• Tidak ada hasil yang ditemukan

Univariate Analysis

Dalam dokumen the direct and indirect influence of (Halaman 145-152)

CHAPTER 4 DATA ANALYSIS AND FINDINGS

4.1 Results of the Quantitative Data Analysis

4.1.1 Univariate Analysis

Earl Babbie (2013) stated that: “the analysis of a single variable, for purposes of description. Frequency distributions, averages and measures of dispersion would be examples of univariate analysis, as distinguished from bivariate and multivariate analysis” (Babbie, 2013, p. 426). Univariate analysis has been done through the presentation of a demographic profile and assessing the response rate of the dependent

and independent variables of the particular items-questions. Additionally, data normality was also verified with the help of these analyses.

4.1.1.1 Demographic Profile

The respondents demographic profile included gender, age, educational qualifications, employment position, total service length, present posting place and length of membership of the innovation team. The basic information collected from the respondents concerning their demographic profile has presented in table 4.1.

Amongst the 372 participants, the female respondents were only 14.8%. This ratio shows the meager level of percentage of female officers in the innovation teams at the field level of Bangladesh. The first reason behind this poor level is the low level of entrance of female members in the civil service of Bangladesh. Another reason behind this condition is the interest of the most female civil servants to work in central administration not in the field level administration. The country’s capital city of Dhaka is the center of all of the civic facilities, especially higher education, health issues, and communication. The respondents’ mean age was around 38 (37.36) years and the range was from 26 to 58. About 43% of the respondents were within the age cluster of 35 to 44 years. In the area of educational qualifications, many respondents had a master’s degree at 72% while 27.2% of the respondents held more than a master’s degree, which is the MPhil or Ph.D. The MPhil is a degree achieved before the Ph.D. but after a master’s degree. A very few number of innovation team members have a bachelor degree, at only .8%, and this can be overlooked. The service length was at around 41% (40.6), which is less than five years. The reason behind this is that a very high volume of junior officers is posted in field administration, especially at the district level, to gain field experience. Among the 372 respondents 36% were found to be working as an innovation team member for more than 20 months.

Table 4.1 Respondents’ Demographic Profile

Characteristics Category Frequency

(f)

Percentage (%)

Gender Female

Male Total

55 317 372

14.8 85.2 100 Age (mean 37.36 yrs.) 25-35 years’ old

35-44 years’ old 45-54 years’ old 55-64 years’ old Total

150 160 50 12 372

40.3 43 13.4

3.2 100 Educational

Qualification

Bachelor Master’s Mphil/Ph.D.

Total

3 268 101 372

.8 72.0 27.2 100 Service experience

(Mean 9.02 years)

Less than 5 years 5-10 years 11-15 years

More than 16 years Total

151 101 67 53 372

40.6 27.2 18 14.2

100 IT Membership

Duration (mean 19.23 months)

Less than 2 months 3-5 months

6-10 months 11-20 months

More than 20 months Total

20 39 53 126 134 372

5.4 10.5 14.2 33.9 36 100

4.1.1.2 Descriptive Analysis of the Independent and Dependent Variables……….

At the stage of the data analysis, the first step is to summarize and describe the data that are collected from a specific set of respondents that represent the sample of interest. In a simple survey type research, the whole analysis can be done using descriptive statistics. However, for most studies, data are summarized using descriptive statistics and then other advanced techniques are used to address the relatively complex questions of the research (Mertler & Reinhart, 2017). In the current study the mean score, standard deviation, and also skewness and kurtosis are described using the descriptive technique for all of the variables.

Table 4.2 Descriptive Statistics of the Variables

Mean Std.

Deviation

Skewness Kurtosis Mean Std.

Deviation Statistic Statistic Statistic Std.

Error Statistic Std. Error

II 5.1035 .55277 -1.148 .126 4.140 .252

IM 4.9898 .55118 -1.002 .126 4.464 .252

IS 5.0429 .56384 -.790 .126 1.837 .252

IC 5.0753 .50311 -1.157 .126 4.028 .252

TC 4.7345 .61424 -.488 .126 .550 .252

RR 4.6783 .72791 -.737 .126 .788 .252

TS 4.6514 .82341 -1.122 .126 1.801 .252

RS 4.8497 .65550 -.698 .126 .694 .252

RO 4.0484 .72150 -.679 .126 2.005 .252

EO 4.2554 .73191 -.895 .126 2.015 .252

PG 4.2957 .67985 -.964 .126 3.174 .252

PS 5.0121 .59189 -.544 .126 .106 .252

FI 4.8714 .59896 -.285 .126 .578 .252

FT 4.8669 .61429 -.230 .126 .137 .252

OG 4.8656 .65328 -.532 .126 .258 .252

IG 4.8441 .66128 -.463 .126 .526 .252

RL 4.9355 .62146 -.419 .126 .068 .252

EF 5.0287 .53740 -.795 .126 1.151 .252

RT 5.0717 .65905 -.643 .126 .582 .252

RC 5.0049 .63989 -1.089 .126 2.717 .252

RV 5.0130 .62227 -.599 .126 .534 .252

TL 5.0543 .46040 -1.233 .127 6.308 .253

POS 4.7877 .51086 -.455 .126 -.059 .252

POC 4.8595 .47333 -.483 .126 .011 .252

CR 4.8624 .50845 -.437 .127 .172 .253

PSIO 5.0081 .48860 -.714 .126 .387 .252

In descriptive statistics table 4.2, it is expressed that the respondents agreed about transformational leadership (mean score 5.04) and public service

innovation outcomes (mean score 5.01) at the highest level. The sub-variables of the independent variables revealed comparatively better levels of influence: they were idealized influence, intellectual stimulation, and individualized consideration (mean was 5.10, 5.04, and 5.07 respectively). Moreover, problem sensitivity, effectiveness, reduced time, reduced costs, and reduced visits had greater influences (mean was 5.01, 5.02, 5.07,5.00, 5.01, respectively).

According to Hair et al. (2010): “the shape of any distribution can be described by two measures: Kurtosis and Skewness. Kurtosis refers to the peakedness or flatness of the distribution compared with the normal distribution” (Hair et al., 2010, p. 71). He also stated that “skewness is used to describe the balance of the distribution; that is, it is unbalanced and shifted to one side (right or left). If a distribution is unbalanced, it is skewed. A positive skew denotes a distribution shifted to the left, whereas, a negative skewness reflects a shift to the right” (Hair et al., 2010).

For the current study, the researcher examined the skewness and kurtosis of the dependent and independent variables and found that they were normally distributed. Skewness and kurtosis for IV and DV were marked within the standard range of -2 to +2 for checking the variables normality (Thapa, 2013, p. 121).

Even though the null hypothesis (p>0.05) was rejected, the standard errors were not satisfactory for all of the cases. In this circumstance, the researcher decided to use two other advanced and sophisticated tests in order to obtain more reliable results, which are the Kolmogorov-Smirnov and Shapiro-Wilk tests.

4.1.1.3 Test of Normality

Hair et al. (2006) described normality as “Normality is accepted as the assumption concerning the data distribution where each item should be in all linear combination of items” (Hair et al., 2006; Kline, 2005; Fidell & Tabachnick, 2007). In table 4.3 it is recorded that the p-values for both the dependent and independent variables were found to be <0.05. This reason was not enough to reject the null hypotheses. Pallant (2010) explained that “violation of the assumption of normality is quite common in large sample sizes” (Pallant, 2010).

Table 4.3 Test of Normality

Kolmogorov-Smirnova Shapiro-Wilk

Statistic Df Sig. Statistic df Sig.

II .153 372 .000 .922 372 .000

IM .085 372 .000 .939 372 .000

IS .110 372 .000 .953 372 .000

IC .107 372 .000 .934 372 .000

TC .105 372 .000 .968 372 .000

RR .125 372 .000 .957 372 .000

TS .147 372 .000 .926 372 .000

RS .104 372 .000 .959 372 .000

RO .282 372 .000 .805 372 .000

EO .254 372 .000 .782 372 .000

PG .262 372 .000 .759 372 .000

PS .139 372 .000 .949 372 .000

FI .123 372 .000 .960 372 .000

FT .122 372 .000 .963 372 .000

OG .123 372 .000 .951 372 .000

IG .150 372 .000 .956 372 .000

RL .141 372 .000 .958 372 .000

EF .080 372 .000 .959 372 .000

RT .122 372 .000 .939 372 .000

RC .158 372 .000 .913 372 .000

RV .118 372 .000 .955 372 .000

TL .050 371 .027 .938 371 .000

POS .068 372 .000 .980 372 .000

OC .069 372 .000 .980 372 .000

CR .066 371 .001 .981 371 .000

PSIO .095 372 .000 .963 372 .000

Dalam dokumen the direct and indirect influence of (Halaman 145-152)