1 Abstract This diploma thesis subjects on rating scales that measure respondent's value of the agreement with given statement. Particularly it focuses on a number of scale points and usage of mid-point and option "Don't know". Due to the fact, there is not an optimal number of points that scale should contain the author focuses on comparing scales of different length. This work includes research that uses four types of the questionnaire to test differences between odd and even scales of different lengths. The thesis shows that share of extreme points is based on scale length. With the use of shorter scales, respondents are more likely to choose extreme points. Based on respondents' answers, the difficulty to choose from scale options is similar in both even and odd scales. Option "Don't know" was mostly chosen by indecisive and poorly-informed respondents when the even scale with above-mentioned option was used. In the case of using an odd scale, the mid-point was chosen also mainly by indecisive respondents, so odd scales should be combined with option "Don't know" for better detection of neutrality. Keywords Rating scale, attitude measurement, odd scale, even scale, mid-point, number of scale points, Web survey, online questionnaire

This thesis deals with an issue of how can graphical modifications of response options in online questionnaire influence the respondents' answers. Online questionnaire as a data collection method offers a wide range of visual adjustments. Therefore, it is necessary for the graphical format to be treated with caution, because it can produce significant differences in respondents' answers. The goal of this thesis is to find out, with the help of two versions of online questionnaire that differ in the graphical format of response options, whether and what differences in answers these modifications produce. The attention is also payed to the response time differences. Together there are eleven modifications tested, each of them is represented twice. The analysis shows that the differences in graphical format of response options do influence the answers; there were 7 of 11 hypotheses confirmed. One of the surprising findings is that in the case of comparing the format of check boxes and the format of writing answers into text boxes, respondents answered with a maximum number of allowed answers in both version. This type of result was not expected in the case of the "writing into text boxes" format. Other findings show that some modifications influence more women than men, for example the use of a...

Private business subjects are characterised by their continuous effort for increasing their market position. Therefore they are permanently monitoring their own sthrengths and weaknesses, and they are also monitoring their competitors´ behaviour and customers´ needs and wishes. Such pieces of information can be received by analysis of business surroundings and from custommers´ opinion. Activities like these are called marketing research. The research should include all aspects that influence the way of perception of the company by any other market subject, or even the atmosphere inside the company. Information received is valuable for managers and their decision-making. Marketing research is a dynamicly developing field where new findings of social sciences are permanently applied. A significant developement in this field was reached mainly in last years. It is a result of the rapid progress of information and communication technologies. Modern forms of marketing research often use the Internet for collecting various information on the market.

This research explores what type of verbal/text survey content translates effectively between survey modes within a Computer Assisted Telephone Interview (CATI) and Computer Assisted Web Interview (CAWI) mixed-mode survey project within unified mixed-mode survey design. This phenomenon is researched through the implementation of online probes within an existing CAWI survey project for sections close to an original CATI design. This research provides insights into how respondents understand and conceptualize verbal content within a unified mixed-mode CAWI survey in today’s online survey environment. This research is timely as the penetration of mobile has increased drastically, which may have implications on CAWI/CATI mixed-mode research considering the conflicting best practices for mobile CAWI survey design and CATI survey design. The results show that respondents do not engage with introductory pages enough to reliably recall their information, even when significantly shortened and simplified. Additionally, respondents are sensitive to high amounts of text and topics within survey question spaces. This means that some aspects of CATI survey design do not translate to CAWI and may even be cause for data quality concerns. These findings highlight some key issues faced by researchers and practitioners, provide some guidance on how design choices may impact results, and presents rich opportunities for future research.

The thesis focuses on body image - defines the main characteristics of this area, describes cultural influences and body image history and explains basic quantitative values (Body Mass Index, Waist Hip Ratio, Bioelectrical Impedance Analysis). Furthemore the thesis deals with media influence on body ideal formation process, especially in gay subculture. The research part explores recent situation of body image in gay subculture compared with heterosexual males. This section includes the content analysis of mainstream gay movies which compares media presentation of gays and the real situation and examines media influence on gay body image formation.