- Hi Ranji,I am not sure if this is correct, but it sounds like the longer measuring period (14 days?) results in more accurate readings. In other words, the longer time you spend "sampling", the more correct are your resistivity readings, and the less "sampling and analytical error" there is.Regards,Colin[Colin Badenhorst] -----Original Message-----
**From:**Rajni Gaur [mailto:rajni.geophy@...]**Sent:**04 September 2005 13:01**To:**ai-geostats@...**Subject:**[ai-geostats] Nugget effect...Dear list members,I have a querry regarding the presence of nugget effect. I have brought to the notice of my seniors before that iam working on the variography of the resistivity data.I have been monitoring the resisivity variations at a fixed point from past many months with a frequency of 7 days or sometimes 14 days. I have come across the remarkable changes in the resitivity values. Simultaneously i have been incorporating the variograms on the acquired values of resitivity. As the time is passing by the nuggest effect is decreasing witht the changes in the resistivity values. though it is not sure the resistivity increase or sometimes it decrease also but nugget effect is showing a decline in the value. Iam not able to interpret this change in the nugget effect. though it is good but in the initial value the nugget effect comes to be 1500 and then after 1 month the value reduces to 300.It would be help to me if list suggest me some thing better for my interpretation work.thanks in advance to all of you who consider me seriously.regardsRajni - Do you have non-spatial control data? i.e. have you measured resistivity at single locations at a number of frequencies? This should help show you whether the effect you are seeing on the spatial data set is due to uncreased accuracy with longer frequency (as suggested by Colin Badenhorst, which would show up as a decreasing variance with increasing frequency at a single location) or due to an interaction between the act of measurement and the value being measured (which would show up as a regression towards an underlying constant, value dependent on the environment), or some other cause, to be postulated based on the results from the contol experiments. But the control experiments are crucial - not just in this case, where you can (a posteriori) see a need for them, but in any experiment involving data possibly dependent on more than one primary factor (in this case, spatial location of observation and observation frequency).Barrie Wells----- Original Message -----
**From:**Rajni Gaur**To:**ai-geostats@...**Sent:**Sunday, September 04, 2005 2:01 PM**Subject:**[ai-geostats] Nugget effect...Dear list members,I have a querry regarding the presence of nugget effect. I have brought to the notice of my seniors before that iam working on the variography of the resistivity data.I have been monitoring the resisivity variations at a fixed point from past many months with a frequency of 7 days or sometimes 14 days. I have come across the remarkable changes in the resitivity values. Simultaneously i have been incorporating the variograms on the acquired values of resitivity. As the time is passing by the nuggest effect is decreasing witht the changes in the resistivity values. though it is not sure the resistivity increase or sometimes it decrease also but nugget effect is showing a decline in the value. Iam not able to interpret this change in the nugget effect. though it is good but in the initial value the nugget effect comes to be 1500 and then after 1 month the value reduces to 300.It would be help to me if list suggest me some thing better for my interpretation work.thanks in advance to all of you who consider me seriously.regardsRajni

* By using the ai-geostats mailing list you agree to follow its rules

( see http://www.ai-geostats.org/help_ai-geostats.htm )

* To unsubscribe to ai-geostats, send the following in the subject or in the body (plain text format) of an email message to sympa@...

Signoff ai-geostats - RajniThe nugget effect is the variance of the difference in values at very short distances. Your calculated nugget effect is an estimate of a true variance.To start with, you have few observations and therefore few degrees of freedom. A confidence interval in your estimated variance is going to be hugely wide around your estimate. Since your first period of observations are very close together, this reduces the degrees of freedom even further. In short, your early estimates of variance could be widely different from the real value.As time goes on, two things happen: you get more observations and (more importantly) they are more widely separated. Your confidence in the estimated nugget effect will increase dramatically as the extent of your observations increases relative to your range of influence.Isobel
wrote:*Rajni Gaur <rajni.geophy@...>*Dear list members,I have a querry regarding the presence of nugget effect. I have brought to the notice of my seniors before that iam working on the variography of the resistivity data.I have been monitoring the resisivity variations at a fixed point from past many months with a frequency of 7 days or sometimes 14 days. I have come across the remarkable changes in the resitivity values. Simultaneously i have been incorporating the variograms on the acquired values of resitivity. As the time is passing by the nuggest effect is decreasing witht the changes in the resistivity values. though it is not sure the resistivity increase or sometimes it decrease also but nugget effect is showing a decline in the value. Iam not able to interpret this change in the nugget effect. though it is good but in the initial value the nugget effect comes to be 1500 and then after 1 month the value reduces to 300.It would be help to me if list suggest me some thing better for my interpretation work.thanks in advance to all of you who consider me seriously.regardsRajni* By using the ai-geostats mailing list you agree to follow its rules

( see http://www.ai-geostats.org/help_ai-geostats.htm )

* To unsubscribe to ai-geostats, send the following in the subject or in the body (plain text format) of an email message to sympa@...

Signoff ai-geostats - Dear Mam and List members,Sorry I could not get to your mail early. I must clarify that every time the number of observations are the same. Iam measuring the values at the same place and exactly at the same point but the vary in time and not in space. everytime of measurement the X and Y remains same.So with time Iam getting the same number of observations.Iam sorry If I have misunderstood your point.One more querry I have regarding the coefficient of variation. How the changes in coefficient of variation effect the semivariogram?Thanks in advanceRegardsRajni

On 9/5/05,**Isobel Clark**<drisobelclark@...> wrote:RajniThe nugget effect is the variance of the difference in values at very short distances. Your calculated nugget effect is an estimate of a true variance.To start with, you have few observations and therefore few degrees of freedom. A confidence interval in your estimated variance is going to be hugely wide around your estimate. Since your first period of observations are very close together, this reduces the degrees of freedom even further. In short, your early estimates of variance could be widely different from the real value.As time goes on, two things happen: you get more observations and (more importantly) they are more widely separated. Your confidence in the estimated nugget effect will increase dramatically as the extent of your observations increases relative to your range of influence.Isobel* By using the ai-geostats mailing list you agree to follow its rulesDear list members,It would be help to me if list suggest me some thing better for my interpretation work.thanks in advance to all of you who consider me seriously.regardsRajni

( see http://www.ai-geostats.org/help_ai-geostats.htm )

* To unsubscribe to ai-geostats, send the following in the subject or in the body (plain text format) of an email message to sympa@...

Signoff ai-geostats

- Rajni,

In simulations that I've done using data created with the same variogram but different CV's, increasing the CV scales the variogram sill and nugget higher. As the expected value of the sample variance equals the average value of the variogram at all distances (not, as often interpreted, the sill) changing the CV and thus the expected value of the sample variance does raise the sill. The range is unaffected. In practice, however, higher CV's make estimating the variogram from the data more difficult and require greater samples sizes. Cressie and Hawkins (1980) method of robust variogram estimation may provide a better variogram in this case. Be careful to examine the histogram of the data as high CV's may be indicative non-normality which may necessitate transformation of the data. Isobel Clark is the expert on this issue.

Cressie, N. and Hawkins, D. M. (1980). Robust estimation of the variogram. Mathematical Geology 12, 115-125.

john

At 06:56 PM 10/1/2005 +0530, Rajni Gaur wrote:Dear Mam and List members,

Sorry I could not get to your mail early. I must clarify that every time the number of observations are the same. Iam measuring the values at the same place and exactly at the same point but the vary in time and not in space. everytime of measurement the X and Y remains same.

So with time Iam getting the same number of observations.

Iam sorry If I have misunderstood your point.

One more querry I have regarding the coefficient of variation. How the changes in coefficient of variation effect the semivariogram?

Thanks in advance

Regards

Rajni

On 9/5/05,**Isobel Clark**<drisobelclark@...> wrote:- Rajni
- The nugget effect is the variance of the difference in values at very short distances. Your calculated nugget effect is an estimate of a true variance.
- To start with, you have few observations and therefore few degrees of freedom. A confidence interval in your estimated variance is going to be hugely wide around your estimate. Since your first period of observations are very close together, this reduces the degrees of freedom even further. In short, your early estimates of variance could be widely different from the real value.
- As time goes on, two things happen: you get more observations and (more importantly) they are more widely separated. Your confidence in the estimated nugget effect will increase dramatically as the extent of your observations increases relative to your range of influence.
- Isobel

- Rajni Gaur <rajni.geophy@...> wrote:
- Dear list members,
- It would be help to me if list suggest me some thing better for my interpretation work.
- thanks in advance to all of you who consider me seriously.
- regards
- Rajni
- * By using the ai-geostats mailing list you agree to follow its rules
- ( see
http://www.ai-geostats.org/help_ai-geostats.htm
)
- * To unsubscribe to ai-geostats, send the following in the subject or in the body (plain text format) of an email message to sympa@...
- Signoff ai-geostats

* By using the ai-geostats mailing list you agree to follow its rules

( see http://www.ai-geostats.org/help_ai-geostats.htm )

* To unsubscribe to ai-geostats, send the following in the subject or in the body (plain text format) of an email message to sympa@...

Signoff ai-geostatsJohn Walter

Virginia Institute of Marine Science

P.O. Box 1346

Gloucester Point, VA 23062

(804) 684-7316

jfwalter@...