Introduction

Film 2011 intends to expand its business by establishing its own chain of cinemas in the UK. To this end, the company has conducted a market research to assess the performance of other key players in this sector. These include three cinema chains A, B and C, which control a significant proportion of the market share in the UK entertainment industry. Each of the three cinema chains employ unique business strategies in a bid to achieve sustainable competitive advantage over their peers. For instance, for promotional purposes, Chain A, unlike the other two chains, leverages cinema passes, which are valid for either 4 or 8 weeks. From the market research, which involved a random sample of 128 cinemas throughout the UK, the directors of the company found out that the average monthly sales of the cinemas is £285,000

Cinema attendance is influenced by several factors, which can be categorized as economic, socio-cultural or environmental. Economic factors such as income, ticket prices and the price of other related goods have a significant influence on the demand for cinema attendance. Several studies have shown that `cultural goods and other services such as video, TV programs, satellite, opera, and theatres are substitutes for cinema (Kim, 2009; Cameron, 2005; Dewenter & Westermann, 2005; Collins & Hand, 2005). As such, the availability of these factors has a negative influence on cinema attendance. Specifically, if the costs incurred in enjoying these services is less compared to the cost of attending cinemas then most people will opt for the former. Other costs incurred in attending cinemas include food, snacks and transportation. If these side cost increase, the demand for cinema attendance declines.

Social-cultural factors such as age, gender, employment status and level of education also have a great bearing on cinema attendance (Kim, 2009; Yamamura, 2008; Redondo & Holbrook, 2010). Collins & Hand (2005), argued that age is inversely proportional to the demand for cinema attendance. This implies that elderly people are less likely to attend the cinema compared to young people. Two Spanish researchers, Redondo & Holbrook (2010), further posited than men go to the movies more frequently than women. Rahimi, et al. (2014) later observed that parents with greater social and occupational prestige patronize the cinema more frequently than parents with less occupational prestige. In essence, an individual’s occupation influences their level of income, which in turn influences their social status. While the cinema is not reserved for the elite in the society, it is also not limited the low end market. People in different social classes therefore attend the cinema at different rates. Other than that, the fact that one’s occupation influences the amount of free time at their disposal suggests that one’s employment also determine their demand for cinema attendance (Azma, 2007). Apart from the fact that one’s level of education influences their literacy, Rahimi, et al. (2014) also observed that socially educated individual have the capacity to comprehend economic, political and social issues better than illiterate individuals and as such, they are likely to attend the cinema than the latter. Other socio-cultural factors that influence cinema attendance include media, values beliefs and habits.

Finally, the environmental factors that influence cinema attendance include the facilities available in cinemas and the level of community development. Walls (2005) and Yamamura (2009) showed that cinemas with better facilities generally attract more attendants than cinemas in deplorable condition. The level of community development determine whether a particular area of region can be categorized as rural or urban. In a bid to model the appeal of movie features to demographic segments of theatrical demand, Redondo & Holbrook (2010) established that the availability of more recreational facilities in urban areas such as cinemas and academies, encouraged individuals living in urban areas to attend the cinema more frequently than individuals living in rural areas.

Methodology

As aforementioned, the information was collected from a random sample of 128 cinemas and stored in Minitab. This information was obtained from the cinema managers who were asked to fill out questionnaires that were used to collect data on several variables. The first variable is the name of the cinema chain, which for confidentiality reasons are denoted as either A, B or C. The second variable is the regional location of the cinema. Because the data was collected randomly from three cinema chains in the UK, it is divided into three regions including England, Scotland and Wales. Apart from the regional location, the information also indicates whether the cinema is located in town or out of town. Another variable is the size of the cinema. There are three categories of cinema sizes, small medium and large. The sitting capacity for small cinemas is less than 400, the capacity for medium cinemas ranges between 400 and 1000 and the capacity of large cinemas is more than 1000. The questionnaires were also used to collect information about the gender of the mangers, the monthly rent paid, the distance of the cinema away from the high streets, monthly advertising expenditure, monthly weekend sales and monthly weekday sales.

The data collected from the field will mainly be analysed using descriptive and inferential statistics. Descriptive statistics include measures of central tendency, and measures of dispersion (Black, 2012). Measures of central tendency will provide a bird’s eye view of the entire data that is in most cases not intelligible (Bradley, 2007). These statistics will enable the research team to understand the true significance of a large aggregate of facts (Lee, et al., 2013). For instance, while it is practically impossible to remember the weekend sales for all the cinemas under observation, the average weekend sales for all the cinemas or a particular cinema chain can be used as a representative for all the sales. These measures are particularly useful for making comparisons. For instance, the average sales for the three cinema chains will be used to determine the most profitable cinema chain. The measures of central tendency that will be use to conduct this analysis include, the arithmetic mean, median and mode. On the other hand, the measures of dispersion include the standard deviation and variance. Finally, the inferential statistics include regression analysis, ANOVA, and t-test. These tools will tools will be leveraged to make inferences about the relationships between the different variables.

Statistical Analysis

Relationship Between Day of the Week and Profitability

Table 1: Descriptive statistics for weekend and weekday sales

It was hypothesized that the average monthly weekend sales were greater than the average monthly weekday sales for the three cinema chains. From the descriptive statistics below it is evident that the average monthly weekend sales is almost double the average monthly weekday sales. Nonetheless, the standard deviation for the monthly weekend sales is greater than that of the monthly weekday sales. This suggests that there is a greater variation in weekend sales compared to weekday sales, which could imply that the difference in the average sales is not statistically significant.

Variable   N N*   Mean SE Mean StDev Minimum Median Maximum

WEEKEND   128   0 157020     7400 83717   10540 143539   398456

WEEKDAY   128   0   90372     5081 57488     3457   85595   287345

 

A t-test is carried out to determine beyond reasonable doubt that the monthly weekend sales are significantly greater than the monthly weekday sales. A paired t-test is selected because the main aim of the analysis was to establish the difference between the same sample subjected to different conditions, in this case weekends and weekdays.

H₀ : On average, monthly weekend sales are not greater than monthly weekday sales

H_a : On average, monthly weekend sales are greater than monthly weekday sales

Paired T for WEEKEND – WEEKDAY

 

N   Mean StDev SE Mean

WEEKEND     128 157020 83717     7400

WEEKDAY     128   90372 57488     5081

Difference 128   66648 29922     2645

 

 

95% lower bound for mean difference: 62266

T-Test of mean difference = 0 (vs > 0): T-Value = 25.20 P-Value = 0.000

 

Assuming that the populations are normally distributed and the population variances are equal, the p value for the test is 0.000 which is lower than the significance interval of 0.05. This implies that the null hypothesis should be rejected and as such, it is safe to conclude that there is sufficient evidence to suggest that monthly weekend sales are significantly greater than monthly weekday sales

 

 

 

 

Relationship between Cinema Chains and Profitability

Table 2: Descriptive statistics for weekend and weekday sales based on Cinema Chains

Variable CHAIN   N N*   Mean SE Mean StDev Minimum Median Maximum

WEEKEND   A     42   0 187234   14715 95361   60859 174558   398456

B     44   0 154427   10429 69180   41330 141514   295304

C     42   0 129523   11831 76676   10540 123908   323279

 

WEEKDAY   A     42   0 108537   10343 67028   22400   99598   287345

B     44   0   90598     7310 48490   12930   85761   194345

C     42   0   71970     7858 50926     3457   64523   200120

 

From the foregoing it can be concluded that Cinema Chain A is the market leader of the three market chains because it generated higher monthly average sales for both weekdays and weekends. Being the leader, the company should identify the strategies that chain A adopted in order to achieve its market position.

Relationship between Region and Profitability

It is evident that England registered higher sales for both weekdays and weekends followed by Scotland and finally Wales. This suggests that the cinema business is more lucrative in England compared to the other regions. However, it should also be noted that rental charges in England are slightly higher than those in both Scotland and whales.

Table 3: Descriptive statistics for weekend and weekday sales based on Region

Variable REGION   N N*   Mean SE Mean StDev Minimum Median Maximum

WEEKEND England 50   0 182135   12647 89425   10540 187447   398456

Scotland 43   0 155585   12514 82061   19568 143500   328659

Wales   35   0 122903   10964 64863   10647 116463   273559

 

WEEKDAY England 50   0 107355     8727 61706     3558 103823   287345

Scotland 43   0   90272     8741 57317     5285   85760   220300

Wales   35   0   66232     7122 42132     3457   63504   167400

 

Table 4: Descriptive statistics for rent based on Region

Variable REGION   N N*   Mean SE Mean StDev Minimum Median Maximum

RENT     England 50   0 21.380   0.849 6.006   10.000 20.500   32.000

Scotland 43   0 20.442   0.835 5.474   12.000 21.000   31.000

Wales   35   0   18.66     1.17   6.92     9.00   18.00   31.00

 

Relationship between Location and Profitability

The descriptive statistics below suggest that cinemas located in towns are more profitable than cinemas located out of town. This is evidenced by the fact that the average monthly sales for cinemas located in towns are significantly higher than the average monthly sales for cinemas located out of town for both weekdays and weekends. The standard deviation is more or less the same in both cases so the variation of sales for the cinemas in the two locations is similar.

Table 5: Descriptive statistics for weekend and weekday sales in terms of location

Variable LOCATION   N N*   Mean SE Mean StDev Minimum Median Maximum

WEEKEND In Town     69   0 165473   10381 86233   19568 156830   398456

Out of Town 59   0 147134   10451 80272   10540 124357   328659

 

WEEKDAY In Town     69   0   93532     6787 56373     5285   89300   226440

Out of Town 59   0   86676     7686 59034     3457   65400   287345

 

Relationship between Gender of Manager and Profitability

The statistics below suggest that male managers are more efficient than female managers. This is implied by the fact that male managers recorded significantly higher sales for both weekdays and weekends. Worse still, the standard deviation for female managers is higher than that of male managers for weekends. This suggests that the sales achieved by female managers exhibited a higher variation than sales achieved by male managers. While the converse is true for weekdays, male managers proved to be more efficient than female managers because they could capitalize on weekends (which are characterized by higher sales) better than female managers. Notwithstanding, the best performed manager was a woman judging from the maximum weekend sales. Unfortunately, the worst performed managers were also women and by very huge margins for both weekdays and weekends.

Table 6: Descriptive statistics for weekend and weekday sales in terms of Gender

Variable GENDER   N N*   Mean SE Mean StDev Minimum Median Maximum

WEEKEND   Male   96   0 170578     8203 80370   38780 156370   350632

Female 32   0 116345   14406 81490   10540 101013   398456

 

WEEKDAY   Male   96   0 100184     5818 57006   10644   92773   287345

Female 32   0   60935     8639 48870     3457   58850   226440

 

Relationship between Cinema size and Profitability

The statistics below suggest that profitability is directly proportional to cinema size. This is because both large and medium cinemas outperformed small cinemas. It should however be noted that the risk inherent in the returns for both small and large cinemas is higher compared to the risk inherent in medium sized cinemas because they both exhibited higher standard deviations. As such, the company should consider both the risk and the return when deciding on the size of the cinema to invest in. Surprisingly, the smallest cinemas with the highest sales outperformed the medium sized cinemas with the highest sales. From this observation, the fact that small cinemas can outperform medium sized cinemas should not be overruled albeit the fact that their returns are characterized by a higher risk.

Table 1: Descriptive statistics for weekend and weekday sales in terms of cinema size

Variable SIZE   N N*   Mean SE Mean StDev Minimum Median Maximum

WEEKEND Small 29   0   74648   11212 60376   10540   62159   268584

Medium 57   0 131668     4953 37395   54259 124357   213859

Large 42   0 248302     8566 55511   147175 235208   398456

 

WEEKDAY Small 29   0   33885     6894 37124     3457   24300   167845

Medium 57   0   73239     3515 26534   19300   67234   156734

Large 42   0 152626     6361 41222   89450 142773   287345

 

 

Influence of Rent, Distance from high streets and Advertising on profitability

From the regression analysis below, it is evident that weekend sales are directly proportional to the rental charge, distance from high streets and the cost incurred in advertising. However, the relationship between weekend sales and the distance from high streets is not statistically significant. The coefficient of determination suggests that 73.53% of the changes in weekend sales can be attributed to the changes in the three variables (rental charge, distance from high streets and the cost of advertising). There is also a direct relationship between weekday sales and the three variables and like the first scenario, the relationship between weekday sales and the distance from high streets is not statistically significant. Moreover, the coefficient of determination suggest that 73.59% of the changes in weekday sales can be attributed to the changes in the three variables.

The direct relationship between profitability and the two variables, rent and advertising can be explained by the fact that cinema halls that cost more to rent are probably located in prime locations and have better facilities. Moreover, advertising helps to enhance market penetration, which in turn contributes to higher sales volume.

Table 4: Regression Analysis for Weekend Sales

Analysis of Variance

 

Source       DF       Adj SS       Adj MS F-Value P-Value

Regression   3 6.54463E+11 2.18154E+11   114.81   0.000

RENT       1   9023290745   9023290745     4.75   0.031

DISTANCE   1   1191101773   1191101773     0.63   0.430

ADVERT     1 5.51296E+11 5.51296E+11   290.13   0.000

Error       124 2.35619E+11   1900154567

Total       127 8.90082E+11

 

 

Model Summary

 

S   R-sq R-sq(adj) R-sq(pred)

43590.8 73.53%     72.89%     71.82%

 

 

Coefficients

 

Term         Coef SE Coef T-Value P-Value   VIF

Constant -131794   32045   -4.11   0.000

RENT         2426     1113     2.18   0.031 3.14

DISTANCE     3263     4121     0.79   0.430 3.02

ADVERT     101.30     5.95   17.03   0.000 1.07

 

 

Regression Equation

 

 

 

Fits and Diagnostics for Unusual Observations

 

Obs WEEKEND     Fit   Resid Std Resid

19   295304 208074   87230       2.02 R

21   268584 175407   93177       2.18 R

22   398456 271464   126992       2.97 R

52   29780 121846   -92066     -2.12 R

58   163456 264617 -101161     -2.35 R

70   197455 283267   -85812     -2.00 R

97   38780 151322 -112542     -2.61 R

 

R Large residual

 

 

 

 

Table 5: Regression Analysis for weekday sales

Analysis of Variance

 

Source       DF       Adj SS       Adj MS F-Value P-Value

Regression   3 3.08884E+11 1.02961E+11   115.18   0.000

RENT       1   3504033521   3504033521     3.92   0.050

DISTANCE   1   972113727   972113727     1.09   0.299

ADVERT     1 2.66826E+11 2.66826E+11   298.50   0.000

Error       124 1.10841E+11   893880121

Total       127 4.19725E+11

 

 

Model Summary

 

S   R-sq R-sq(adj) R-sq(pred)

29897.8 73.59%     72.95%     71.92%

 

 

Coefficients

 

Term         Coef SE Coef T-Value P-Value   VIF

Constant -108638   21979   -4.94   0.000

RENT         1512     764     1.98   0.050 3.14

DISTANCE     2948     2827     1.04   0.299 3.02

ADVERT     70.48     4.08   17.28   0.000 1.07

 

 

Regression Equation

 

 

 

Fits and Diagnostics for Unusual Observations

 

Obs WEEKDAY     Fit   Resid Std Resid

19   194345 124073   70272       2.37 R

21   167845   99789   68056       2.33 R

22   226440 167307   59133       2.02 R

40   154235   92937   61298       2.07 R

49   287345 185915 101430       3.46 R

52     5285   66861 -61576     -2.07 R

58   99345 163938 -64593     -2.19 R

70   96245 177259 -81014     -2.76 R

87   220300 161801   58499       2.00 R

97   10644   83907 -73263     -2.48 R

104   100379 163182 -62803     -2.13 R

 

R Large residual

 

 

 

 

Conclusion and Recommendation

From the foregoing, the company should adopt a business strategy similar to that employed by Chain A because it controls the majority market share among the three cinema chains. It should also focus on showing movies during weekends because this is the time when cinema attendance is highest. Additionally, it should consider opening a medium sized cinema in England because while the region is characterised by the highest demand for cinema attendance, there is a very low risk inherent in returns for medium sized cinemas. Other than that, the company should open the cinema in town and hire a male manager. The company should also look for a cinema hall with good facilities regardless of the rental charge and invest in advertising campaigns to enhance market penetration.

 

 

References

Anderson, D. R. et al., 2010. Statistics for business and economics. 2 ed. London : Cengage Learning.

Azma, F., 2007. Investigating how to increase willingness of audiences to the cinema, Tehran: Islamic Ministry of Culture and Guidance.

Black, K., 2012. Business statistics : for contemporary decision making. 7 ed. Hoboken, NJ: Wiley.

Bradley, T., 2007. Essential statistics for economics, business and management. Chichester, England: John Wiley & Sons.

Cameron, S., 2005. Demand for Cinema in the United Kingdom. Journal of Cultural Economics , 14(1), pp. 35-47.

Collins, A. & Hand, C., 2005. Analyzing movie going demand: An individual level cross-sectional approach. Managerial and Decision Economics, 26(5), pp. 319-330.

Dewenter, R. & Westermann, M., 2005. Cinema Demand in Germany. Journal of Cultural Economics, 29(3), pp. 213-231.

Kim, S., 2009. Cinema demand in Korea. Journal of Media Econimics , 22(1), pp. 36-56.

Lee, C. F., Lee, J. C. & Lee, A. C., 2013. Statistics for business and financial economics. 3 ed. New York : Springer.

Lee, J. C., River Edge, N.J.. Business and financial statistics using Minitab 12 and Microsoft Excel 97. 2000: World Scientific.

Lesik, S., 2010. Applied Statistical Inference with MINITAB. New York : CRC Press.

Powers, G., 2013. Cambridge HSC Mathematics General 1. Melbourne: Cambridge University Press.

Rahimi, A., Mousai, M., Azad, N. & Syedaliakbar, S. M., 2014. Impact of economic, cultural, social, individual, and environmental factors on demand for cinema: Case study of Tehran. African Journal of Business Management , 8(13), pp. 480-494.

Redondo, I. & Holbrook, M. B., 2010. Modelling the appeal of movie features to demographic segments of theatrical demand. Journal of Cultural Economics, pp. 1-17.

Sleeper, A. D., 2012. Minitab demystified. New York : McGraw-Hill.

Sweeney, D. J., Anderson, D. R. & Williams, T. A., 2011. Fundamentals of business statistics. 6 ed. London : Cengage Learning.

Yamamura, E. J., 2008. Sicio-Economic Effects on Increased Cinema Attendance: The case of Japan. Journal of Socio-Economics, 37(6), pp. 2546-2555.