If this is your first visit, be sure to check out the FAQ by clicking the link above. You may have to register before you can post: click the register link above to proceed. To start viewing messages, select the forum that you want to visit from the selection below. |
|
|
Thread Tools | Display Modes |
#1
|
|||
|
|||
OT Statistics help
Hi,
I have to review some data and and I don't understand the term " back-transformed means " I know it's something to do with averages but can any one explain it in simple terms (the simpler the beterG) and how accurate is it? TIA Alison |
#2
|
|||
|
|||
Alison wrote:
Hi, I have to review some data and and I don't understand the term " back-transformed means " I know it's something to do with averages but can any one explain it in simple terms (the simpler the beterG) and how accurate is it? TIA Alison Here's a slide show that gives a brief definition. When the simple arithmetic mean isn't a good representation of the data, sometimes the data are transformed (e.g., by taking log10 of each data point), then averaging the transformed values. The resulting mean is still expressed as a log value, so it is back-transformed (10 raised to the log value) to give a geometric mean of the original data set - which normally would be different than the arithmetic mean. http://www.plantbio.ohiou.edu/epb/in...pdf/lec1&2.pdf HTH FurPaw -- Brain cells come and brain cells go, but fat cells live forever. To reply, unleash the dog. |
#3
|
|||
|
|||
Alison wrote:
Hi, I have to review some data and and I don't understand the term " back-transformed means " I know it's something to do with averages but can any one explain it in simple terms (the simpler the beterG) and how accurate is it? TIA Alison Here's a slide show that gives a brief definition. When the simple arithmetic mean isn't a good representation of the data, sometimes the data are transformed (e.g., by taking log10 of each data point), then averaging the transformed values. The resulting mean is still expressed as a log value, so it is back-transformed (10 raised to the log value) to give a geometric mean of the original data set - which normally would be different than the arithmetic mean. http://www.plantbio.ohiou.edu/epb/in...pdf/lec1&2.pdf HTH FurPaw -- Brain cells come and brain cells go, but fat cells live forever. To reply, unleash the dog. |
#4
|
|||
|
|||
Alison wrote:
Hi, I have to review some data and and I don't understand the term " back-transformed means " I know it's something to do with averages but can any one explain it in simple terms (the simpler the beterG) and how accurate is it? TIA Alison Here's a slide show that gives a brief definition. When the simple arithmetic mean isn't a good representation of the data, sometimes the data are transformed (e.g., by taking log10 of each data point), then averaging the transformed values. The resulting mean is still expressed as a log value, so it is back-transformed (10 raised to the log value) to give a geometric mean of the original data set - which normally would be different than the arithmetic mean. http://www.plantbio.ohiou.edu/epb/in...pdf/lec1&2.pdf HTH FurPaw -- Brain cells come and brain cells go, but fat cells live forever. To reply, unleash the dog. |
#5
|
|||
|
|||
Alison wrote:
Hi, I have to review some data and and I don't understand the term " back-transformed means " I know it's something to do with averages but can any one explain it in simple terms (the simpler the beterG) and how accurate is it? TIA Alison Here's a slide show that gives a brief definition. When the simple arithmetic mean isn't a good representation of the data, sometimes the data are transformed (e.g., by taking log10 of each data point), then averaging the transformed values. The resulting mean is still expressed as a log value, so it is back-transformed (10 raised to the log value) to give a geometric mean of the original data set - which normally would be different than the arithmetic mean. http://www.plantbio.ohiou.edu/epb/in...pdf/lec1&2.pdf HTH FurPaw -- Brain cells come and brain cells go, but fat cells live forever. To reply, unleash the dog. |
#6
|
|||
|
|||
"FurPaw" wrote in message ... Here's a slide show that gives a brief definition. When the simple arithmetic mean isn't a good representation of the data, sometimes the data are transformed (e.g., by taking log10 of each data point), then averaging the transformed values. The resulting mean is still expressed as a log value, so it is back-transformed (10 raised to the log value) to give a geometric mean of the original data set - which normally would be different than the arithmetic mean. http://www.plantbio.ohiou.edu/epb/in...ures/pdf/lec1& 2.pdf HTH FurPaw Thanks Furpaw, That helps . I took out a maths school book from the library today and I didn't realise there was so much I'd forgotten. Maths wasn't my strong point at school but at least we didn't use calculators in exams like kids do now. Alison |
#7
|
|||
|
|||
"FurPaw" wrote in message ... Here's a slide show that gives a brief definition. When the simple arithmetic mean isn't a good representation of the data, sometimes the data are transformed (e.g., by taking log10 of each data point), then averaging the transformed values. The resulting mean is still expressed as a log value, so it is back-transformed (10 raised to the log value) to give a geometric mean of the original data set - which normally would be different than the arithmetic mean. http://www.plantbio.ohiou.edu/epb/in...ures/pdf/lec1& 2.pdf HTH FurPaw Thanks Furpaw, That helps . I took out a maths school book from the library today and I didn't realise there was so much I'd forgotten. Maths wasn't my strong point at school but at least we didn't use calculators in exams like kids do now. Alison |
#8
|
|||
|
|||
"FurPaw" wrote in message ... Here's a slide show that gives a brief definition. When the simple arithmetic mean isn't a good representation of the data, sometimes the data are transformed (e.g., by taking log10 of each data point), then averaging the transformed values. The resulting mean is still expressed as a log value, so it is back-transformed (10 raised to the log value) to give a geometric mean of the original data set - which normally would be different than the arithmetic mean. http://www.plantbio.ohiou.edu/epb/in...ures/pdf/lec1& 2.pdf HTH FurPaw Thanks Furpaw, That helps . I took out a maths school book from the library today and I didn't realise there was so much I'd forgotten. Maths wasn't my strong point at school but at least we didn't use calculators in exams like kids do now. Alison |
#9
|
|||
|
|||
"FurPaw" wrote in message ... Here's a slide show that gives a brief definition. When the simple arithmetic mean isn't a good representation of the data, sometimes the data are transformed (e.g., by taking log10 of each data point), then averaging the transformed values. The resulting mean is still expressed as a log value, so it is back-transformed (10 raised to the log value) to give a geometric mean of the original data set - which normally would be different than the arithmetic mean. http://www.plantbio.ohiou.edu/epb/in...ures/pdf/lec1& 2.pdf HTH FurPaw Thanks Furpaw, That helps . I took out a maths school book from the library today and I didn't realise there was so much I'd forgotten. Maths wasn't my strong point at school but at least we didn't use calculators in exams like kids do now. Alison |
Thread Tools | |
Display Modes | |
|
|