# histogram yelp wat sort of distribution is this?

Watch
Announcements
#1

1. Is it wrong to say this is a normal distribution i.e. bell shaped? mean is 15.6 and mode is 15
0
4 years ago
#2
(Original post by Danny McCoyne)

1. Is it wrong to say this is a normal distribution i.e. bell shaped? mean is 15.6 and mode is 15
Is the data continuous? If so, it looks reasonably like a suitable Gamma distribution or a Gumbel distribution. Against normaility it appears to be strictly positive and to be skewed.

However, the big quesions are (i) where did it come from (i.e. what sort of mechanism?) and (ii) what do you want to do with it? A normal approximation may be sufficient depending on the purpose of the analysis.
0
#3
(Original post by Gregorius)
Is the data continuous? If so, it looks reasonably like a suitable Gamma distribution or a Gumbel distribution. Against normaility it appears to be strictly positive and to be skewed.

However, the big quesions are (i) where did it come from (i.e. what sort of mechanism?) and (ii) what do you want to do with it? A normal approximation may be sufficient depending on the purpose of the analysis.
It's number of hospital visits for 100 people in 5 years. So the 40 on the histogram covers 37-40.
0
4 years ago
#4
(Original post by Danny McCoyne)
It's number of hospital visits for 100 people in 5 years. So the 40 on the histogram covers 37-40.
Right. Then these are best modelled as over-dispersed Poisson - that it, like a Poisson distribution but with the variance not tied to the mean. The nicest distribution with this property is the Negative Binomial distribution. This distribution and supporting ancillary procedures (like regression) are built into most modern software packages.
0
#5
(Original post by Gregorius)
Right. Then these are best modelled as over-dispersed Poisson - that it, like a Poisson distribution but with the variance not tied to the mean. The nicest distribution with this property is the Negative Binomial distribution. This distribution and supporting ancillary procedures (like regression) are built into most modern software packages.
Right, I see. So are you saying that you cannot infer whether the histogram in the OP is normally distributed or not?
0
4 years ago
#6
(Original post by Danny McCoyne)
Right, I see. So are you saying that you cannot infer whether the histogram in the OP is normally distributed or not?
It can't be a normal distribution. There are no negative value.
0
X

new posts
Back
to top
Latest
My Feed

### Oops, nobody has postedin the last few hours.

Why not re-start the conversation?

see more

### See more of what you like onThe Student Room

You can personalise what you see on TSR. Tell us a little about yourself to get started.

### Poll

Join the discussion

#### Current uni students - are you thinking of dropping out of university?

Yes, I'm seriously considering dropping out (47)
16.04%
I'm not sure (8)
2.73%
No, I'm going to stick it out for now (100)
34.13%
I have already dropped out (4)
1.37%
I'm not a current university student (134)
45.73%