Professional Documents
Culture Documents
1. Building Block of Science & Research Process 2. Theoretical Framework, Hyphothesis & Analysis 3. Research design 4. Writing 5. Regression Analysis 6. Factor Analysis, Cluster Analysis, MDS + Delivery Discussion Material 7. Discussion & Critics 8. Final Test Proposal Research Paper
Metodologi Penelitian
Oleh : DR.RORIM PANDAY,MT
Desember 2006
Analysis Of Data
Research Design
PROBLEM DEFINITION
Research problem delineated
THEORETICAL FRAMEWORK
Variables clearly identified and labeled
GENERATION OF HYPOTHESES
TAHAPAN PENELITIAN
Dalam melakukan riset ada beberapa komponen yang harus diperhatikan yaitu : 1. Menentukan problem secara tepat dari suatu fenomena yang akan diteliti. 2. Menentukan tujuan dari riset/ penelitian tersebut secara tepat dan spesifik
diolah dengan menggunakan suatu metode statistik multivariat tertentu. Analisa yang dilakukan antara lain : - Analisa mengenai validasi data - Analisa mengenai validasi model - Kesimpulan dari model yang diperoleh.
7. Membuat suatu kesimpulan berdasarkan hasil yang diperoleh dengan cara yang sistematis. 8. Memberikan saran yang tepat
PROBLEM/ PERMASALAHAN
KESENJANGAN ANTARA APA YANG SEHARUSNYA
DENGAN APA YANG ADA DALAM KENYATAAN KESENJANGAN ANTARA APA YANG DIPERLUKAN DENGAN APA YANG TERSEDIA
TUJUAN PENELITIAN
Memecahkan masalah / problem yang telah dirumuskan , mencari solusi
Membuktikan hipotesa
KERANGKA PEMIKIRAN
Organizational Commitment
Dependent Variable
Gender
Independent variables
KERANGKA PEMIKIRAN
Workforce diversity
Independent Variable
Organizational Effectiveness
Dependent Variable
Managerial Expertise
Moderating Variable
Independent Variable
Intervening Variable
Dependent Variable
Independent Variable
Moderating Variable
Dependent Variable
Diagram of the relationships among independent, intervening, moderating and dependent variable
Workforce diversity
Independent Variable
Creative Synergy
Intervening Variable
Organizational Effectiveness
Dependent Variable
Managerial Expertise
Moderating Variable
HYPOTHESIS /Hipotesis
Ho : Penjualan tidak dipengaruhi oleh harga barang, harga barang pesaing, kualitas, cita rasa, pendapatan masyarakat, dan promosi
Ha : Penjualan dipengaruhi oleh harga barang, harga barang pesaing, kualitas, cita rasa, pendapatan masyarakat, dan promosi
CAUSAL HYPOTHESIS
RESEARCH DESIGN
TYPE OF RESEARCH CAUSAL RESEARCH
DESCRIPTIVE RESEARCH EXPLORATION RESEARCH
FIELD RESEARCH
LABORATORY STUDY / EXPERIMENTAL STUDY
Metric
X1 X2 X3 X4 .... Xn
0.221 0.115 0.785 0.211 0.150 0.007 0.012 0.880 ......... ......... 0.450 0.072
Metric
CLUSTER ANALYSIS A B C D E F
dendogram
MUlTI-DIMENSIONAL SCALLING
non metric
A B E F D C
PERCEPTUAL-MAP
HIPOTESIS Ho DAN Ha
TERIMA Ho
TOLAK Ho
T- table
T- table
T- table
T- table
4P
SAMPLING
PROBABILITY SAMPLING 1. Sampling acak sederhana (Simple random sampling)
SKALA PENGUKUR
1. Nominal Scale : - indicate no order - no distance relationship - no arithmatic origin - Just count 2. Ordinal Scale : -a>b>c - indicate order - no distance relationship - no arithmatic origin
Your gender: --- Male --- Female
Your Department: --- Production --- Sales --- Accounting --- Finance
Rank ----- Jakarta ---- Bandung ---- Bogor ---- Medan ---- Surabaya
SKALA PENGUKUR
3. Interval Scale : - indicate order - distance - have arithmatic origin 4. Ratio Scale : - indicate order - distance - have absolute zero origin
1. 2. 3. 4. 5. Strongly disagree Disagree Neutral Agree Strongly Agree
How many member in this organization? How many dollar cost of production?
Variables / Variabel
CONTOH
Sample
67 mine workers from the XYZ Mine co, illnois. Mean age = 35; all males
Results / Hasil
Working condition influenced absenteeism the most especially toxic dust and explosions. None of the other variables was significantly related to absenteeism.
Conclusions / Kesimpulan
Chemical that would absorb the toxic dust and mechanism for explosion danger warning should substantially reduce absenteeism
SEGMENTASI ---> CLUSTER, DISKRIMINAN, FACTOR ANALISIS POSITIONING ---> MDS, DISKRIMINAN, CLUSTER DIFFERENSIASI ---> DISKRIMINAN, MANOVA SWOT ---> MUTIPLE REGRESI, FACTOR ANALYSIS PREDIKSI --> MULTIPLE REGRESI, DISKRIMINAN, MDS BAURAN PEMASARAN --> MULTIPLE REGRESI, FACTOR ANALISIS,ANOVA/MANOVA REKRUITMEN ---> DISKRIMINAN PRODUKTIVITAS ---> REGRESI
Bab-1
Bab-2
Bab-3
Bab-4
Bab-5
Landasan Teori
1. Journal Internet Thesis/ Disertasi
CONTOH :
1. PERFORMANCE MEASUREMENT MODEL FOR SENIOR SECONDARY SCHOOL IN INDONESIA (20022003) 2. Factor Analysis Of Service Quality Argo Gede Train As a Tool For Improving the Service (2000) 3. Analisis Variabel Time Robber Di Lingkungan Manajemen Proyek Ditinjau dari Manajer Proyek (2001) 4. Profil 20 Sekolah Menengah Atas di Jakarta dan Bogor (2004)
5. ANALYSIS THE IMPACT OF MONETARY VARIABLES TO THE STOCK PRICES INDEX INDUSTRIES AT JAKARTA STOCK EXCHANGE (CASE STUDY JULY 1997 TO OCTOBER 1998) 6. Evaluasi Keterampilan Dan Kompetensi Tenaga Ahli Geodesi Antara Hasil Pendidikan dan Kebutuhan Tempat Kerja.(Laporan Penelitian thn 2000) 7. Tinjauan Strategi Di dalam Industri Survei dan pemetaan (1995)
KATCO menetapkan variabel tingkat penggunaan produksi (Usage level) sebagai X9. Variabel X1 sampai dengan X7 disebut sebagai variabel independent, sedangan X9 ditentukan sebagai variabel dependen.
Untuk data tingkat penggunaan produksi, responden menentukan dalam bentuk persentase 40% misalnya atau 55% dan sebagainya. Hasil dari 100 responden setelah diukur, ditabulasi
Cor relations price f lexibility (x3) .559 .509 -.487 1.000 -.116 .067 -.034 -.448 .000 .000 .000 . .125 .255 .367 .000 100 100 100 100 100 100 100 100
Pearson Correlation
Sig. (1-tailed)
us age level (x9) us age lev el (x 9) 1.000 delivery s peed .676 (x1) price level (x2) .082 price f lexibility .559 (x3) manuf ac turer's .224 image (x4) service (x5) .701 salesf orc e .256 image (x6) produc t quality -.192 (x7) us age lev el (x 9) . delivery s peed .000 (x1) price level (x2) .209 price f lexibility .000 (x3) manuf ac turer's .012 image (x4) service (x5) .000 salesf orc e .005 image (x6) produc t quality .028 (x7) us age lev el (x 9) 100 delivery s peed 100 (x1) price level (x2) 100 price f lexibility 100 (x3) manuf ac turer's 100 image (x4) service (x5) 100 salesf orc e 100 image (x6) produc t quality 100 (x7)
delivery speed (x1) .676 1.000 -.349 .509 .050 .612 .077 -.483 .000 . .000 .000 .309 .000 .223 .000 100 100 100 100 100 100 100 100
price level (x2) .082 -.349 1.000 -.487 .272 .513 .186 .470 .209 .000 . .000 .003 .000 .032 .000 100 100 100 100 100 100 100 100
manuf ac turer's image (x4) .224 .050 .272 -.116 1.000 .299 .788 .200 .012 .309 .003 .125 . .001 .000 .023 100 100 100 100 100 100 100 100
service (x5) .701 .612 .513 .067 .299 1.000 .241 -.055 .000 .000 .000 .255 .001 . .008 .293 100 100 100 100 100 100 100 100
salesf orc e produc t image (x6) quality (x7) .256 -.192 .077 .186 -.034 .788 .241 1.000 .177 .005 .223 .032 .367 .000 .008 . .039 100 100 100 100 100 100 100 100 -.483 .470 -.448 .200 -.055 .177 1.000 .028 .000 .000 .000 .023 .293 .039 . 100 100 100 100 100 100 100 100
Mean us age level (x9) price f lexibility (x3) service (x5) salesf orc e image (x 6) 46.100 7.894 2.916 2.665
Cor relations price f lexibility (x3) .559 1.000 .067 -.034 .000 . .255 .367 100 100 100 100
us age level (x9) Pearson Correlation us age level (x9) price f lexibility (x3) service (x5) salesf orc e image (x6) us age level (x9) price f lexibility (x3) service (x5) salesf orc e image (x6) us age level (x9) price f lexibility (x3) service (x5) salesf orc e image (x6) 1.000 .559 .701 .256 . .000 .000 .005 100 100 100 100
service (x5) .701 .067 1.000 .241 .000 .255 . .008 100 100 100 100
salesf orc e image (x6) .256 -.034 .241 1.000 .005 .367 .008 . 100 100 100 100
Sig. (1-tailed)
V ariables Entere d/Re m ovebd V ariables V ariables Entered Remov ed salesf orc e image (x6), price . f lexibility (x3), service a (x5)
Model 1
Method
Enter
Model 1
Change Statistics R Square Change .768 F Change 106.115 df1 3 df2 96 Sig. F Change .000 Durbin-Watson 1.910
a. Predictors: (Constant), salesforce image (x6), price flexibility (x3), service (x5) b. Dependent Variable: usage level (x9)
ANOVAb Sum of Squares 6145.700 1853.300 7999.000 Mean Square 2048.567 19.305
Model 1
df 3 96 99
F 106.115
Sig. .000 a
a. Predictors: (Constant), sales f orce image (x 6), pric e f lex ibility (x3), serv ic e (x5) b. Dependent Variable: usage level (x 9)
a Coefficients
Unstandardiz ed Coefficients Model 1 B Std. Error -6.520 3.247 3.376 7.621 1.406 .320 .607 .591
Standardi zed Coefficien ts Beta t -2.008 10.562 12.547 2.378 Sig. .047 .000 .000 .019
(Constant) price fle xibility (x3) service (x5) sale sforce image (x6)
95% Confidence In terval for B Correlatio ns Low er Upper Bound Bound Zero-order Partial -12.965 -.075 2.742 6.416 .232 4.010 8.827 2.579 .559 .701 .256 .733 .788 .236
Model 1
salesf orc e image (x 6) Correlations salesf orc e 1.000 image (x 6) price f lexibility .052 (x3) service (x5) -.244 salesf orc e .349 image (x 6) price f lexibility 9.824E-03 (x3) service (x5) -8.752E-02
Covariances
Model 1
Dimension 1 2 3 4
Varianc e Proportions price f lexibility service (x3) (x5) .00 .00 .11 .02 .14 .91 .75 .07
Minimum Predicted Value Residual Std. Predicted Value Std. Residual 23.373 -12.552 -2.885 -2.857
Frequency
4 2 0
Normal P-P Plot of Regression Standardized Re Dependent Variable: usage level (x9)
1.00
.75
.50
.25
10 10
0 0
-10
-10
-20 -3 -2 -1 0 1 2 3
-20 -3 -2 -1 0 1 2
-10
Y= a+bX
SA LES A DVER
N 10 10
Cor relations SALES 1.000 .923 . .000 10 10 ADVER .923 1.000 .000 . 10 10
Model 1
Change Statistics Std. Error A djusted of the R Square R R Square R Square Estimate Change F Change df 1 df 2 a .923 .851 .833 2.86 .851 45.768 1 8
ANOVAb Sum of Squares 374.533 65.467 440.000 Mean Square 374.533 8.183
Model 1
df 1 8 9
F 45.768
Sig. .000 a
a Coe fficients
Standardi zed Unstandardized Coef ficien Coef ficients ts Model 1 B Std. Error Beta (Constant) 7.600 6.332 ADV ER 3.533 .522 .923 t 1.200 6.765
95% Conf idence Interval f or B Correlations Collinearity Statistics Low er Upper Sig. Bound BoundZero-orderPartial Part Tolerance VIF .264 -7.002 22.202 .000 2.329 4.738 .923 .923 .923 1.000 1.000
a Collinearity Diagnostics
Model 1
Dimension 1 2
Minimum Predicted Value Residual Std. Predicted Value Std. Residual 39.40 -4.47 -1.643 -1.561
N 10 10 10 10
Component 1 delivery speed -.787 (x1) price lev el (x 2) .714 price f lex ibility -.804 (x3) manuf ac turer's .102 image (x 4) salesf orc e 2.537E-02 image (x 6) product quality .764 (x7) 2 .194 .266 -1.06E-02 .933 .934 .179
Ex traction Method: Principal Component A naly sis . Rotation Method: V arimax w ith Kaiser Normaliz ation. a. Rotation converged in 3 iterations .
Rotated Component Matriax Component 4 5 .189 .856 -6.80E-02 4. 546E-03 .117 -3.83E-02 -6.10E-02 1. 325E-02 -5.10E-02 .570 .299 .564 -. 159 5. 496E-02 9. 483E-02 .836 .142 .256 -2.67E-02 -1.98E-02 -1.64E-02 -8.33E-02 4. 921E-02 -. 139 -1.16E-02 .279 1. 605E-02 .674 .353 9. 164E-02 .116 .145 -9.47E-02 .173
iklan harga saluran dis tribusi mutu dis ain selera pasar as ses soris suku cadang pelay anan serv is mesin int erior purna jual pilihan warna perawat an mesin merek harga suku cadang keny amanan
1 .104 7. 893E-02 1. 855E-02 .680 -3.41E-02 .829 3. 797E-02 -. 171 .160 .295 -6.53E-02 .294 .666 2. 188E-02 .263 -. 141 9. 868E-02
2 -. 162 8. 013E-02 5. 000E-02 -1.36E-02 .125 .106 .781 6. 724E-03 .123 -. 501 2. 296E-02 .524 -. 390 .108 .156 .642 9. 358E-02
3 -4.89E-02 .800 -2.37E-02 .416 1. 419E-03 6. 443E-03 8. 654E-02 .314 9. 716E-02 .100 .487 -6.54E-02 -7.84E-03 -9.50E-02 .644 .420 -8.17E-02
6 5. 230E-02 -. 278 1. 318E-02 -3.77E-02 6. 597E-02 -3.51E-02 8. 263E-02 .427 -. 399 .103 .257 -. 119 .241 -. 145 .163 .136 .883
7 -3.59E-02 2. 640E-02 -4.14E-02 .131 .894 -. 109 .291 .346 .552 -5.50E-02 2. 670E-02 -. 250 6. 041E-02 -5.67E-02 1. 511E-02 -1.09E-02 -7.68E-04
8 -1.78E-02 -. 182 .896 .111 -8.03E-02 7. 662E-03 7. 472E-02 5. 938E-02 .277 -. 307 -5.89E-02 -. 466 -. 195 .189 .232 -6.24E-02 3. 808E-02
Extrac tion Met hod: Principal Component Analy sis . Rotat ion Met hod: Varimax wit h Kais er Normalization. a. Rotat ion conv erged in 14 iterat ions .
Canonical Dis criminant Function Coefficie nts Func tion 1 .532 1.150 .798 .167 -14.876
CODE 1 2