Dear Virgilio,
Interesting problem. Let me know if you need help collecting data. ;)
Thanks :) Actually, I'm busy with developing a Location-Based Service (a
restaurant finder to be precise) utilising SDA. The goal of my research is
to integrate SDA in an LBS. For this purpose, I've gathered about 13,000
unique restaurants in the Netherlands and would like to use 3 SDA techniques
that enhance the restaurant finder either visually and/or analytically. The
motivation behind my research is to start a discussion on how SDA can be
used inside LBSs to enhance the services. In this case, to enable users to
make better decisions about nearby restaurants. One thing that popped in my
mind was to use kernel density estimation and overlay it on the
google/microsoft map to allow users to easily grasp the proximity of
restaurants.
Depending on the number of different types of restaurants, you may want
> to estimate a different surface for each type. Basically, you may
> consider a multivariate point pattern, so that you estimate a different
> surface for each type and you compare then to see if they are similar
> or not. This will address the question of whether the spatial
> distribution of different types of restaurants is the same or not
This is quite interesting. Would this allow me to estimate a surface for
let's say Italian restaurants vs Greek restaurants? I have ratings for each
restaurant. So a user might want to ask "Where can I find good Italian
restaurants in the South?" Where good is any rating above a 7.0 for example.
You may also want to compute bivariate K-functions (see 'k12hat' in
> splancs; 'Kmulti' in spatstat) to detect differences between the spatial
> distributions of types of restaurants. This will give you a partial
> answer to Question 2.
Would this mean that a kmulti analysis should be applied for each restaurant
type and thus each subset I wish to test?
Have you considered to test for whether a certain type of
> restaurant tends to appear around a particular area of the city? For
> example, are Chinese restaurants clustered around Chinatown?
This is something I'm looking for as well. Considering the fact that I'm in
the process of developing such an LBS, it would be something along the line
of: A user takes out his mobile phone. He starts the application and the
applications looks acquires a position fix. When this is done, a user might
want to know: "What type of restaurant is typical for my current location or
current neighbourhood. So, analysing whether a certain type of restaurant
tends to appear around the CURRENT area of the city. Is this possible?
Finally, another option is to aggregate your data (counts per
> neighbourhood, for example) and do a similar analysis as in disease
> mapping.
>
I'll have a go with the literature on disease mapping. Thanks for pointing
me into that direction.
Overall, thanks very much for your reply. I'm really excited about using
these SDA techniques and am very grateful for your quick reply. I'll look up
a copy of the papers you mentioned and will read through them as soon as I
can. When I've successfully analysed the dataset with some SDA techniques I
can begin the process of constructing the appropriate architecture for the
LBS. I'll definitely keep you guys posted if you're interested.
2009/2/15 Virgilio Gomez Rubio <virgilio.go...@uclm.es>
> Dear Michel,
>
> > I'm new to Spatial Data Analysis and have just begun working through
> > "Applied Spatial Data Analysis wit R" by Bivand et al. For my research I
> > would like to use SDA to be able to tell more about my restaurant data
> set
> > than just pinpointing them on a google map. So far, from reading the
> > literature on SDA I've been able to construct the following questions.
>
> Interesting problem. Let me know if you need help collecting data. ;)
>
> >
> > 1. How far / close are restaurants from each other? (answered by using
> > kernel density estimation)
> > 2. Which type of restaurants stand next to each other?
> > 3. How are the restaurants positioned relatlivey from each other?
> > 4. What's the difference between restaurant A and restaurant B?
>
>
> Questions 2 and 3 are much alike, and I believe that question 4 is too
> general and not necessarily about the spatial distribution of the
> restaurants.
>
> Depending on the number of different types of restaurants, you may want
> to estimate a different surface for each type. Basically, you may
> consider a multivariate point pattern, so that you estimate a different
> surface for each type and you compare then to see if they are similar
> or not. This will address the question of whether the spatial
> distribution of different types of restaurants is the same or not. This
> is discussed in Diggle et al. (2005, JRSS Series A). Some of the methods
> described in the paper are implemented in package spatialkernel.
>
> You may also want to compute bivariate K-functions (see 'k12hat' in
> splancs; 'Kmulti' in spatstat) to detect differences between the spatial
> distributions of types of restaurants. This will give you a partial
> answer to Question 2.
>
> If you have a set of covariates for each restaurant and you want to
> estimate their effect and how they explain the spatial distribution of
> the data you can check Diggle et al. (2006, Biometrics). There is also
> an example of this in Bivand et al. (2008).
>
> I am not sure about the best way of tackling Question 3 (and why this is
> important). Have you considered to test for whether a certain type of
> restaurant tends to appear around a particular area of the city? For
> example, are Chinese restaurants clustered around Chinatown?
>
> Finally, another option is to aggregate your data (counts per
> neighbourhood, for example) and do a similar analysis as in disease
> mapping.
>
> > I've exported a subset of my dataset to CSV in order to import it in R.
> > Currently, my CSV file is of the form
> >
> > *restaurant name; latitude; longitude; type*
> > Amigo;52.996058;6.564229;Italian
> > Bella Italia;52.99281;6.560353;Italian
> > Isola Bella;52.993764;6.560245;Italian
>
> I would not use long/lat but UTM to do your analysis. You can do this
> very easily with R.
>
> >
> > I've tried to import the CSV in R by doing:
> >
> > library(spatstat)
> > info <- read.csv(file = "sample.csv", sep = ";", strip.white = TRUE)
> > win <- owin(c(0,100),c(0,100))
> > pattern <- ppp(info$lat, info$lng, window = win, marks=info$name)
> >
> > However, if I plot the pattern, the points are all cluttered. What advice
> > could you give me on setting the window size?
>
> If you try to plot more than 10,000 points, then I am not surprised that
> they are all cluttered. :) I would plot the estimated intensity of the
> point patterns. Or you may aggregate your data and produce a map based
> on the neighbourhoods in your area.
>
> Hope this helps.
>
> Virgilio
>
[[alternative HTML version deleted]]
_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@stat.math.ethz.ch
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
