
ONEWAY/TTEST(1)        UNIX User's Manual         ONEWAY/TTEST(1)

NAME
     oneway/ttest - one way analysis of variance and t-test

SYNOPSIS
     oneway [-t] [-s splitter] [group names]

DESCRIPTION
     _o_n_e_w_a_y does a one-way analysis of variance on data from dif-
     ferent groups.  The group sizes can differ, in which case, a
     weighted means solution is used.

     The input format is simple: each group's data is separated
     from other groups' by including a special value, called the
     splitter.

OPTIONS
     Group names can be supplied on the command line.  Otherwise,
     names like ``Group 1'' are used.

     -s splitter
          This value is used to tell when one group's data ends
          and another's begins.

     -t   Request a between group's t-test format for the signi-
          ficance test.  This option is automatic when the pro-
          gram is called _t_t_e_s_t.

EXAMPLE
     Suppose you had two groups of data in two files, called
     ``long'' and ``short.'' To compare these, you would do some-
     thing like:
        echo 999 | cat long - short | oneway -s 999 long short

ALGORITHM
     The algorithm follows Guilford & Fruchter's _F_u_n_d_a_m_e_n_t_a_l
     _S_t_a_t_i_s_t_i_c_s _f_o_r _P_s_y_c_h_o_l_o_g_y _a_n_d _E_d_u_c_a_t_i_o_n (_5_t_h _E_d_i_t_i_o_n).

SEE ALSO
     unixstat(1), pair(1), anova(1)

AUTHOR
     Gary Perlman

BUGS
     _o_n_e_w_a_y duplicates some functionality of _a_n_o_v_a (_1) but is
     included to make this common type of data more easily
     analyzed.

KEYWORDS
     interential statistics, data analysis

Printed 6/30/85           March 9, 1985                         1

