Timeline for Lower Denomination Imputation
Current License: CC BY-SA 3.0
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 13, 2017 at 9:53 | answer | added | DivyaJyoti Rajdev | timeline score: 0 | |
| Jan 19, 2016 at 15:53 | comment | added | Michael Barrowman | I've searched for literature but couldn't find any. I had hoped someone on here could provide some but alas, I guess not. I'll just have to figure it out myself, write it up and be the first! | |
| Jan 19, 2016 at 15:42 | comment | added | Nick Cox | I don't know specific literature, which means no more than it says. My impression in general is that data management of this kind is often poorly documented. No one wants to write about it: it can be embarrassing to yourself or data providers if datasets are publicly shown to be lousy, as they usually are; the details often seem too mundane or too localised to deserve writing up; and most of the rewards are elsewhere, for interesting results or a new method or model for analysis. | |
| Jan 19, 2016 at 15:30 | comment | added | Michael Barrowman | My main question was whether there is any documentation on how to deal with this kind of situation. It would work for other situations (weight, prices, volume or any other measurement with a lower denominator). I didn't want to perform multiple imputation straight away on the lower denomination as I was worried that this might cause some sort of a bias in my results (estimating 6'11" because inches should be 11 regardless of feet), but also thought that splitting the data up would cause a greater bias as it would only be analysing a portion of the data. | |
| Jan 19, 2016 at 15:22 | comment | added | Nick Cox | You seemed to be suggesting zero inches as the replacement input for missing; I am suggesting only that an interval midpoint or an empirical mean would work better. I am happy to agree that you could do better still if you could use other variables within multiple imputation. Although you mention that context clearly, your question didn't seem to be about it. | |
| Jan 19, 2016 at 15:18 | comment | added | Michael Barrowman | Hi Nick, thanks for your input in regards to the units. I had assumed, rather naively, that people knew of feet and inches even if they didn't use them. In your suggestion, do you mean to use the same value for everyone with NAs in the 5' bracket? I don't think this would be the right way to go as it would essentially be performing an overall mean imputation on each bracket which doesn't tend to give good results (plus, as far as I'm aware, wouldn't work under a multiple imputation model). | |
| Jan 19, 2016 at 13:46 | comment | added | Nick Cox | Just to point out that in statistical circles "skew" is not synonymous with "bias". | |
| Jan 19, 2016 at 13:42 | history | edited | Michael Barrowman | CC BY-SA 3.0 |
edited body
|
| Jan 19, 2016 at 13:38 | comment | added | Nick Cox | For readers in this thoroughly international forum puzzled by these quaint units: 1 inch, written sometimes 1", is 25.4 mm; 1 foot, written sometimes 1', is 12 inches. From other data you should able to work out the means of those 4 foot and up, 5 foot and up, 6 foot and up. In other situations using a midpoint would be a much better stab than using zero (which is indeed absurd), but you should be able to do better than 4'6" (I guess much too low) or 6'6" (too high). | |
| Jan 19, 2016 at 13:21 | review | First posts | |||
| Jan 19, 2016 at 13:24 | |||||
| Jan 19, 2016 at 13:19 | history | asked | Michael Barrowman | CC BY-SA 3.0 |