PFS was defined as the time from the date of randomization in study until the date of first documented objective tumor progression (according to RECIST v1.1 as determined by IRR) or death (due to any cause), whichever occurred first. PFS (in months) was calculated as (first event date - randomization date +1)/30.44. Objective progression was defined as a 20 percent (%) increase in the sum of the diameters of target measurable lesions taking as reference the smallest sum on study (this includes the baseline sum if that is the smallest on study), with a minimum absolute increase of 5 millimeter (mm) or clear progression of pre-existing non-target lesions, or the appearance of any new clear lesions.

The FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization.

OS (in months) was defined as the duration from start of study treatment to date of death due to any cause. OS = (date of death minus the date of randomization of study medication plus 1) divided by 30.4. For participants who were alive, overall survival was censored on last date the participants were known to be alive.

The FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization.

Overall survival probability at Month 12 and 18 was defined as the probability of overall survival at 12 and 18 months respectively, where the OS was defined as the duration from date of randomization to date of death due to any cause. The survival probability was estimated using the Kaplan-Meier method.

The FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization.

ORR was defined as percentage of participants with complete response (CR) or partial response (PR) according to RECIST v1.1 determined by IRR. CR was defined as complete disappearance of all target lesions and non-target disease. All nodes, both target and non-target, must decrease to normal (short axis <10 mm). No new lesions and disappearance of all non-target lesions. PR was defined as greater than or equal to (>=) 30% decrease taking as reference the baseline sum of lesion dimensions. The short axis was used in the sum for target nodes, while the longest diameter was used in the sum for all other target lesions. No clear progression of non-target disease. No new lesions.

The FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization.

DR: time from first documentation of objective tumor response (CR or PR) to first documentation of PD or death due to any cause, whichever occurred first as per RECIST v1.1 determined by IRR. CR: complete disappearance of all target and non-target disease. All nodes, both target and non-target, must decrease to normal (short axis <10 mm). No new lesions, disappearance of all non-target lesions. PR: >=30% decrease taking as reference the baseline sum of lesion dimensions. Short axis was used in sum for target nodes, while longest diameter was used in sum for all or target lesions. No clear progression of non-target disease. No new lesions. c) PD: 20 % increase in the sum of the diameters of target measurable lesions taking as reference the smallest sum on study (this includes the baseline sum if that is the smallest on study), with a minimum absolute increase of 5 mm or clear progression of pre-existing non-target lesions, or the appearance of any new clear lesions.

The FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization. Here Overall number of participants analyzed (N) signifies participants with objective tumor response and were evaluable for this outcome measure.

TTR was defined as the time from randomization to first documentation of objective tumor response (CR or PR) according to RECIST v1.1 determined by IRR. CR: complete disappearance of all target lesions and non-target disease. All nodes, both target and non-target, must decrease to normal (short axis <10 mm). No new lesions and disappearance of all non-target lesions. PR: >=30% decrease taking as reference the baseline sum of lesion dimensions. Short axis was used in sum for target nodes, while longest diameter was used in sum for all or target lesions. No clear progression of non-target disease. No new lesions.

The FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization. Here N signifies participants with objective tumor response and were evaluable for this outcome measure.

Disease control rate at week 12 is defined as the percent of participants with CR, PR, or stable disease (SD) at week 12 according to RECIST v1.1 determined by IRR. The best response of SD would be assigned if SD criteria was met at least once after randomization at a minimum interval of 6 weeks. CR: complete disappearance of all target lesions and non-target disease, with exception of nodal disease. All nodes, both target and non-target, must decrease to normal (short axis <10 mm). No new lesions and disappearance of all non-target lesions. PR: >=30% decrease taking as reference the baseline sum of lesion dimensions. SD: neither sufficient shrinkage to qualify for PR nor sufficient increase to qualify for PD, taking as reference the smallest sum diameters. Short axis was used in sum for target nodes, while longest diameter was used in sum for all or target lesions. No clear progression of non-target disease. No new lesions.

The FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization.

TTP was defined as the time from the date of randomization to the date of the first documentation of objective tumor progression according to RECIST v1.1 determined by IRR. Objective tumor progression was defined as 20% increase in the sum of the diameters of target measurable lesions taking as reference the smallest sum on study (this includes the baseline sum if that is the smallest on study), with a minimum absolute increase of 5 mm or clear progression of pre-existing non-target lesions, or the appearance of any new clear lesions. If tumor progression data included more than 1 date, the first date was used. TTP (in months) was calculated as (first event date - randomization date +1)/30.44.

The FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization.

IC-TTP was defined similarly to TTP, but only considering intracranial disease (excluding extracranial disease) and the progression was determined based on either new brain metastases or progression of existing brain metastases. TTP was defined as the time from the date of randomization to the date of the first documentation of objective tumor progression according to RECIST v1.1 determined by IRR. Objective tumor progression was defined as 20% increase in the sum of the diameters of target measurable lesions taking as reference the smallest sum on study (this includes the baseline sum if that is the smallest on study), with a minimum absolute increase of 5 mm or clear progression of pre-existing non-target lesions, or the appearance of any new clear lesions.

The FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization.

EC-TTP was defined similarly to TTP, but only considering extracranial disease (excluding intracranial disease) and the progression was determined based on either new extracranial lesions or progression of existing extracranial lesions. TTP was defined as the time from the date of randomization to the date of the first documentation of objective tumor progression according to RECIST v1.1 determined by IRR. Objective tumor progression was defined as 20% increase in the sum of the diameters of target measurable lesions taking as reference the smallest sum on study (this includes the baseline sum if that is the smallest on study), with a minimum absolute increase of 5 mm or clear progression of pre-existing non-target lesions, or the appearance of any new clear lesions.

FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization.

An AE was any untoward medical occurrence in a participant who received study drug without regard to possibility of causal relationship. SAE was an AE resulting in any of the following outcomes or deemed significant for any other reason: death; initial or prolonged inpatient hospitalization; life-threatening experience (immediate risk of dying); persistent or significant disability/incapacity; congenital anomaly. Treatment-emergent are events between first dose of study drug and up to 28 days after last dose of study drug that were absent before treatment or that worsened relative to pretreatment state. AEs included both SAEs and non-SAEs.

The safety analysis population included all randomized participants who received at least 1 dose of study treatment, with treatment assignments designated according to actual study treatment received during the first cycle.

Treatment-related AE was any untoward medical occurrence attributed to study drug in a participant who received study drug. SAE was an AE resulting in any of the following outcomes or deemed significant for any other reason: death; initial or prolonged inpatient hospitalization; life-threatening experience (immediate risk of dying); persistent or significant disability/incapacity; congenital anomaly. Treatment-emergent are events between first dose of study drug and up to 28 days after last dose of study drug that were absent before treatment or that worsened relative to pre-treatment state. Relatedness to study drug was assessed by the investigator.

The safety analysis population included all randomized subjects who received at least 1 dose of study treatment, with treatment assignments designated according to actual study treatment received during the first cycle.

An AE was any untoward medical occurrence in a participant who received study drug without regard to possibility of causal relationship. AE was assessed according to maximum severity grading based on National Cancer Institute (NCI) Common Terminology Criteria for Adverse Events (CTCAE) Version 4.0. Grade 1 =mild; Grade 2 =moderate; within normal limits, Grade 3 =severe or medically significant but not immediately life-threatening; Grade 4 =life-threatening or disabling; urgent intervention indicated; Grade 5 =death.

The safety analysis population included all randomized subjects who received at least 1 dose of study treatment, with treatment assignments designated according to actual study treatment received during the first cycle.

Ctrough is the concentration prior to study drug administration on Day 1 of Cycle 2 onwards. PF-06260182 is the metabolite of Crizotinib.

Pharmacokinetic concentration population included all participants in the safety analysis population who had at least 1 plasma concentration of crizotinib or its metabolite.N=participants evaluable for this measure.Number of participants analyzed(n)=participants evaluable at specified time points.This analysis was performed in crizotinib arm only.

The Response Genetics, Inc. Echinoderm Microtubule Associated Protein Like 4 (EML4) ALK reverse transcriptase polymerase chain reaction (RT PCR) gene fusion test was used for the analysis of tissue samples for the ALK gene fusion variants (either no rearrangement, or 1 of 9 results reflecting 8 specific rearrangements [V1, V2, V3a, V3b,V3a/b, V4, V5a, V6, V7]). Percentage of participants who tested positive for ALK gene fusion variants were reported in this outcome measure.

The ALK variant evaluable population included participants from the FA population who had a result from ALK gene fusion variant testing of either no rearrangement, or 1 of 9 results reflecting 8 specific rearrangements (V1, V2, V3a, V3b, V3a/b, V4, V5a, V6, and V7).

The Response Genetics, Inc. EML4 ALK reverse transcriptase polymerase chain reaction (RT PCR) gene fusion test was used for the analysis of tissue samples for the ALK gene fusion variants (either no rearrangement, or 1 of 9 results reflecting 8 specific rearrangements [V1, V2, V3a, V3b,V3a/b, V4, V5a, V6, V7]). Percentage of participants with confirmed CR or PR according to RECIST v1.1 determined by IRR, by type of ALK gene fusion variant were reported in this outcome measure. CR: complete disappearance of all target lesions and non-target disease. All nodes, both target and non-target, must decrease to normal (short axis <10 mm). No new lesions and disappearance of all non-target lesions. PR: >=30% decrease decrease taking as reference the baseline sum of lesion dimensions. Short axis was used in sum for target nodes, while longest diameter was used in sum for all or target lesions. No clear progression of non-target disease. No new lesions.

The ALK variant evaluable population included participants from the FA population who had a result from ALK gene fusion variant testing of either no rearrangement, or 1 of 9 results reflecting 8 specific rearrangements (V1, V2, V3a, V3b, V3a/b, V4, V5a, V6, and V7). Here, n signifies participants who were evaluable at specified time points.

TTD in pain in chest, dyspnea, or cough from the Quality of Life Questionnaire Core 30 (QLQ-LC13) was a composite endpoint defined as the time from randomization to the earliest time the participant's scale scores showed a 10 point or greater increase after baseline in any of the 3 symptoms. For those who had not shown deterioration, the data was censored at the last date when the participants completed an assessment (QLQ-LC13) for pain, dyspnea, or cough or at last visit date prior to crossover for participants randomized to chemotherapy who subsequently crossed over to crizotinib. A 10-point or higher change in the score was perceived by participants as clinically significant. The transformed score of pain, dyspnea, and cough symptom scales of EORTC QLQ-LC13 (European Organization for the Research and Treatment of Cancer) range from 0 to 100, where higher scores indicate greater symptom severity.

The patient reported outcome (PRO) evaluable population included all participants from the FA population who completed a baseline and at least 1 postbaseline PRO assessment prior to crossover to crizotinib or end of randomized study treatment.

EORTC QLQ-C30: included 5 functional scales (physical, role, cognitive, emotional and social), global health status/global quality of life scale, 3 symptom scales (fatigue, pain, nausea and vomiting), 6 single items that assess the additional symptoms (dyspnea, appetite loss, sleep disturbance, constipation, diarrhea) and financial difficulties. All scales and single-item measures range from 0 to 100. A high score for a functional scale represents a high/healthy level of functioning, for the global health status/QoL represents a high QoL (better participant state), and for a symptom scale/item represents a high level of symptoms/problems (worse participant state).

The PRO evaluable population included all participants from the FA population who completed a baseline and at least 1 postbaseline PRO assessment prior to crossover to crizotinib or end of randomized study treatment.

EORTC QLQ-C30: included 5 functional scales (physical, role, cognitive, emotional and social), global health status/global quality of life scale, 3 symptom scales (fatigue, pain, nausea and vomiting), 6 single items that assess the additional symptoms (dyspnea, appetite loss, sleep disturbance, constipation, diarrhea) and financial difficulties. All scales and single-item measures range from 0 to 100. A high score for a functional scale represents a high/healthy level of functioning, for the global health status/QoL represents a high QoL (better participant state), and for a symptom scale/item represents a high level of symptoms/problems (worse participant state).

The PRO evaluable population included all participants from the FA population who completed a baseline and at least 1 postbaseline PRO assessment prior to crossover to crizotinib or end of randomized study treatment.

QLQ-LC13 consists of 1 multi-item scale and 9 single items that assess the specific symptoms (dyspnea, cough, hemoptysis, and site-specific pain), side effects (sore mouth, dysphagia, neuropathy, and alopecia), and pain medication use of patients with lung cancer receiving chemotherapy. All multi-item scales and single-item measures range from 0 to 100, where higher score indicates greater degree of symptom severity.

The PRO evaluable population included all participants from the FA population who completed a baseline and at least 1 postbaseline PRO assessment prior to crossover to crizotinib or end of randomized study treatment.

EQ-5D: participant rated questionnaire to assess health-related quality of life in terms of a single index value. VAS component: participants rated their current health state on a scale from 0 (worst imaginable health state) to 100 (best imaginable health state); higher scores indicate a better health.

The patient reported outcome (PRO) evaluable population included all participants from the FA population who completed a baseline and at least 1 postbaseline PRO assessment prior to crossover to crizotinib or end of randomized study treatment. Here, "N" signifies participants who were evaluable for this outcome measure.

Healthcare resource utilization was to be evaluated using the assessment of the following: date and duration of index admission, duration of hospitalization and date of discharge.

FA population included all participants who were randomized with study treatment assignment designated according to the initial randomization.

Anemia(grade[g]1:Less than[<] Lower limit of normal[LLN] to 10gram per[/] deciliter[g/dL],g2:<10 to 8g/dL,g3:<8g/dL,g4:lifethreatening);platelet (g1:<LLN to 75*10^3/millimeter[mm]^3,g2:<75*10^3/mm^3 to 50*10^3/mm^3,g3:<50*10^3/mm^3 to 25*10^3/mm^3,g4:<25*10^3/mm^3);lymphopenia(g1:<LLN to 8*10^2/mm^3,g2:<8*10^2 to 5*10^2/mm^3,g3:<5*10^2 to 2*10^2/mm^3,g4:<2*10^2/mm^3);neutrophil (Absolute)(g1:<LLN to 15*10^2/mm^3,g2:<15*10^2 to 10*10^2/mm^3,g3:<10*10^2 to 5*10^2/mm^3,g4:<5*10^2/mm^3);white blood cell count(g1:<LLN to 3*10^3/mm^3,g2:<3*10^3 to 2*10^3/mm^3,g3:<2*10^3 to 1*10^3/mm^3,g4:<1*10^3/mm^3);hemoglobin(g1:increase in hemoglobin level>0 to 2 g/dL above ULN or above baseline if baseline is above ULN,g2:increase in hemoglobin level>2 to 4g/dL above ULN or above baseline if baseline is above ULN,g3:increase in hemoglobin level>4 g/dL above ULN or above baseline if baseline is above ULN). Only categories with atleast 1 participant with abnormality are reported in this outcome measure.

Safety analysis population included all randomized subjects who received at least 1 dose of study treatment, with treatment assignments designated according to actual study treatment received during the first cycle. Here, N=participants who were evaluable for this outcome measure.

ALT/AST (Grade[g]1:>ULN-3*ULN,g2:>3-5*ULN,g3:>5-20*ULN,g4:>20*ULN);Alkaline Phosphatase (g1:>ULN-2.5*ULN,g2:>2.5-5*ULN,g3:>5-20*ULN,g4:>20*ULN);Creatinine (g1:>ULN-1.5*ULN,g2:>1.5-3*ULN,g3:>3-6*ULN,g4:>6*ULN);hyperglycemia (g1:>ULN-160,g2:>160-250,g3:>250-500,g4:>500mg/dL);bilirubin(total) (g1:>ULN-1.5*ULN,g2:>1.5-3*ULN,g3:>3-10*ULN,g4:>10*ULN);hypoglycaemia (g1:<LLN-55,g2:<55-40,g3:<40-30,g4:<30mg/dL);hyperkalemia (g1:>ULN-5.5,g2:>5.5-6,g3:>6-7,g4:>7mmol/L);hypokalemia (g1:<LLN-3,g2:<LLN-3,g3:<3-2.5,g4:<2.5mmol/L);hypermagnesemia (g1:>ULN-3,g3:>3-8,g4:>8mg/dL);hypocalcemia (g1:<LLN-8,g2:<8-7,g3:<7-6,g4:<6mg/dL); hypercalcemia (g1:>ULN-11.5,g2:>11.5-12.5,g3:>12.5-13.5,g4:>13.5mg/dL);hypomagnesemia (g1:<LLN-1.2,g2:<1.2-0.9,g3:<0.9-0.7,g4:<0.7mg/dL);hyponatremia (g1:<LLN-130,g3:<130-120,g4:<120mmol/L);hypoalbuminemia (g1:<LLN-3,g2:<3-2,g3:<2,g4:lifethreatening);hypophosphatemia (g1:<LLN-2.5,g2:<2.5-2,g3:<2-1,g4:<1mg/dL). Participant>=1 abnormality given.

Safety analysis population included all randomized subjects who received at least 1 dose of study treatment, with treatment assignments designated according to actual study treatment received during the first cycle. Here, N=participants who were evaluable for this outcome measure. Here, "n"=participants who were evaluable at specified time points.