Data squashing, Advanced Statistics

An approach to decrease the size of very large data sets in which the data are first 'binned' and then statistics such as the mean and variance/covariance are calculated on each bin. These statistics are then used to obtain a new sample in each bin to construct a reduced data set with the similar statistical properties to original one.

Posted Date: 7/27/2012 2:03:17 AM | Location : United States







Related Discussions:- Data squashing, Assignment Help, Ask Question on Data squashing, Get Answer, Expert's Help, Data squashing Discussions

Write discussion on Data squashing
Your posts are moderated
Related Questions
Attack rate : This term frequently used for the incidence of the disease or condition in the particular group, or during a limited interval of time, or under the special circumstan

The probability distribution, f (x), of largest extreme can be given as    The location parameter, α is the mode and β is the scale parameter. The mean, variance skewn

Confidence interval : A range of the values, calculated from the sample observations which is believed, with the particular probability, to posses the true parameter value. A 95% c

Lancaster models : The means of representing the joint distribution of the set of variables in terms of the marginal distributions, supposing all the interactions higher than a par

Mosaic displays  is the graphical display of the standardized residuals from the fitting a log-linear model to a contingency table in which the colour and outline of the mosaic's '

Coefficient of concordance : The coef?cient is taken in use to assess the agreement among m raters ranking n individuals according to some of the speci?c characteristic. Which can

Censored observations : An observation xi on some variable of interest is consired to be censored if it is known that xi Li (left-censored)or xi Ui (right-censored) where Li and Ui

A construction for events that happen in some planar area a, consisting of the series of 'territories' each of which comprises of that part of a closer to the particular event xi t

Behrens Fisher problem : The difficulty of testing for the equality of the means of the two normal distributions which do not have the equal variance. Various test statistics have

The process of providing the numerical value for the population parameter on the basis of information gathered from a sample. If a single ?gure is computed for the unknown paramete