Suppose that my data $y \in \{0,0.1,\ldots,1\}$. What are the consequences of modeling that data as continuous, i.e., as if $y \in [0,1]$, by using the beta distribution? Is there a version of the beta distribution that can account for this?
Probability – Beta Distribution Analysis on Discrete Data
beta distributionprobability
Related Solutions
The plots indicate that the data have a shorter right tail than a two parameter lognormal, not a longer tail.
Certainly the data are right skewed, but their logs are distinctly left-skew, and a lognormal would be unlikely to be useful
I suggest looking at a normal Q-Q plot of log(x) (qqnorm(log(x)) in R), or indeed a histogram of log(x) if you use plenty of bins.
If anything these plots hint at something nearer to a gamma or something perhaps even a little lighter tailed still. (If they're real data they won't be from a gamma distribution either, but it's considerably more plausible). A normal Q-Q plot of the cube root of the data looks reasonably close to straight but there's a big gap (1.057 to 1.478) in the cube-root values that would make a gamma not ideal (while being considerably better than lognormal). Aide from that gap an exponential looks feasible.
Can I, at this point, infer that the data come from a Beta(0.8660958,6.610806)?
Certainly not. It's a reasonable fit. That doesn't mean any more than just that. Don't imagine your model is anything other than a plausible fiction (possibly a useful one).
(Note also that you appear to have actually fitted a three parameter model, not a two parameter model. How did you figure to divide by 100 except by reference to the data?)
What other analysis can I perform to strengthen this hypothesis?
"Oh, it looks a bit like such-and-such" isn't really what I'd call a hypothesis, but consider issues with hypotheses suggested by the data (whether formal statistical hypotheses or not, the issues are similar)
Those issues aside, you should not seek to confirm the results of your search for a model but to disconfirm them. If we seek to confirm what we already like the idea of we'll be ignoring (generally subsconsciously) evidence otherwise. But with models, better still to just accept they're not true and focus instead on trying to get an idea of how much that might matter (or indeed, to consider whether we really require an explicit distributional model at all).
This is a story about degrees of freedom and statistical parameters and why it is nice that the two have a direct simple connection.
Historically, the "$-1$" terms appeared in Euler's studies of the Beta function. He was using that parameterization by 1763, and so was Adrien-Marie Legendre: their usage established the subsequent mathematical convention. This work antedates all known statistical applications.
Modern mathematical theory provides ample indications, through the wealth of applications in analysis, number theory, and geometry, that the "$-1$" terms actually have some meaning. I have sketched some of those reasons in comments to the question.
Of more interest is what the "right" statistical parameterization ought to be. That is not quite as clear and it doesn't have to be the same as the mathematical convention. There is a huge web of commonly used, well-known, interrelated families of probability distributions. Thus, the conventions used to name (that is, parameterize) one family typically imply related conventions to name related families. Change one parameterization and you will want to change them all. We might therefore look at these relationships for clues.
Few people would disagree that the most important distribution families derive from the Normal family. Recall that a random variable $X$ is said to be "Normally distributed" when $(X-\mu)/\sigma$ has a probability density $f(x)$ proportional to $\exp(-x^2/2)$. When $\sigma=1$ and $\mu=0$, $X$ is said to have a standard normal distribution.
Many datasets $x_1, x_2, \ldots, x_n$ are studied using relatively simple statistics involving rational combinations of the data and low powers (typically squares). When those data are modeled as random samples from a Normal distribution--so that each $x_i$ is viewed as a realization of a Normal variable $X_i$, all the $X_i$ share a common distribution, and are independent--the distributions of those statistics are determined by that Normal distribution. The ones that arise most often in practice are
$t_\nu$, the Student $t$ distribution with $\nu = n-1$ "degrees of freedom." This is the distribution of the statistic $$t = \frac{\bar X}{\operatorname{se}(X)}$$ where $\bar X = (X_1 + X_2 + \cdots + X_n)/n$ models the mean of the data and $\operatorname{se}(X) = (1/\sqrt{n})\sqrt{(X_1^2+X_2^2 + \cdots + X_n^2)/(n-1) - \bar X^2}$ is the standard error of the mean. The division by $n-1$ shows that $n$ must be $2$ or greater, whence $\nu$ is an integer $1$ or greater. The formula, although apparently a little complicated, is the square root of a rational function of the data of degree two: it is relatively simple.
$\chi^2_\nu$, the $\chi^2$ (chi-squared) distribution with $\nu$ "degrees of freedom" (d.f.). This is the distribution of the sum of squares of $\nu$ independent standard Normal variables. The distribution of the mean of the squares of these variables will therefore be a $\chi^2$ distribution scaled by $1/\nu$: I will refer to this as a "normalized" $\chi^2$ distribution.
$F_{\nu_1, \nu_2}$, the $F$ ratio distribution with parameters $(\nu_1, \nu_2)$ is the ratio of two independent normalized $\chi^2$ distributions with $\nu_1$ and $\nu_2$ degrees of freedom.
Mathematical calculations show that all three of these distributions have densities. Importantly, the density of the $\chi^2_\nu$ distribution is proportional to the integrand in Euler's integral definition of the Gamma ($\Gamma$) function. Let's compare them:
$$f_{\chi^2_\nu}(2x) \propto x^{\nu/2 - 1}e^{-x};\quad f_{\Gamma(\nu)}(x) \propto x^{\nu-1}e^{-x}.$$
This shows that twice a $\chi^2_\nu$ variable has a Gamma distribution with parameter $\nu/2$. The factor of one-half is bothersome enough, but subtracting $1$ would make the relationship much worse. This already supplies a compelling answer to the question: if we want the parameter of a $\chi^2$ distribution to count the number of squared Normal variables that produce it (up to a factor of $1/2$), then the exponent in its density function must be one less than half that count.
Why is the factor of $1/2$ less troublesome than a difference of $1$? The reason is that the factor will remain consistent when we add things up. If the sum of squares of $n$ independent standard Normals is proportional to a Gamma distribution with parameter $n$ (times some factor), then the sum of squares of $m$ independent standard Normals is proportional to a Gamma distribution with parameter $m$ (times the same factor), whence the sum of squares of all $n+m$ variables is proportional to a Gamma distribution with parameter $m+n$ (still times the same factor). The fact that adding the parameters so closely emulates adding the counts is very helpful.
If, however, we were to remove that pesky-looking "$-1$" from the mathematical formulas, these nice relationships would become more complicated. For example, if we changed the parameterization of Gamma distributions to refer to the actual power of $x$ in the formula, so that a $\chi^2_1$ distribution would be related to a "Gamma$(0)$" distribution (since the power of $x$ in its PDF is $1-1=0$), then the sum of three $\chi^2_1$ distributions would have to be called a "Gamma$(2)$" distribution. In short, the close additive relationship between degrees of freedom and the parameter in Gamma distributions would be lost by removing the $-1$ from the formula and absorbing it in the parameter.
Similarly, the probability function of an $F$ ratio distribution is closely related to Beta distributions. Indeed, when $Y$ has an $F$ ratio distribution, the distribution of $Z=\nu_1 Y/(\nu_1 Y + \nu_2)$ has a Beta$(\nu_1/2, \nu_2/2)$ distribution. Its density function is proportional to
$$f_Z(z) \propto z^{\nu_1/2 - 1}(1-z)^{\nu_2/2-1}.$$
Furthermore--taking these ideas full circle--the square of a Student $t$ distribution with $\nu$ d.f. has an $F$ ratio distribution with parameters $(1,\nu)$. Once more it is apparent that keeping the conventional parameterization maintains a clear relationship with the underlying counts that contribute to the degrees of freedom.
From a statistical point of view, then, it would be most natural and simplest to use a variation of the conventional mathematical parameterizations of $\Gamma$ and Beta distributions: we should prefer calling a $\Gamma(\alpha)$ distribution a "$\Gamma(2\alpha)$ distribution" and the Beta$(\alpha, \beta)$ distribution ought to be called a "Beta$(2\alpha, 2\beta)$ distribution." In fact, we have already done that: this is precisely why we continue to use the names "Chi-squared" and "$F$ Ratio" distribution instead of "Gamma" and "Beta". Regardless, in no case would we want to remove the "$-1$" terms that appear in the mathematical formulas for their densities. If we did that, we would lose the direct connection between the parameters in the densities and the data counts with which they are associated: we would always be off by one.
Best Answer
You could model the variable $10Y \sim {\rm BetaBinomial}(n = 10, a, b)$. Specifically, if $X \sim {\rm BetaBinomial}(n, a, b)$, then $$\Pr[X = x] = \frac{\Gamma (b+1) \Gamma (a+n) \Gamma (n+x) \Gamma (a+b-x)}{\Gamma (a) \Gamma (n) \Gamma (x+1) \Gamma (b-x+1) \Gamma (a+b+n)}.$$ The only restriction on the parameters $a,b$ is that they be positive; $n$ must be a nonnegative integer; and $x \in \{0, 1, \ldots, n\}$. This PMF has many nice properties: see http://en.wikipedia.org/wiki/Beta-binomial_distribution