Make your own free website on Tripod.com

PROJECT 4: ANALYSES OF POWERLESSNESS SURVEY DATA

MKTG 7213 - Dr. Gregory W. Boller

Submitted by Indradi Soemardjan on April 23, 2001


 

OBJECTIVE

To explore the different levels of “felt powerlessness” in relation to exposure to various electronic media types and violent video games buying behavior.

 

SCOPE OF WORK

Using historical data provided by Dr. Gregory W. Boller, the followings tasks are to be accomplished:

DATA SOURCE

The analyses and statistics were generated using the data extracted from these URL’s”


INTRODUCTION TO CONCEPTS AND TERMS

Independent Samples Tests for Information Mastery

Statistical significance is founded on estimating how likely an event is. For example, if we tossed a coin 100 times and got 51 heads and 49 tails, we wouldn't be likely to think the coin was crooked or defective. We expect some variation from 50%, after all; in data analysis this variation is called random error. If we got 55 heads, though, we might wonder about our coin. A statistical test would work out the probability of getting 55 heads with an honest coin, and we would then decide if the probability were low enough to worry about.

For the purpose of this assignment, we will concentrate on information mastery, rather than information management. In this Marketing Research course, we are trying to get trained in the simple skills and concepts, which give us mastery over information.

Our focus at this point is statistical significance. It is truly a simple concept, but most people have not been taught about it. It is also one of the most important concepts in real analysis, so the general lack of acquaintance with it is hampering our ability to get useful information out of all this electronic technology we've surrounded ourselves with.

* Click hereto read the manual/guidelines on how we run the Independent Samples Tests and how we analyze the results.

Correlation is only a descriptive analysis

Correlations are relationships between two or more variables or sets of variables. They have three fundamental dimensions: significance, direction, and magnitude. These dimensions will be addressed throughout. The correlations differ with respect to the number and kinds of variables whose relationship is being studied. When we say that two variables are correlated, we mean that knowledge of one enables you to predict the other with known accuracy.

Correlation may be measured with several different statistics, but the one used for this purpose is the Pearson correlation coefficient, which ranges from 1 to -1. The higher the coefficient, the more alike two variables are, the lower the coefficient, the more unlike they are. Of course, even when they are unlike you still may be able to predict one from the other. Textbooks often classify different strengths of correlation. For example, a coefficient of .90 or above (or -.90 or below) will be said to be strong, correlations of .70 to .89 and -.70 to -.89 will be said to be moderate, and so on. However, the value of a correlation coefficient depends on its practical implications rather than on arbitrary numerical standards.  

People often note that correlation does not imply causation. Correlation is only a descriptive analysis; hence, strong correlations do not necessarily mean there is a cause-effect relationship between two variables. The truth is: there's not much, if anything, we can do in research that will imply causation, but the point is that a correlation does not imply that if we manipulate one variable you will control the other. For example, levels of felt powerlessness are correlated with the value of violent video game sales, but if you control levels of felt powerlessness in public you wouldn't lower the value of violent video game sales. Violent video game sales and levels of felt powerlessness are correlated because they are both correlated with the exposure to different entertainment media – perhaps when people watch more horror or mystery movies they are more likely to feel powerless and to buy violent video games. When one goes up so does the other, and voilà – there's our significant correlation.

* Click here to read the manual/guidelines on how we run the Correlation Analysis and how we interpret the Correlation Matrix.


PART 1 - Gender and electronic media type preferences

A. Gender and Game title preferences

Click here to view Table 1A

Our study shows that gender differences play an important role in video games buying behavior. Seven out of eight sample computer games listed above appealed to each gender types significantly. The chart above also shows that video games that consisted of adult violence and sports appeal mostly to males than they do to females.

B. Gender and TV programming type preferences

Click here to view Table 1B

The table above shows the various level of enjoyment in watching each type of programming. Apparently, only sitcom, news and cartoon programming types appeal almost equally to both gender types; the remaining programming types present different appeals to each gender type.  

C. Gender and movie type preferences

Click here to view Table 1C

Four of ten different types of movie do not present unique appeals to each gender type. According to our Independent Samples Tests, males and females are equally interested in mystery, horror, foreign and comedy movies. The only movie type that appeals significantly to females (than they do to males) is romance movie. Science fiction movies, on the other hand, spark more interests from males than it does from females.

D. Gender and computer game type preferences

Click here to view Table 1D

Four of ten different types of computer game do not present unique appeals to each gender type. According to our sample tests, males and females are equally interested in adventure/mystery, role-playing game, fly-drive simulation and arcade-style games on computer. Males are distinguishably very interested in playing sports game than females

E. Gender and the level of felt powerlessness

Click here to view Table 1E

Surprisingly, the group statistics show that there is no significant difference between the two groups; which means that males and females evidently share the same level of felt powerlessness as described in this study.

 

PART 2 - Age and electronic media type preferences

A. Age and Game title preferences

Click here to view Table 2A

Riven, Links and Flight clearly appeal to both younger and older people equally. Surprisingly, Dahlia and Redneck, despite of their realistic blood and gore, still seem appealing to young people equally as they do to the older people. Out of all games titles, Postal and Sword have the greatest tendency to be played by older people than the younger ones

B. Age and TV programming type preferences

Click here to view Table 2B

Sports, drama, true-life story and science fiction programming types are all equally appealing to both age groups. However, science and music programming types (such as PBS and MTV/VH-1) significantly appeal to specific age group only; one to the older and the other to the younger, respectively.

C. Age and movie type preferences

Click here to view Table 2C

Action/adventure, romance, mystery, drama and family movie types are all equally appealing to both age groups. Science fiction and foreign movie types are dominantly popular among older people, while horror movie type, on the other hand, is very appealing to younger people.

D. Age and computer game type preferences

Click here to view Table 2D

In this Independent Samples Tests, only one game type appeals more dominantly to one age group; role-playing game type appeals more to young people. Among all game types, adventure/mystery game type has the least unique appeal to either group; both younger and older people enjoy playing such a game.

E. Age and the level of felt powerlessness

Click here to view Table 2E

Younger people tend to have higher level of felt powerlessness than older people do, implying that it may be a function of the level of maturity.

 

PART 3 - Correlation Analyses between Level of Felt Powerlessness and Various Variables

A. Correlation between Level of Felt Powerlessness and various game titles

Click here to view Table 3A

Evidently, there are no significant correlations between the level of felt powerlessness and these non-violent game titles: Riven, Links and Flight. However, the correlations are positive and of relatively significant magnitude between the level of felt powerlessness and these game titles: Sword, Postal, Dahlia and Redneck (all of them have relatively dominant violent content). Out of those five violent game titles, Redneck has the greatest magnitude. There is no negative correlations indicated by this analysis, thus, implying positive causation among all variables. Postal and sword game types are ranked the strongest in positive correlation category

B. Correlation between Level of Felt Powerlessness and various TV programming types

Click here to view Table 3B

There are apparent correlations between the level of felt powerlessness and these TV programming types: soap Opera, music (MTV/VH-1), cartoons and science fiction. The strongest positive correlation exists between historical and science/PBS programming types, followed by science/PBS and science fiction as the second strongest. The strongest negative correlation exists between soap opera and science/PBS programming types, which indicates the opposite causation between the two.

C. Correlation between Level of Felt Powerlessness and various movie types

Click here to view Table 3C

Surprisingly, level of felt powerlessness has a strong positive correlation with foreign movie type. It’s somewhat less positive correlation with horror movie type makes this data matrix interesting to look at. This study shows that level of felt powerlessness has no significant correlation with mystery, western, nor action/adventure movie types. The strongest positive correlation exists between action/adventure and comedy programming types, followed by drama and romance as the second strongest.

D. Correlation between Level of Felt Powerlessness and various computer game types

Click here to view Table 3D

Surprisingly, level of felt powerlessness does not have any significant correlation with any of the game types. However, card and puzzle game types are ranked the strongest in positive correlation category, followed by strategy and role-playing game types in second place (and action/fighting and adventure/mystery in the third place). Puzzle and sports game types have the only negative significant correlation, hence, implying negative causation among them.

 

CONCLUSION  

These findings present so many intriguing ideas about how the level of felt powerlessness, age and gender are actually related to people's perceptions about various electronic media such as television programming, movie and computer game types (as well as the most popular computer game titles). Table 3A indicates that the correlations are positive and of relatively significant magnitude between the level of felt powerlessness and these game titles: Sword, Postal, Dahlia and Redneck, while Table 3D indicates no apparent correlation between the level of felt powerlessness and any of the game types. Such inferences may create some ambiguity in explaining the main objectives of this study. 

 

It is very easy to misinterpret the findings due to some apparent discrepancies that are present among several different measures. However, there  are general patterns that are somewhat consistent in this context:

 

 


© 2001 Indradi Soemardjan http://masindi.tripod.com Email: indi@mem.net