HbA1c is measured to identify average plasma glucose concentration over prolonged periods of time. The Least Squares (LS) mean was estimated from a mixed-effects model with repeated measures (MMRM) that included the independent variables:Baseline + Pooled Country + Treatment + Time + Treatment\*Time (Type III sum of squares).

HbA1c is a form of hemoglobin that is measured primarily to identify the average plasma glucose concentration over prolonged periods of time. Least-squares (LS) mean and standard error (SE) changes from baseline in HbA1c at 28 weeks were measured using mixed model regression and restricted maximum likelihood (REML) with treatment, pooled country, visit, and treatment-by -visit interaction as fixed effects, baseline as covariate, and participant as a random effect.

Least Squares (LS) means of change from baseline were calculated using analysis of covariance (ANCOVA) adjusted by treatment, country, baseline metformin, and baseline HbA1c.

Least squares (LS) means were calculated using analysis of covariance (ANCOVA) with country and treatment as fixed effects and baseline HbA1c as a covariate.

Least Squares (LS) means were calculated using analysis of covariance (ANCOVA) with country and treatment as fixed effects and baseline HbA1c as a covariate.

Mean 24-hour systolic blood pressure (SBP) was measured by using a 24-hour ambulatory blood pressure monitoring (ABPM) device attached to the participant's nondominant arm. Ambulatory blood pressure measurements were recorded every 20 minutes during the daytime (0700 to 2200 hours) and every 30 minutes during the nighttime hours (2200 to 0700), as preprogrammed into the device. For statistical analyses, diurnal hours were defined as 0800 to 2100 and nocturnal hours were defined as 0000 to 0600. Least Squares (LS) means were calculated using mixed model repeated measures (MMRM) adjusting for baseline, pooled sites, treatment, visit, treatment-by-visit interaction, and the stratified variable of diagnosis of hypertension.

Change in HbA1c from baseline following 12 weeks of therapy (that is, HbA1c at week 12 minus HbA1c at baseline). Changes in HbA1c were analyzed by a mixed model repeated measures (MMRM) model that included dose, pre-study therapy, body mass index (BMI) group at baseline, baseline value, visit, and dose\*visit, where the participant was treated as a random effect.

Least squares (LS) means were calculated using analysis of covariance (ANCOVA) and last observation carried forward (LOCF) imputation with country and treatment as fixed effects and baseline HbA1c as a covariate.

Pharmacokinetic parameters were assessed on Day 1 in Part A and Days 1 and 22 in Part B.

Pharmacokinetic parameters were assessed on Day 1 in Part A and Days 1 and 22 in Part B.

Pharmacokinetic parameters were assessed on Day 1 in Part A and Days 1 and 22 in Part B.

Pharmacokinetic parameters were assessed on Day 1 in Part A and Days 1 and 22 in Part B.

Area under the concentration versus time curve (AUC) from zero to infinity was determined from plasma concentrations of the S- and R- enantiomers of warfarin.

Area under the sitagliptin pharmacokinetic (PK) concentration versus time curve (AUC \[0-tau\]) during one dosing interval (24 hours) is summarized.

On Day 1 of each treatment period, all participants (healthy or with type 2 diabetes mellitus \[T2DM\]) received a single subcutaneous dose of either LY2189265 or placebo. On Day 3 of each treatment period, participants underwent a 6-hour insulin infusion, followed by an intravenous (IV) dextrose 50% bolus to stimulate insulin secretion. Three hours later, participants were administered a second dextrose bolus, followed by an infusion of 20% dextrose and, 15 minutes after the start of the 20% dextrose infusion, a 1-mg glucagon bolus was administered. Maximum plasma insulin concentration from 0 to 10 minutes (INSCmax\[0-10\]) following the first dextrose bolus (the first phase response) was corrected for baseline, where baseline was the mean of the insulin concentrations obtained between -30 and 0 minutes relative to the first dextrose bolus.

On Day 1 of each treatment period, all participants (healthy or with type 2 diabetes mellitus \[T2DM\]) received a single subcutaneous dose of either LY2189265 or placebo. On Day 3 of each treatment period, participants underwent a 6-hour insulin infusion, followed by an intravenous (IV) dextrose 50% bolus to stimulate insulin secretion. Three hours later, participants were administered a second dextrose bolus, followed by an infusion of 20% dextrose and, 15 minutes after the start of the 20% dextrose infusion, a 1-mg glucagon bolus was administered. Area under the plasma insulin concentration time curve from 0 to 10 minutes (INSAUC\[0-10\]) following the first dextrose bolus (the first phase response) was corrected for baseline, where baseline was the mean of the insulin concentrations obtained between -30 and 0 minutes relative to the first dextrose bolus.

On Day 1 of each treatment period, all participants (healthy or with type 2 diabetes mellitus \[T2DM\]) received a single subcutaneous dose of either LY2189265 or placebo. On Day 3 of each treatment period, participants underwent a 6-hour insulin infusion, followed by an intravenous (IV) dextrose 50% bolus to stimulate insulin secretion. Three hours later, participants were administered a second dextrose bolus, followed by an infusion of 20% dextrose and, 15 minutes after the start of the 20% dextrose infusion, a 1-mg glucagon bolus was administered. Maximum plasma insulin concentration from 10 to 180 minutes (INSCmax\[10-180\]) following the first dextrose bolus (the second phase response) was corrected for baseline, where baseline was the mean of the insulin concentrations obtained between -30 and 0 minutes relative to the first dextrose bolus.

On Day 1 of each treatment period, all participants (healthy or with type 2 diabetes mellitus \[T2DM\]) received a single subcutaneous dose of either LY2189265 or placebo. On Day 3 of each treatment period, participants underwent a 6-hour insulin infusion, followed by an intravenous (IV) dextrose 50% bolus to stimulate insulin secretion. Three hours later, participants were administered a second dextrose bolus, followed by an infusion of 20% dextrose and, 15 minutes after the start of the 20% dextrose infusion, a 1-mg glucagon bolus was administered. Area under the plasma insulin concentration time curve from 10 to 180 minutes (INSAUC\[10-180\]) following the first dextrose bolus (the second phase response) was corrected for baseline, where baseline was the mean of the insulin concentrations obtained between -30 and 0 minutes relative to the first dextrose bolus.

This measure was calculated using non-compartmental analysis techniques.

This measure was calculated using non-compartmental analysis techniques.

This measure was calculated using non-compartmental analysis techniques.

This measure was calculated using non-compartmental analysis techniques.

The half life associated with the terminal rate constant is summarized. This measure was calculated using non-compartmental analysis techniques.

The apparent total body clearance of drug calculated after extra vascular administration is summarized. This measure was calculated using non-compartmental analysis techniques.

The apparent volume of distribution during the terminal phase after extra vascular administration is summarized. This measure was calculated using non-compartmental analysis techniques.

After at least 8 hours fasting, participants received a radiolabeled breakfast containing technetium-99m-tin colloid (99mTc-tin colloid). After which serial anterior and posterior scintigraphy images were taken. Data presented are the time required for 50% of radioactivity to be emptied from stomach. The results presented are Geometric Least Squares (LS) Mean. LS Mean values were controlled for weeks.