Posted on

Non Response Bias Test Business Essay

This chapter intends to bespeak the consequences based on the analysis of informations collected utilizing Structural Equation Modeling. This information collected is screened, validated and analyzed by utilizing factor analysis and the internal consistence process of dependability analysis, correlativity appraisal, convergent cogency analysis, discriminant cogency, collateral factor analysis ( CFA ) , and Structural Equation Modeling ( SEM ) . The consequences of the analysis are presented utilizing statistical bundles, Analysis of Moment Structures ( AMOS ) and Statistical Package for the Social Sciences ( SPSS ) . Hypothesis testing is used to analyze the relationship between the variables of larning organisation, organisational innovativeness, and organisational public presentation.

4.2 Non-Response Bias Test

Non-response prejudice trial was undertaken because this type of prejudice affects the reading of the variables and later affects the overall decisions resulted from the information analysis. Evidence from bing literatures have established that the non-respondents sometimes differ consistently from the respondents both in attitudes, behaviours, personalities, motives, demographics and/or psychographics, in which any or all of which might impact the consequences of the survey ( Malhotra, Hall, Shaw, Oppenheim, 2006 ) .

Non-response prejudice was assessed by comparing the responses in the questionnaires between the early and late returns ( Armstrong & A ; Overton, 1977, Churchill & A ; Brown, 2004, Malhortra et al. , 2006 ) . Non-response prejudice has been tested utilizing the t-test to compare the similarities between mean, standard divergence, and standard mistake mean of the demographic information of the last 60 per centum of the respondents ( figure of instances = 238 ) to the information of the first 40 per centum of the respondents ( figure of instances = 160 ) . Harmonizing to the consequences as shown in Table 4.1, the responses indicate no important differences between each group. Therefore, non-response prejudice has no important impact in this survey.

Table 4.1

Trial of Non-Response Bias between Group Differences of Early 40 per centum and Late 60 per centum

Variable

Response

Number of Cases

Mean

Standard Deviation

Standard Error Mean

Gender

Early on

160

1.280

0.451

0.036

Late

238

1.300

0.458

0.030

Type of Business

Early on

160

1.430

0.497

0.039

Late

238

1.470

0.500

0.032

Experience

Early on

160

3.140

0.759

0.060

Late

238

2.990

0.787

0.051

Position

Early on

160

1.310

0.465

0.037

Late

238

1.300

0.460

0.030

Number of Employees

Early on

160

1.900

0.301

0.024

Late

238

1.890

0.307

0.020

Age of Business

Early on

160

2.530

0.501

0.040

Late

238

2.550

0.499

0.032

International Business

Early on

160

1.510

0.502

0.040

Late

238

1.450

0.498

0.032

4.3 Data Screening and Outliers

This subdivision considers each portion of the informations showing and investigates the root cause of informations mistakes that may impact the concluding result. The information showing observes the informations place for all staying informations. All information is entered into SPSS version 20 and analyzed utilizing AMOS version 18.0. Datas testing includes outlier checking, losing informations, descriptive statistic, univariate normalcy, multicollinearity, dependability, and cogency testing.

4.3.1 Outlier Checking ( Mahalanobis Distance )

Statistical grounds has established outliers as any observations, which are numerically distant if compared to the remainder of the information set ( Bryne, 2010 ) . There is bing research literature that uses different methods of observing outliers among which are includes sorting informations points based on an observed ( Mahalanobis ) distance from the research expected values ( Hair et al. , 2010 ; Hau & A ; Marsh, 2004 ) . The constructive statement in favour of outlier interventions based on Mahalanobis distance is that it serves as an effectual agencies of observing outliers through the scenes of some preset threshold that will help in specifying whether a point could be categorized as outlier or non.

For this research, chi-square statistics has been used as the threshold value to find the empirical optimal values in the research. This determination is in line with the statements of Hair et Al. ( 2010 ) which emphasized on the demand to make a new variable in the SPSS excel to be labelled ‘No. ‘ totaling from the beginning to the terminal of all variables. The Mahalanobis can merely be achieved by running a simple additive arrested development through the choice of the freshly created response figure as the dependant variable and choosing all measurement points apart from the demographic variables as independent variables. Consequently, a new end product is created called Mahalanobis1 ( Mah1 ) , upon which a comparing was made between the chi-square value and a upper limit of Mahalanobis distance value in Table 4.2, which besides includes the new Mahalanobis end product.

Table 4.2

Outlier Detection ( Mahalanobis Distance )

Min.

Max.

Mean

Standard Deviation

Number of Cases

Predicted Value

-6.32

451.63

199.50

77.192

398

Standard Predicted Value

-2.666

3.266

.000

1.000

398

Standard Error of Predicted Value

5.899

59.259

28.507

6.600

398

Adjusted Predicted Value

-31.67

463.81

198.32

78.266

398

Residual

-253.756

193.111

.000

85.293

398

Standard Residual

-2.817

2.144

.000

.947

398

Deleted Residual

-270.853

226.881

1.179

94.793

398

Mahal. Distance

.706

170.845

40.897

18.576

398

Note. Min. = lower limit ; Max. = upper limit

The value of Mahalanobis Distance ( D2 ) is greater than a critical value and used as the threshold degree for D2/df step which should be conservative degree of significance ( 0.005 or 0.001 ) for appellation on outliers ( Hair et al. , 2010 ) . D2 is known as the Mahalanobis distance and is the distance between each observation in multidimensional infinite from the average Centre of all the observations. Df is the grade of freedom, or the figure of variables involved ( Hair et al. , 2010 ) .

For this survey, the upper limit of Mahalanobis distance is 170.845 as shown in Table 4.2 greater than the critical value. The critical value mentioned in chi-square value is 74.745 at df=41, p=0.001 ( mention to Appendix D ) . This means there are 6 respondents of the sum of 398 respondents that were deleted. The testing informations of these outliers and the concluding arrested development in this survey were performed utilizing the staying 392 samples in the information set.

4.3.2 Missing Data

Once the questionnaire informations are collected, the first measure in informations showing is to place the information mistakes. The extent of losing informations affects the unit informations seting at hazard the analysis consequence. Normally, losing informations under 10 per centum for an single instance or observation can by and large be ignored, except when the losing information occurs in a specific nonrandom manner such as concentration in a specific set of inquiries and abrasion at the terminal of the questionnaire ( Hair et al. , 2010 ) . In this survey, the losing informations ( refer to Appendix E ) does non be in every questionnaire. Therefore, this survey determines the figure of instances without losing variables, which provide the sample size variable for informations analysis still remedies.

4.3.3 Descriptive Statistic

The following profile was found among the informations showing procedure. In general, the descriptive latent concepts include maximal, minimal, average, standard divergence, manner, and average. The nine latent concepts ( uninterrupted acquisition ( CL ) , enquiry and duologue ( ID ) , squad acquisition ( TL ) , embedded system ( ES ) , empowerment ( EM ) , system connexion ( SC ) , strategic leading ( SL ) , organisational innovativeness ( OI ) , and organisational public presentation ( OP ) are presented in Table 4.3.

Table 4.3

Descriptive Statisticss of Variables

Number of Cases

Missing Datas

Mean

Standard Deviation

Continuous Learning

392

0

3.169

1.263

Inquiry and Dialogue

392

0

3.379

1.147

Team Learning

392

0

3.304

1.223

Embedded system

392

0

3.401

1.134

Authorization

392

0

3.480

1.129

System Connection

392

0

3.098

1.294

Strategic Leadership

392

0

3.361

1.174

Organizational Innovativeness

392

0

3.342

0.945

Organizational Performance

392

0

2.998

1.037

The average value of the nine concepts are based on 41 inquiries. Organizational public presentation ( OP ) is lowest for average value ( 2.998 ) while the highest mean is empowerment ( EM = 3.480 ) . For standard divergence, system connexion ( SC ) is the highest value ( 1.294 ) , uninterrupted acquisition ( CL ) is 1.263, squad acquisition ( TL ) is 1.223, strategic leading ( SL ) is 1.174, enquiry and duologue ( ID ) is 1.147, embedded system ( ES ) is 1.134, authorization ( EM ) is 1.129, and organisational public presentation ( OP ) is 1.037, but the lowest value is the organisational innovativeness ( OI ) with 0.945.

4.3.3.1 Demographic Profile of the Respondents

The demographic profile of the participants SMEs characteristic consists of the seven major points as follows: ( 1 ) gender, ( 2 ) type of concern, ( 3 ) experience, ( 4 ) place, ( 5 ) figure of employees, ( 6 ) age of concern, and ( 7 ) international concern. The analysis consequences of the before mentioned variables are presented in Table 4.4 and Appendix F. The consequences are shown as the frequence and per centum.

Table 4.4

The Demographic Profile of the Respondents consist of the Seven Major Items

Demographics

Frequency

Percentage

Gender

Male

Female

280

112

71.4

28.6

Type of concern

Manufacturing

Service

216

176

55.1

44.9

Experience of work ( in this concern )

More than 5 but less than 7 old ages

More than 7 but less than 9 old ages

More than 9 old ages

109

153

130

27.8

39.0

33.2

Position

Owner

Director

272

120

69.4

30.6

Number of employees

1-50

51-200

40

352

10.2

89.8

Age of concern

6-10 old ages

More than 10 old ages

180

212

45.9

54.1

International concern

Yes

No

207

185

52.8

47.2

Table 4.4 shows the demographic information of all respondents. A sum of 398 ( 39.8 per centum ) functional responses were obtained out of the 1,000 questionnaires sent. Harmonizing to Sekaran ( 2003 ) the lower limit of 10 per centum response from the sample justifies the rational to get down and execute the analysis. In this survey, the concern proprietor or directors were identified as the cardinal sources. They are considered the most appropriate as they are the best positioned forces to hold the broadest cognition of the overall issues under probe.

Based on the informations from Table 4.4, the bulk of the respondents were male with a sum of 280 respondents ( 71.4 per centum ) , while female respondents accounted for 28.6 per centum ( 112 respondents ) from the entire sample. The concern type of fabrication had the highest figure of respondents with 216 ( 55.1 per centum ) . Other type ( service concern ) with 176 respondents accounted for 44.9 per centum.

130 respondents or 33.2 per centum indicated that they have had more than 9 old ages experience in concern, whereas the highest degree of concern experience was more than 7 old ages but less than 9 old ages with 153 respondents or 39.0 per centum. 109 respondents or 27.8 per centum indicated that they have had more than 5 old ages but less than 7 old ages experience in concern.

272 or 69.4 per centum of the respondents were proprietors, while 120 respondents or 30.6 per centum were directors. From these analyses, it can be concluded that the bulk of the respondents were from the fabrication and service concerns, they were proprietor or director and have sufficient cognition to be in this industry.

89.9 per centum or 352 respondents were of a medium size concern with between 51 and 200 employees, whereas 10.2 per centum or 40 respondents were of a little size concern with less than 50 employees.

212 respondents or 54.1 per centum indicated that their concerns have been established for more than 10 old ages, 180 respondents or 45.9 per centum established from 6 to 10 old ages.

Finally, 207 respondents or 52.8 per centums are international concerns, and 185 respondents or 47.2 per centum are domestic concerns.

4.3.5 Univariate Normality

Univariate normalcy calculation is conducted utilizing z-scores of lopsidedness statistics, standard mistake of lopsidedness every bit good as kurtosis statistics to analyse the dataset. The z-score of lopsidedness more than 3 demands to be transformed since it is considered as non-normal informations ( Hair et al. , 2010 ) . This survey found that the absolute of lower limit and a maximal skewness value indicated normal distribution because the value z-score is below 3 ( refer to Appendix G ) . Therefore, informations distribution is separately normal.

4.3.6 Multicollinearity Trials

The multicollinearity was examined utilizing the discrepancy rising prices factor ( VIF ) steps and tolerance value. The consequence of VIF and Tolerance for all variables under survey as shown in Table 4.5 found that VIF values were ranged between 1.586 to 2.239 that were below the threshold value of 10 ( & lt ; 10 ) and tolerance value of all variables were ranged between 0.447 to 0.631 that is well more than 0.10 ( Hair, Black, Babin, & A ; Anderson, 2009 ) . The VIF and tolerance of the variables indicated that there was non grounds of terrible collinearity between the independent variables.

Table 4.5

Multicollinearity Test – Discrepancy Inflation Factor ( VIF ) and Tolerance

Variables

Collinearity Statisticss

Tolerance

Variance Inflation Factor ( VIF )

Continuous Learning

.561

1.784

Inquiry and Dialogue

.536

1.865

Team Learning

.575

1.738

Embedded System

.598

1.671

Authorization

.524

1.909

System Connection

.608

1.644

Strategic Leadership

.494

2.024

4.3.7 Reliability Test

Cronbach ‘s alpha dependability analysis is applied to prove the internal consistence to esteem multi-dimension. Nunnally ( 1967 ) and Shih and Fang ( 2004 ) minimum Cronbach ‘s alpha of dependability is sufficient above 0.6 for the early phase of the research.

Table 4.6

Descriptive Statistic of Reliability

Variables

Number of points

Cronbach ‘s alpha

Composite dependability

Continuous Learning

3

0.871

0.975

Inquiry and Dialogue

3

0.889

0.981

Team Learning

3

0.917

0.983

Embedded System

3

0.923

0.984

Authorization

3

0.865

0.978

System Connection

3

0.923

0.984

Strategic Leadership

3

0.929

0.984

Organizational Innovativeness

11

0.934

0.991

Organizational Performance

9

0.920

0.989

As shown in Table 4.6 and Appendix H, each concept is Cronbach ‘s alpha reading with peculiar property to related runing from 0.865 to 0.934.

Composite dependability is listed in Table 4.6. There is acceptable value that indicates a possible internal consistence. The computation of composite dependability is based on the standardised factor lading resulted from the concluding modified structural theoretical account ( refer to Appendix H ) . The expression of composite dependability is shown as follows:

Composite dependability = ( a?‘ standardized lading ) 2

( a?‘ standardized lading ) 2 + a‚¬a?‘j

With regard of composite dependability and Cronbach ‘s Alpha value, George and Mallery ( 2003 ) indicated that dependability greater than 0.9 is considered to be first-class, greater than 0.8 is good, greater than 0.7 is acceptable, greater than 0.6 is questionable, and less than 0.5 is hapless. Additionally, Sekaran ( 2000 ) indicated that the closer the dependability gets to one the better it is. Therefore, with a value between 0.983 to 0.991. The composite dependability of concepts are of an first-class criterion. It is considered that any tonss above 0.60 is of an acceptable criterion ( Nunnally, 1967 ) . All dependability in this survey are above the acceptable criterion.

4.3.8 Validity Test

Cogency refers to the truth of measuring, whether the conceptual and operational definitions are genuinely a contemplation of the underlying construct to be measured ( Burns & A ; Bush, 1995 ; Neuman, 1994 ) . There are three types of cogency: content cogency, concept cogency, and standard cogency.

Contented Cogency

Contented cogency was used to stand for the grade of truth between a set of steps and the constructs of involvement ( Cronbach & A ; Meehl, 1955 ; Hair et al. , 2010 ) . Prior to establishing the study, the questionnaire was pretest and pilot trial to formalize content cogency and was generated foremost in an English version and so interpret into Thai. The procedure for the pilot trial as described in Chapter 3 ( refer to page 108 ) included two research workers and two proprietors from a sample in the pilot trial. Their function was to guarantee the lucidity of each inquiry. As a consequence, five inquiries were modified and included in the concluding questionnaire.

Construct Validity

Construct cogency was used to corroborate that the indexs aligned with the factors as they are mensurating instrument adequateness ( Schwab, 1980 ; O’Leary-Kelly & A ; Vokurka, 1998 ; Cronbach & A ; Meehl, 1955 ) . This survey performed concept cogency for nine measuring concepts, that represent the theoretical latent, they are uninterrupted acquisition, enquiry and duologue, squad acquisition, embedded system, authorization, system connexion, strategic leading, organisational innovativeness, and organisational public presentation. Construct cogency was evaluated by convergent cogency, discriminant cogency, and nomological cogency.

( 1b ) Convergent Cogency

Convergent cogency is established by high factor burdens and high important degrees of the index variable ( Schwab, 1980 ) . In order to measure convergent cogency, it is indispensable to measure the statistical significance of the estimated parametric quantities between concepts and their points. This survey used Confirmatory Factor Analysis ( CFA ) ( refer to Postpone 4.7 ) to gauge the values of the factor lading between indexs and the factor. The factor burdens indicate the correlativity between the indexs and the factor. The values of the factor burden should be greater than 0.50 for each index in the factor ( Hair et al. , 2010 ) . A single-factor CFA is carried out merely when executable, given that CFA needs at least four points per latent variable to obtain grades of freedom. When this status was non achieved, the corresponding concept was allowed to correlate to another concept to obtain factor burdens ( Anderson & A ; Gerbing, 1988 ) . Consequently, a individual factor theoretical account was performed for organisational innovativeness and organisational public presentation, whereas the learning organisation factors ( uninterrupted acquisition, enquiry and duologue, squad acquisition, embedded system, authorization, system connexion, and strategic leading ) were correlated.

Table 4.7

Convergent Validity – Confirmatory Factor Analysis ( CFA )

Exogenous

Variables

Code

Indexs

Factor

Loading

Continuous

Learning ( CL )

CL1

In my organisation, people help each other learn.

0.818

( 3 points )

CL2

In my organisation, people take clip to back up acquisition.

0.849

CL3

In my organisation, people are rewarded for acquisition.

0.828

Inquiry and

Dialogue ( ID )

ID1

In my organisation, people give unfastened and honest feedback to each other.

A 0.910

( 3 points )

ID2

In my organisation, whenever people province their position, they besides ask what others think.

0.800

A

ID3

In my organisation, people spend clip edifice trust with each other.

0.859A

Team

Learning ( TL )

TL1

In my organisation, people have the freedom to accommodate their ends as needed.

0.876

( 3 points )

TL2

In my organisation, people revise believing as a consequence of organisation treatments or information collected.

0.939

A

TL3

In my organisation, we are confident that the organisation will move on our recommendations.

0.845A

Embedded

System ( ES )

( 3 points )

ES1

My organisation creates systems to mensurate spread between current and expected public presentation.

0.899A

ES2

My organisation makes its lessons learned available to all employees.

0.897

A

ES3

My organisation measures the consequences of the clip and resources spent on preparation and acquisition.

0.886A

Empowerment ( EM )

( 3 points )

EM1

My organisation recognizes people for taking enterprise.

0.854

EM2

My organisation gives people control over the resources they need to carry through their work.

0.862

A

EM3

My organisation supports members who take deliberate hazards.

0.769

Table 4.7 ( Continued )

Convergent Validity – Confirmatory Factor Analysis ( CFA )

Exogenous

Variables

Code

Indexs

Factor

Loading

System

Connection ( SC )

SC1

My organisation encourages people to believe from a planetary position.

0.888

( 3 points )

SC2

My organisation works together with the outside community or other outside resources to run into common demands.

0.918

SC3

My organisation encourages people to acquire replies from multiple locations and positions when work outing jobs.

0.877

Strategic

Leadership ( SL )

SL1

In my organisation, leaders mentor and coach those they lead.

0.869

( 3 points )

SL2

In my organisation, leaders continually look for chances to larn.

0.930

SL3

In my organisation, leaders guarantee that the organisation ‘s actions are

0.912

Organizational

Innovativeness

OI1

Management actively seeks advanced thoughts.

0.809

( 11 points )

OI2

Invention is readily accepted in program/project direction.

0.751

OI3

Technical invention, based on research consequences, is readily accepted.

0.762

A

OI4

Invention in this concern unit is perceived as excessively hazardous and is resisted.

0.761

A

OI5

In new merchandise and service debuts, our company is frequently first-to-market.

0.734

A

OI6

Our new merchandises and services are frequently perceived as really fresh by clients

0.745

A

OI7

In comparings with our rivals, our company has introduced more advanced merchandises and services during the past five old ages.

0.771

A

OI8

In comparings with our rivals, our company has lower success rate in new merchandises and services launch.

0.773

Table 4.7 ( Continued )

Convergent Validity – Confirmatory Factor Analysis ( CFA )

Exogenous

Variables

Code

Indexs

Factor

Loading

Organizational

Innovativeness

OI9

We are invariably bettering our concern procedures.

0.719

OI10

Our company changes production methods at a great velocity in comparing with our rivals.

0.711

OI11

During the past five old ages, our company has developed many new direction attacks.

0.707

Organizational

Performance ( OP )

OP1

In my organisation, return on investing is greater than last twelvemonth

0.780

( 9 points )

OP2

In my organisation, gross revenues growing is greater than last twelvemonth

0.769

OP3

In my organisation, mean productiveness per employee is greater than last twelvemonth.

0.648

A

OP4

In my organisation, clip to market for merchandises and services is less than last twelvemonth.

0.773

A

OP5

In my organisation, take attention for client complaints/needs is better than last twelvemonth.

0.764

A

OP6

In my organisation, the cost per concern dealing is less than last twelvemonth.

0.680

A

OP7

In my organisation, market portion is greater than last twelvemonth.

0.811

A

OP8

In my organisation, the net income volume is greater than last twelvemonth.

0.773

A

OP9

In my organisation, the extra capital is greater than last twelvemonth.

0.752

Leave a Reply

Your email address will not be published.