Kavish, the short answer is yes, if I understand your question. I would think that what you describe is more or less a histogram (although I've seen strange definitions of histogram too). Number of times, or percentage of time, a given number, or range of numbers, occurs, on the Y axis. And on the X axis, the parameter, or bin of values.

Such as, run the pseudo-random number generator in your program, and see the distribution of those random numbers. Let's say, in 10 bins on the X axis, for the ranges 0 to < 0.1, then 0.1 to < 0.2, 0.2 to < 0.3, ... , and lastly 0.9 to < 1.0. (Many PRNGs never quite provide 1.0 as a result.)

In this example, a decent PRNG would produce a flat line, over a large number of trials. You want an even distribution of values to be generated by the PRNG, over time.

On the other hand, you might be plotting the waiting times for customers at a checkout counter in a supermarket. In that case, you won't expect a flat line. More like, very few customers require very little time at the cashier, very few require a very long time, and the majority will fall somewhere between. In this example something more like a normal distribution would be expected.

To show skew from a true normal distribution, possibly you could superimpose a normal distribution of roughly the same mean and sigma values that your bar chart of waiting times comes up with.

Not sure if this answers your question.

Yes. The bar graphs give an idea about the distribution of the variable. Many exploratory researchers start with that