helicopter               package:nlreg               R Documentation

_H_e_l_i_c_o_p_t_e_r _D_a_t_a

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

     The 'helicopter' data frame has 9 rows and 6 columns.

     Experimental design for studying the influences of the factors
     wing  length and wing width on a paper helicopter's flight time. 
     The goal is  to find the factor setting that maximizes flight time
     when the paper  helicopter is dropped from a fixed height of 15.5
     feet

_U_s_a_g_e:

     data(helicopter)

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

     A data frame with 9 observations on the following 6 variables:

     '_L' wing length in inches; 

     '_W' wing width in inches;

     '_B' base length (always set to 3in);

     '_H' base height (always set to 2in);

     '_O_r_d_e_r' run order;

     '_T_i_m_e' flight time in seconds.

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

     The data were obtained from

     Annis, D. H. (2006)  Rethinking the paper helicopter: Combining 
     statistical and engineering knowledge.  _The American 
     Statistician_, *59*, 320-326.

_R_e_f_e_r_e_n_c_e_s:

     Box, G. E. P. (1992)  Teaching engineers experimental design with
     a paper helicopter.  _Quality Engineering_, *4*, 453-459.

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

     data(helicopter)
     ##
     ## fit model (5) of Annis (2005)
     ## -----------------------------
     heli <- helicopter
     ##
     heli$LW <- heli$L * heli$W
     heli$S <- heli$B * heli$H + ( 2 * heli$L + 1 ) * heli$W
     heli$logTime <- log( heli$Time )
     heli$Y <- heli$logTime + log( heli$S ) / 2
     #
     heli.nlreg <- nlreg( Y ~ b0 + b1 * log( b2^2 / LW + LW ), data = heli, 
                         start = c( b0 = 6, b1 = -1, b2 = 20 ) )

