

MGH10(NISTnls)                               R Documentation

_M_o_r_e_, _G_a_b_r_o_w _a_n_d _H_i_l_l_s_t_r_o_m _e_x_a_m_p_l_e _1_0

_D_e_s_c_r_i_p_t_i_o_n_:

     The `MGH10' data frame has 16 rows and 2 columns.

_A_r_g_u_m_e_n_t_s_:

       y: A numeric vector of response values.

       x: A numeric vector of input values.

_F_o_r_m_a_t_:

     This data frame contains the following columns:

_D_e_t_a_i_l_s_:

     This problem was found to be difficult for some very
     good algorithms.

     See More, J. J., Garbow, B. S., and Hillstrom, K. E.
     (1981).  Testing unconstrained optimization software.
     ACM Transactions on Mathematical Software. 7(1): pp.
     17-41.

_A_u_t_h_o_r_(_s_)_:

_S_o_u_r_c_e_:

     Meyer, R. R. (1970).  Theoretical and computational
     aspects of nonlinear regression.  In Nonlinear Program-
     ming, Rosen, Mangasarian and Ritter (Eds).  New York,
     NY: Academic Press, pp. 465-486.

_E_x_a_m_p_l_e_s_:

     library(NISTnls)
     data(MGH10)
     plot(y ~ x, data = MGH10)
     ## check plot on log scale for shape
     plot(y ~ x, data = MGH10, log = "y")
     ## starting values for this run are ridiculous
     fm1 <- nls(y ~ b1 * exp(b2/(x+b3)), data = MGH10, trace = TRUE,
                start = c(b1 = 2, b2 = 400000, b3 = 25000),
                warnOnly = TRUE)
     fm2 <- nls(y ~ b1 * exp(b2/(x+b3)), data = MGH10, trace = TRUE,
                start = c(b1 = 0.02, b2 = 4000, b3 = 250),
                warnOnly = TRUE)
     fm3 <- nls(y ~ exp(b2/(x+b3)), data = MGH10, trace = TRUE,
                start = c(b2 = 400000, b3 = 25000),
                warnOnly = TRUE, algorithm = "plinear")
     fm4 <- nls(y ~ exp(b2/(x+b3)), data = MGH10, trace = TRUE,
                start = c(b2 = 4000, b3 = 250),
                warnOnly = TRUE, algorithm = "plinear")

