non-est lsmeans table

[meghbali14]

Dear Friends,

When I run the PROC MIXED procedure, in the SAS 9.4 result, I found the “Non-est” for one group (in my set of data, group 2). Please let me know how to solve this problem? Thank you very much in advance.

data chew_act_cov;

input number  Name$  day  group  RUMINATETIME  EATTIME  TOTALCHEWINGTIME  RUMINATECHEWSPERMINUTE;

cards;

2 Kiana 1     1     512.33     234.75      747.08      55.35

2 Kiana 2     1     557.6       238.55      796.15      54.74

2 Kiana 3     1     606.17     272.25      878.42      59.57

2 Kiana 4     1     573.43    185.9        759.33       55.16

4 Babsi 1     1     428.25     307.68     735.93       61.80

4 Babsi 2     1     567.3       397.55      964.85      70.08

4 Babsi 3     1     567.3       397.55      964.85      70.08

4 Babsi 4     1     592.58     414.98      1007.57    70.57

4 Babsi 5     1     538.13      409.6        947.73     60.41

4 Babsi 6     1     498.42      309.98      808.4       62.34

5 Utah  1     1     493.37      429.57       922.93     51.67

5 Utah  2     1     495.32      438.32       933.63     60.63

6 Uruguay     1     1     479.65      146.88       626.53    43.95

6 Uruguay     2     1     648.48     180.57        829.05      60.76

6 Uruguay     3     1     667.55      222.9          890.45      57.94

6 Uruguay     4     1     680.93     171.82        852.75      54.65

6 Uruguay     5     1     683.13     162.23        845.37      60.12

7 Polli 1     1     421.93       239.68         661.62        52.46

7 Polli 2     1     306.05       214          520.05      41.65

7 Polli 3     1     214.8        279.08      493.88      36.05

17 Prima 1     1     448.92   197.57      646.48     57.23

17 Prima 2     1     550.47    209.9       760.37     57.72

17 Prima 3     1     518.18    210.45      728.63    59.96

17 Prima 4     1     496.22   171.1          667.32    55.42

17 Prima 5     1     520.12    171.88       692        56.69

25 Zoey  1     1     88.1         180.3       268.4      19.34

25 Zoey  2     1     72.83       215.55     288.39     17.11

25 Zoey  3     1     78.57      192.08      270.65      19.26

26 Anna  1     1     592.82    328.95      921.77      74.45

26 Anna  2     1     530.55      345.15      875.7      68.13

10 Bella 1     2     539.95      455.317    995.27       55.27

10 Bella 2     2     565.1        435.9        1001       64.05

10 Bella 3     2     539.63      444.75      984.38     57.025

10 Bella 4     2     529.9        416.42      946.32      60.54

10 Bella 5     2     577.42       407.08      984.5       63.42

12 Mala  1     2     456.28      358.05      814.33      57.85 

12 Mala  2     2     606.7        393.23      999.93      74.71 

12 Mala  3     2     580.6       444.52      1025.12     75.04

12 Mala  4     2     538.93      372.2        911.13      65.26

14 Wendy 1     2     420.87    276.42     697.28      46.49

14 Wendy 2     2     586.95      349.73   936.68     68.89

14 Wendy 3     2     573.27     392.8      966.07     68.46

14 Wendy 4     2     534.65      363.15   897.8        62.34

18 Mona  1     2     430.42       300.08   730.5       56.42

18 Mona  2     2     577.92      402.03    979.95      70.58

18    Mona  3     2     633.47     332.7       966.17      63.35

18 Mona  4     2     635.35     378.65     1014        73.07

18 Mona  5     2     578.28      353.4       931.68    70.91

21 Peggy 1     2     453.73       347.95    801.68   42.48

21 Peggy 2     2     572.6       458.18     1030.78   66.99

21 Peggy 3     2     600.8      401.62      1002.42   64.48

21 Peggy 4     2     560.22     476.95      1037.16    61.47

21 Peggy 5     2     617.82     417.9       1035.72      58.71

22 Panama      1     2     355.95      410.68      766.63     46.36

22 Panama      2     2     508.4        414.63      923.03    1583.50

22 Panama      3     2     544.17      473.7 1017.87         59.46

22 Panama      4     2     578.25      391.25      969.5     74.88

22 Panama      5     2     580.02      418.43     998.45      68.03

24 Bianca      1     2     487.53        368.15      855.68     48.79

24 Bianca      2     2     514.52      480.73       995.25      51.77

24 Bianca      3     2     516.03      445.52       961.55      56.87

24 Bianca      4     2     514.88      387.35      902.23       56.00

;

proc mixed;

class Name day group;

model RUMINATETIME=group day group*day;

repeated day/type=ar(1) sub=Name(group);

lsmeans group;

run;

proc mixed;

class Name day group;

model       EATTIME=group day group*day;

repeated day/type=ar(1) sub=Name(group);

lsmeans group;

run;

proc mixed;

class Name day group;

model       TOTALCHEWINGTIME=group day group*day;

repeated day/type=ar(1) sub=Name(group);

lsmeans group;

run;

proc mixed;

class Name day group;

model RUMINATECHEWSPERMINUTE=group day group*day;

repeated day/type=ar(1) sub=Name(group);

lsmeans group;

run;

[PaigeMiller]

There is an empty cell, with 0 data points, where day is 6 and group is 2. Interactions cannot be estimated when there are cells with 0 data points; and in addition some of the LSMEANS are non-estimable.

Possible paths forward is to remove day 6 from the analysis, or remove the interaction from the model.

[SteveDenham · Accepted solution]

I am expand a bit on @PaigeMiller 's response. If you fit a model with main effects and an interaction, and you have a missing cell, the main effects will be non-estimable.  However, if you fit a model that contains ONLY the interaction (a one-way model often called a "means model"), and use an LSMESTIMATE statement you can calculate main effect means and standard errors. Main effect F tests can also be calculated within LSMESTIMATE statements as well, using the JOINT and/or FTEST options.

SteveDenham 

[meghbali14]

Dear Paige Miller,

Thanks for your response. The first path didn't worked, after removing the day 6 for one of cow, but I also had non-estimated error.

Fortunately, the second path you suggested was worked. I removed the interaction in the model and then get the results. Thank you very much.

All the best,

Mansour

[Ksharp]

Calling @StatDave @SteveDenham @lvm