Robenacoxib versus meloxicam for the management of pain and inflammation associated with soft tissue surgery in dogs: a randomized, non-inferiority clinical trial

Table 5 Efficacy endpoints: non-inferiority analysis, ANOVA or RMANOVA estimates for group quotients robenacoxib/meloxicam

Variable	Estimate (quotient)	Standard error	95% Confidence limits		P value ANOVA/RMANOVA	P value for normality (Shapiro-Wilk)
Variable	Estimate (quotient)	Standard error	Lower	Upper	P value ANOVA/RMANOVA	P value for normality (Shapiro-Wilk)
Primary endpoint
1/Modified GCPS score (without B)	1.12	0.08	0.97*	1.29	0.12	<.0001**
1/Unmodified GCPS score (with B)	1.13	0.09	0.96*	1.32	0.13	0.0005**
Secondary endpoints
1/Pain at rest	1.19	0.16	0.91*	1.55	0.20	<.0001**
1/Pain at palpation/manipulation	1.18	0.18	0.87*	1.58	0.28	0.0049**
1/Global efficacy score	1.08	0.07	0.94*	1.23	0.28	<.0001**
1/Global inflammation score	1.31	0.23	0.93*	1.85	0.12	0.058
1/Owner assessment: demeanor	1.00	0.02	0.95*	1.05	0.96	0.010**
1/Owner assessment: mobility	0.95	0.03	0.89*	1.02	0.17	0.010**

GCPS = Glasgow Composite Pain Scale.
All data were log transformed for the ANOVA/RMANOVA analyses.
Values are reciprocals of scores, thus values >1.00 indicate lower scores (higher efficacy) for robenacoxib versus meloxicam.
* Non-inferiority of robenacoxib to meloxicam shown (lower confidence limit >0.80).
** Data were not normally distributed after log transformation.

ISSN: 1746-6148