kde2d                  package:MASS                  R Documentation

_T_w_o-_D_i_m_e_n_s_i_o_n_a_l _K_e_r_n_e_l _D_e_n_s_i_t_y _E_s_t_i_m_a_t_i_o_n

_D_e_s_c_r_i_p_t_i_o_n:

     Two-dimensional kernel density estimation with an axis-aligned
     bivariate normal kernel, evaluated on a square grid.

_U_s_a_g_e:

     kde2d(x, y, h, n = 25, lims = c(range(x), range(y)))

_A_r_g_u_m_e_n_t_s:

       x: x coordinate of data 

       y: y coordinate of data 

       h: vector of bandwidths for x and y directions. Defaults to
          normal reference bandwidth (see 'bandwidth.nrd'). 

       n: Number of grid points in each direction. 

    lims: The limits of the rectangle covered by the grid as 'c(xl, xu,
          yl, yu)'. 

_V_a_l_u_e:

     A list of three components.

    x, y: The x and y coordinates of the grid points, vectors of length
          'n'. 

       z: An 'n'  x  'n' matrix of the evaluated density. 

_R_e_f_e_r_e_n_c_e_s:

     Venables, W. N. and Ripley, B. D. (2002) _Modern Applied
     Statistics with S._ Fourth edition.  Springer.

_E_x_a_m_p_l_e_s:

     attach(geyser)
     plot(duration, waiting, xlim = c(0.5,6), ylim = c(40,100))
     f1 <- kde2d(duration, waiting, n = 50, lims = c(0.5, 6, 40, 100))
     image(f1, zlim = c(0, 0.05))
     f2 <- kde2d(duration, waiting, n = 50, lims = c(0.5, 6, 40, 100),
                 h = c(width.SJ(duration), width.SJ(waiting)) )
     image(f2, zlim = c(0, 0.05))
     persp(f2, phi = 30, theta = 20, d = 5)

     plot(duration[-272], duration[-1], xlim = c(0.5, 6),
          ylim = c(1, 6),xlab = "previous duration", ylab = "duration")
     f1 <- kde2d(duration[-272], duration[-1],
                 h = rep(1.5, 2), n = 50, lims = c(0.5, 6, 0.5, 6))
     contour(f1, xlab = "previous duration",
             ylab = "duration", levels  =  c(0.05, 0.1, 0.2, 0.4) )
     f1 <- kde2d(duration[-272], duration[-1],
                 h = rep(0.6, 2), n = 50, lims = c(0.5, 6, 0.5, 6))
     contour(f1, xlab = "previous duration",
             ylab = "duration", levels  =  c(0.05, 0.1, 0.2, 0.4) )
     f1 <- kde2d(duration[-272], duration[-1],
                 h = rep(0.4, 2), n = 50, lims = c(0.5, 6, 0.5, 6))
     contour(f1, xlab = "previous duration",
             ylab = "duration", levels  =  c(0.05, 0.1, 0.2, 0.4) )
     detach("geyser")