with a fresh new one, while in Monte-Carlo you can just simply add points to the existing set and so refine the outcome.
I've been trying to find an answer to this for months (to be used in a machine learning application), it doesn't seem like it should be a terribly hard problem, but I'm a software engineer, and math was never one of my strengths.
Here is the scenario:
I have a (possibly) unevenly weighted coin and I want to figure out the probability of it coming up heads. I know that coins from the same box that this one came from have an average probability of p, and I also know the standard deviation of these probabilities (call it s).
(If other summary properties of the probabilities of other coins aside from their mean and stddev would be useful, I can probably get them too.)
I toss the coin n times, and it comes up heads h times.
The naive approach is that the probability is just h/n - but if n is small this is unlikely to be accurate.
Is there a computationally efficient way (ie. doesn't involve very very large or very very small numbers) to take p and s into consideration to come up with a more accurate probability estimate, even when n is small?
I'd appreciate it if any answers could use pseudocode rather than mathematical notation since I find most mathematical notation to be impenetrable ;-)
Other answers:
There are some other answers on SO that are similar, but the answers provided are unsatisfactory. For example this is not computationally efficient because it quickly involves numbers way smaller than can be represented even in double-precision floats. And this one turned out to be incorrect.
Unfortunately you can't do machine learning without knowing some basic math---it's like asking somebody for help in programming but not wanting to know about "variables" , "subroutines" and all that if-then stuff.
The better way to do this is called a Bayesian integration, but there is a simpler approximation called "maximum a postieri" (MAP). It's pretty much like the usual thinking except you can put in the prior distribution.
Fancy words, but you may ask, well where did the h/(h+t) formula come from? Of course it's obvious, but it turns out that it is answer that you get when you have "no prior". And the method below is the next level of sophistication up when you add a prior. Going to Bayesian integration would be the next one but that's harder and perhaps unnecessary.
As I understand it the problem is two fold: first you draw a coin from the bag of coins. This coin has a "headsiness" called theta, so that it gives a head theta fraction of the flips. But the theta for this coin comes from the master distribution which I guess I assume is Gaussian with mean P and standard deviation S.
What you do next is to write down the total unnormalized probability (called likelihood) of seeing the whole shebang, all the data: (h heads, t tails)
L = (theta)^h * (1-theta)^t * Gaussian(theta; P, S).
Gaussian(theta; P, S) = exp( -(theta-P)^2/(2*S^2) ) / sqrt(2*Pi*S^2)
This is the meaning of "first draw 1 value of theta from the Gaussian" and then draw h heads and t tails from a coin using that theta.
The MAP principle says, if you don't know theta, find the value which maximizes L given the data that you do know. You do that with calculus. The trick to make it easy is that you take logarithms first. Define LL = log(L). Wherever L is maximized, then LL will be too.
so
LL = hlog(theta) + tlog(1-theta) + -(theta-P)^2 / (2*S^2)) - 1/2 * log(2*pi*S^2)
By calculus to look for extrema you find the value of theta such that dLL/dtheta = 0.
Since the last term with the log has no theta in it you can ignore it.
dLL/dtheta = 0 = (h/theta) + (P-theta)/S^2 - (t/(1-theta)) = 0.
If you can solve this equation for theta you will get an answer, the MAP estimate for theta given the number of heads h and the number of tails t.
If you want a fast approximation, try doing one step of Newton's method, where you start with your proposed theta at the obvious (called maximum likelihood) estimate of theta = h/(h+t).
And where does that 'obvious' estimate come from? If you do the stuff above but don't put in the Gaussian prior: h/theta - t/(1-theta) = 0 you'll come up with theta = h/(h+t).
If your prior probabilities are really small, as is often the case, instead of near 0.5, then a Gaussian prior on theta is probably inappropriate, as it predicts some weight with negative probabilities, clearly wrong. More appropriate is a Gaussian prior on log theta ('lognormal distribution'). Plug it in the same way and work through the calculus.
You can use p as a prior on your estimated probability. This is basically the same as doing pseudocount smoothing. I.e., use
(h + c * p) / (n + c)
as your estimate. When h and n are large, then this just becomes h / n. When h and n are small, this is just c * p / c = p. The choice of c is up to you. You can base it on s but in the end you have to decide how small is too small.
You don't have nearly enough info in this question.
How many coins are in the box? If it's two, then in some scenarios (for example one coin is always heads, the other always tails) knowing p and s would be useful. If it's more than a few, and especially if only some of the coins are only slightly weighted then it is not useful.
What is a small n? 2? 5? 10? 100? What is the probability of a weighted coin coming up heads/tail? 100/0, 60/40, 50.00001/49.99999? How is the weighting distributed? Is every coin one of 2 possible weightings? Do they follow a bell curve? etc.
It boils down to this: the differences between a weighted/unweighted coin, the distribution of weighted coins, and the number coins in your box will all decide what n has to be for you to solve this with a high confidence.
The name for what you're trying to do is a Bernoulli trial. Knowing the name should be helpful in finding better resources.
Response to comment:
If you have differences in p that small, you are going to have to do a lot of trials and there's no getting around it.
Assuming a uniform distribution of bias, p will still be 0.5 and all standard deviation will tell you is that at least some of the coins have a minor bias.
How many tosses, again, will be determined under these circumstances by the weighting of the coins. Even with 500 tosses, you won't get a strong confidence (about 2/3) detecting a .51/.49 split.
In general, what you are looking for is Maximum Likelihood Estimation. Wolfram Demonstration Project has an illustration of estimating the probability of a coin landing head, given a sample of tosses.
Well I'm no math man, but I think the simple Bayesian approach is intuitive and broadly applicable enough to put a little though into it. Others above have already suggested this, but perhaps if your like me you would prefer more verbosity.
In this lingo, you have a set of mutually-exclusive hypotheses, H, and some data D, and you want to find the (posterior) probabilities that each hypothesis Hi is correct given the data. Presumably you would choose the hypothesis that had the largest posterior probability (the MAP as noted above), if you had to choose one. As Matt notes above, what distinguishes the Bayesian approach from only maximum likelihood (finding the H that maximizes Pr(D|H)) is that you also have some PRIOR info regarding which hypotheses are most likely, and you want to incorporate these priors.
So you have from basic probability Pr(H|D) = Pr(D|H)*Pr(H)/Pr(D). You can estimate these Pr(H|D) numerically by creating a series of discrete probabilities Hi for each hypothesis you wish to test, eg [0.0,0.05, 0.1 ... 0.95, 1.0], and then determining your prior Pr(H) for each Hi -- above it is assumed you have a normal distribution of priors, and if that is acceptable you could use the mean and stdev to get each Pr(Hi) -- or use another distribution if you prefer. With coin tosses the Pr(D|H) is of course determined by the binomial using the observed number of successes with n trials and the particular Hi being tested. The denominator Pr(D) may seem daunting but we assume that we have covered all the bases with our hypotheses, so that Pr(D) is the summation of Pr(D|Hi)Pr(H) over all H.
Very simple if you think about it a bit, and maybe not so if you think about it a bit more.