Analysis Using SAS 

Data Input:
For performing the analysis, input the data in the following format. {Here call the Tree Specie Number as Tree and Replication as Rep.It may, however, be noted that one can retain the same name or can code in any other fashion}.

 Prepare a SAS data file using

    DATA plantheight;  /*one can enter any other name for Data*/;
    Input Tree Rep Height;
    Cards;
    1           1           144.44
    2           1           113.50
    3           1             60.88
    4           1           163.44
    5           1           110.11
    6           1           260.05
    7           1           114.00
    8           1             91.94
    9           1           156.11
    10         1             80.20
    1           2           145.11
    2           2           118.61
    3           2             90.94
    4           2           158.55
    5           2           116.00
    6           2           102.27
    7           2           115.16
    8           2             58.16
    9           2           177.97
    10         2           108.05
    1           3           104.00
    2           3           118.61
    3           3             80.33
    4           3           158.88
    5           3           119.66
    6           3           256.22
    7           3           114.88
    8           3             76.83
    9           3           148.22
    10         3             45.18
    1           4           105.44
    2           4           123.00
    3           4             92.00
    4           4           153.11
    5           4           103.22
    6           4           217.80
    7           4           106.33
    8           4             79.50
    9           4           183.17
    10         4             79.55
     ;
* To test the equality of different species tree with respect to heights , one can perform the analysis of variance of the data using the following steps ;

PROC ANOVA;
Class Rep Tree;
Model    Height = Rep Tree;
Run;

/*One can obtain means of trees and all possible pair wise treatment comparisons using least significant differences and Duncan’s New Multiple range tests by using of the following statements:*/

 PROC ANOVA;
Class Rep Tree;
Model    Height = Rep Tree;
Means Tree/LSD;
Means  Tree/DUNCAN;
Run;

/*One may use a host of multiple comparison procedures under the options in MEANS statement viz.  Least Significant Difference (LSD), Duncan’s New multiple - range test (DUNCAN), Waller - Duncan (WALLER) test, Tukey’s Honest Significant Difference (TUKEY).  The LSD, DUNCAN and TUKEY options takes level of significance ALPHA = 5% unless ALPHA = options is specified.  Only ALPHA = 1%, 5% and 10% are allowed with the Duncan’s test.  95% Confidence intervals about means can be obtained using CLM option under MEANS statement 

One can not perform Contrast analysis by using PROC ANOVA, therefore, one has to use PROC GLM. This can be done using the following steps.
Note: Here we want to test

 Proc GLM;
Class Rep Tree;
Model Height = Rep Tree;
Contrast 'group 1 vs group 2' Tree 1 1 1 1 -1 -1 -1 -1 -1 1;
Contrast 'within group 1' Tree 1 -1 0 0 0 0 0 0 0 0,
                                          Tree 1 1 -2 0 0 0 0 0 0 0,
                                          Tree 1 1 1 -3 0 0 0 0 0 0,
                                          Tree 1 1 1 1 0 0 0 0 0 -4;
Contrast 'within group 2' Tree 0 0 0 0 1 -1 0 0 0 0,
                                          Tree  0 0 0 0 1 1 -2 0 0 0,
                                          Tree  0 0 0 0 1 1 1 -3 0 0,
                                          Tree  0 0 0 0 1 1 1 1  -4 0;
Contrast '1 vs 2 3 4 5 6 7 8 9 10' Tree 9 -1 -1 -1 -1 -1 -1 -1 -1 -1;
Contrast '1 2 3 4 vs 9' Tree 1 1 1 1 0 0 0 0 -4 0;
Contrast '1 2 3 4 vs 10' Tree 1 1 1 1 0 0 0 0 0 -4;
Contrast '5 6 7 8 vs 9' Tree 0 0 0 0 1 1 1 1 -4 0;
Contrast '5 6 7 8 vs 10' Tree 0 0 0 0 1 1 1 1 0 -4;
 run;