Retail & Marketing Analytics

Effectiveness of Marketing Activities at Local Level

A Spatial Panel Autoregressive Model

Andreas Georgopoulos CID: 01281486 Abstract

Abstract

At this project the effectiveness of different marketing acitivities and communication campaigns, of a fast-food retail chain at restaurant-level, on increasing daily net sales and total receipts count is assessed. Daily data is used and only fully operated restaurants from 2015-01-01 to 2016-12-31 are examined, resulting in a “same-store” analysis. Additional daily data that migh explain a lot of the response variables’ variation, such as weather data, sport events bank holidays and weekends, is also acquired. A Spatial Panel Autoregressive Model with Fixed Effects that accounts for spatial dependencies between restaurants is proposed. Each advertising activity is modeled separately as an adstock variable for each Italian Province, capturing the provincial carryover effect of alternative media on consumers’ decisions. With the adstock variables defined at a Province- level, the Advertising Elasticities of each Province of the statistically and economically significant marketing activities, e.g. GRP TV and Euro Spent in other Offline Campaigns, are computed, underlining the effectiveness of different media in the short and long run. The proposed model provides the potential of capturing the effect of a change in a marketing activity on net sales and/or foot traffic of specific “target” restaurants. Therefore, a focused budget allocation can be implemented in order to improve individual performance of specific restaurants based on their location (Province).

ii Table of Contents

Table of Contents

1 Introduction 4 2 Spatial Panel Model 5 2.1 Spatial Panel Autoregressive Model ...... 5 2.2 Spatial Weight Matrix ...... 6 2.3 Spatial Autocorrelation ...... 7 3 Explanatory Variables 8 3.1 Marketing Activities ...... 8 3.2 Weather Data ...... 9 3.3 Additional Explanatory Variables ...... 9 4 Model Estimation 11 4.1 Regression Estimation ...... 11 4.2 Advertising Elasticities ...... 13 5 Recommendations 15 References 16 Appendices 17 A. Fixed Effects ...... 17 B. Advertising Elasticities per Province ...... 19

iii 1. Introduction

1 Introduction

This project is considered a sequential analysis of the (Georgopoulos A., 2017) project, where the effectiveness of different media on net sales and foot traffic at an aggregated country-level was examined. At this project a restaurant-level analysis on daily data takes place. Therefore, a panel dataset with restaurants as cross-sectional that are fully operated for the entire time period from 2015-01-01 to 2016-12-31 is generated. In Figure 1, a data model that underlies the data preprocessing and aggregation procedures of the provided and newly constructed datasets, is presented. The final panel dataset, consists of � = 505 cross-sectional units (restaurants) with recorded information for � = 731 days, resulting in a total number of 369,155 observations.

Figure 1. Construction of Final Panel Dataset

4 2. Spatial Panel Model Spatial Panel Autoregressive Model

2 Spatial Panel Model

2.1 Spatial Panel Autoregressive Model

A Spatial Autoregressive Model with Fixed Effects (Spatial Error Model, SEM) controls for all space-specific time-invariant variables. More specifically, this model takes into consideration spatial effects through the error structure (LeSage, 2008). The fixed effects “absorb the effects of omitted variables that differ between cross-sectional units but are constant over time”, the absence of which cause bias in the estimated parameters (Elhorst, 2014). When specifying for such spatial dependencies between units, a SAR (SEM) model includes a spatial autoregressive process in the error term, known as the spatial autocorrelated coefficient or the spatial error (Elhorst, 2014) (Viton, 2010). A Spatial Panel Data Autoregressive Model with Fixed Effects of the previously mentioned panel dataset with � = 505 cross-sectional units (restaurants) and � = 731 time periods, can be formulated as following:

�!,! = �!,! ∙ � + �! + �!,!, !

�!,! = � ∙ �!,! ∙ �!,! + �!,!, !!! where: − � = (1, … ,505). Cross-sectional unit index for each restaurant of the retail chain. − � = (2015-01-01, … , 2016-12-31). Time period for years 2015 and 2016. − �!,!: observation on response variable, either net sales or receipt count, for restaurant � at time �. − �!,!: explanatory variable of restaurant � at time �. − �!": element of the Spatial Weight Matrix underlying if restaurants �, � are neighbors (spatial location of each restaurant). − �!,!: spatially autocorrelated error term. ! − �!,! ∼ (0, � ): independent and normally distributed error term equation restaurant � at time �. − �!: spatial fixed effects for each cross-sectional restaurant unit − �: spatial autocorrelated coefficient (spatial error) � �: vector of fixed but unknown parameters.

5 2. Spatial Panel Model Spatial Weight Matrix

2.2 Spatial Weight Matrix

The spatial dependencies between the cross-sectional units (restaurants) have to be quantified into a Spatial Weight Matrix �, in order to indicate the neighboring relationships between all restaurants of the retail chain. The Spatial Weight Matrix is an � x � matrix (N: total number of restaurants) where: 1, if restaurants �, � are neighbors � = !,! 0, otherwise In order to define when two restaurants to be considered as “neighbors” a distance- based contiguity approach is implemented (Viton, 2010, Bivand, 2016). A threshold distance �!"# (bandwidth) is introduced in order to define the neighboring relationships between restaurants. More specifically, two restaurants are “neighbors” if the distance between their spatial locations is less or equal to the threshold distance, and thus:

1, �!,! ≤ �!"# �!,! = 0, �!,! > �!"# Since the location of each store is provided by latitude and longitude, the distance between all restaurants in space can be calculated. The Harvesine distance between restaurants in km is calculated. After computing the neighboring relationships between all restaurants, the Spatial Weight Matrix is “row-standardised” to remove any scale dependencies, resulting in a row-stochastic Weight Matrix (LeSage, 2008). In order to observe the “optimal” radius beyond which there is no spatial influence between restaurants, different weight matrices are generated with the threshold distance ranging from 1 to 10 km. The Spatial Panel Autoregressive model with Fixed Effects is estimated with the different Spatial Weight Matrices, and the regression Standard Error (SE) is observed. The Spatial Weight Matrix that resulted in the minimum SE corresponds to a threshold distance of 1km (Figure 2). Therefore, the final row-stochastic Spatial Weight Matrix with a threshold distance of 1km is computed in order to depict the spatial dependencies between the restaurants of the retail chain.

Figure 2. Regression Standard Error for different Threshold Distances (km)

6 2. Spatial Panel Model Spatial Autocorrelation

2.3 Spatial Autocorrelation

After defining the spatial dependencies between the restaurants, the panel data is tested for spatial autocorrelation through a series of Lagrange Multiplier (LM) tests (Breusch and Pagan, 1980, Baltagi et al., 2003). The LM2 Marginal Test assumes that random individual effects do not exist, whereas the Conidtional LM test assumes a possible existence (Baltagi et al., 2003). From the results shown in Table 1, someone can observe that both tests indicate the existence of spatial autocorrelation in the panel data model. Therefore, a spatial panel data model is needed, as the one proposed in this project, to account for spatial dependencies and control for all space-specific and time-invariant variables that result in biased estimations.

Baltagi, Song and Koh LM2 Marginal Test Dependent variable:

Total Net Sales Total Receipts Count

LM2 116.2 156.28 p-value < 2.2e-16 < 2.2e-16 Alternative hypothesis: Spatial autocorrelation

Baltagi, Song and Koh LM*-lambda conditional LM test

Dependent variable: Total Net Sales Total Receipts Count LM2 105.86 100.34 p-value < 2.2e-16 < 2.2e-16 Alternative hypothesis: Spatial autocorrelation

Table 1. Lagrange Multiplier Tests for Spatial Autocorrelation

7 3. Explanatory Variables Marketing Activities

3 Explanatory Variables

3.1 Marketing Activities

Different communication campaigns have a different impact on consumers memory rate and thus on their final decisions. However, the effect of the same marketing activity on consumers’ behavior might vary with respect to local preferences and habits. In order to capture the regional carryover effect of alternative media on consumers’ decisions, each marketing activity is modeled separately at a Province-level. Therefore, for each Province and response variable a different adstock variable is generated in order to capture the provincial carryover effect of alternative communication campaigns on net sales and total number of receipts count, as following: �! ∗ �������! + ��� ! ! !,!!! ! �������!,! = atan ( ! ) �! where: − � = {Agrigento,Imperia, … ,Brescia, Napoli, Nuoro}. Factor vector of each of the 100 Italian Provinces that stores are operating in whole time period. − � = (2015-01-01, … , 2016-12-31). Time period for years 2015 and 2016. − � = {Net Sales , Total Receipts Count}. Response variables, the effect of media upon which is expected to be estimated. ! ! − �! , �! : Adstock parameters to be determined per Province and response variable. − ���! = {GRP TV, GRP Radio, Euro spent on Online Campaigns, Euro spent on other Offline campaigns}. Alternative marketing activities that take place in each time period �.

! ! The parameters (�! , �! ) of each adstock variable are determined via a grid search procedure, where the final values are chosen based on the respective RMSE of each regression model as well as on the significance of each marketing activity as an explanatory variable. Each adstock variable is assigned each store based on the latter’s Province location. The above mentioned adstock modeling technique, failed to capture the effect of Radio GRP and Euro spent in Online campaigns, since they occur in scarce time periods and with a limited marketing budget. Therefore, a linear form with no carryover effects is chosen to model the communication campaigns of Radio GRP and Euro spent in Online campaigns. In Figure 3 the newly constructed adstock variables for TV GRP in “Agrigento” and “Brescia” for Net Sales as dependent variable, with corresponding adstock parameters of

8 3. Explanatory Variables Weather Data

!"# !"#$% !"# !"#$% !"# !"#$% !"# !"#$% �!"#$"%&'( = 0.3, �!"#$"%&'( = 271, �!"#$%&' = 0.15, �!"#$%&' = 111 respectively, are presented.

Figure 3. Adstock variable of TV GRPS in “Agrigento” and “Brescia” for Net Sales

3.2 Weather Data

Weather conditions, such as average temperature, rain, snow and others, affect consumers’ decisions on visiting a fast-food retail store and might explain a lot of variation on each store’s daily net sales and customer foot traffic. Since the analysis that takes place on this project occur on a daily-store level for 2015-2016, daily weather data for the location of each store for the whole time horizon is needed. Historical daily weather data for each Italian Province is collected from the international weather e-database (http://www.wunderground.com) at a Province level. Based on the Province of each store, different nearby weather stations are identified that provide daily weather records, until complete weather data is collected for each of the 731 days in 2015 and 2016. Average temperature as well as weather events (i.e. rain, snow, etc.) are selected to be included as explanatory variables. Weather events are transformed into a binary variable indicating the occurrence of an extreme weather event, e.g. rain, thunderstorm or snow, at each day per province. Each weather variable is assigned to each store based on the latter’s Province location.

3.3 Additional Explanatory Variables

A consumer’s decision on visiting a fast-food retail restaurant is undeniably influenced by additional exogenous conditions apart from his/her personal intention. For instance, if the corresponding day is a Bank Holiday or a Weekend, consumers are most likely to decide to go out and probably visit a fast-food restaurant. Therefore, in order to capture the effect of alternative advertising media on consumer behavior, additional explanatory variables of Bank Holidays, Weekends (Friday, Saturday and Sunday) and Sporting Events are investigated as shown in Figure 4. Holidays and Weekends appear to explain a lot of variation on restaurant’s net sales, whereas Sporting Events rare but might be a significant factor for both net sales and foot traffic. Last but not least, seasonality is taken into account and more specifically the Month that each record takes place in order to capture the effect of each month on each restaurant’s net sales and total receipts count.

9 3. Explanatory Variables Additional Explanatory Variables

Figure 4. Bank Holidays, Weekend and Sport Events on Total Net Sales (Georgopoulos A., 2017)

10 4. Model Estimation Regression Estimation

4 Model Estimation

4.1 Regression Estimation

The parameters of the Spatial Autoregressive Model are estimated through an iterative concentrated maximum likelihood approach, where iterations are continued until Maximum Likelihood (ML) and Generalised Least Square (GLS) estimations converge under a pre- defined threshold convergence criterion (Millo and Piras, 2012). The concentrated log- likelihood function that is maximized with respect to the spatial autocorrelated coefficient �: � ∙ � ���� = − ∙ ln � � ! ∙ � � + � ∙ ln |� − � ∙ �| 2 ! where:

− � � = � − � �!⨂� ∙ � − [� − �(�!⨂�) ∙ �] ∙ � ! !! ! − � = ( � − � �!⨂� ∙ � ∙ � − � �!⨂� ∙ � ) ∙ � − � �!⨂� ∙ � ∙ [� − � �!⨂� ∙ �]

− �: � ∙ �, 1 vector of response variable �!,!, with � = 505, � = 731

− �: � ∙ �, � matrix of � = 21 independent variables �!,! − �: the Spatial Weight Matrix

The cross-sectional fixed effects are omitted from the regression equation by demeaning the dependent and independent variables � and � (Elhorst, 2014). Once the regression equation is estimated, they can be recovered as following: !!!"# 1 � = (� − � ∙ �) , ∀ restaurant � ! 731 !,! !,! !!! The regression results of the Spatial Autoregressive Models with Fixed Effects for net sales and total receipts count are presented in Table 2 (the cross-sectional fixed effects are depicted in Table 5, Appendix A). The estimated spatial autocorrelated coefficient � appears to be statisticaly significant at 1% significance level underlying the importance of spatial dependencies in explaining the variation of the corresponding response variables. In other words, 27.3% and 24.9% of the variance in net sales and foot traffic respectively, is due to differences across individual restaurant spatial locations.

11 4. Model Estimation Regression Estimation

Regression results: Spatial panel fixed effects error model Dependent variable:

Total Net Sales Total Receipts Count

Spatial error (rho) 0.273*** 0.249*** Average Temperature 0.516 1.060*** Extreme Weather Events 66.807*** -1.138 Bank Holidays 1351.527*** 74.803*** Weekend 2168.923*** 208.324*** Month.February -96.5883*** -3.426 . Month.March 95.048*** 8.643*** Month.April 137.036*** 27.106*** Month.May -72.057*** -12.658*** Month.June 55.853* -12.737*** Month.July 234.431*** 13.022*** Month.August 434.766*** 18.972*** Month.September 354.618*** 32.361*** Month.October 228.498*** 1.740 Month.November -23.172 -23.668*** Month.December 351.258*** 10.786*** Sport Event Day -188.423*** -38.223*** AAdstock of GRPS TV 244.326*** 28.498*** GRPS Radio -2.790*** -0.237*** Euro spent in Online -0.0053*** -0.0002*** campaigns AAdstock of Euro spent in 317.514*** 44.314** other Offline campaigns Constant 2,188,230.000*** 316,389.800*** Restaurants 505 505 Time period (days) 731 731 Total Observations 369,155 369,155 pseudo-R2 0.709 0.799 Note: *p**p***p<0.01

Table 2. Regression Estimation Results for Net Sales and Total Receipts Count As far as the effect of each marketing activity on daily net sales and receipts count per restaurant, the adstock variables of GRP TV and Euros Spent in other Offline Campaigns are appear to be both statistical and economically significant. Moreover, the GRP Radio and Euros Spent in Online Campaigns appear to have a negative impact on the response variables, however this impact is economically insignificant and therefore those two activities are considered ineffective in increasing the daily net sales and foot traffic of stores that operate in entire time horizon. The effectiveness and individual impact on the statistically and economically significant advertising activities is captured through an Advertising Elasticity Analysis.

12 4. Model Estimation Advertising Elasticities

4.2 Advertising Elasticities

Having estimated each Spatial Panel Error Model with Fixed Effects, the Advertising Elasticities of each Province of the statistically and economically significant marketing activities, e.g. GRP TV and Euro Spent in other Offline Campaigns, are computed. Advertising Elasticities underline the effectiveness of different communication campaigns in the short and long run. Short-term elasticities underline the concurrent effect of marketing activities on the response variables, whereas long-term elasticities take into consideration the additional carryover effect of a marketing activity due to consumer’s memory rate. Furthermore, Advertising Elasticities provide a guideline for future advertising budget allocation for the client on a restaurant level taking into consideration location dependencies and provincial memory rates. Given limited alternative advertising media and marketing budget, in advertising campaigns with higher elasticities a higher budget may be allocated with respect to the client’s goals at a high-level decision making. For each Province, both short-term and long-term Advertising Elasticities (of GRP TV and Euro spent in other Offline Campaigns) are estimated with respect to each response variable of net sales or total receipts count. Since no close forms are available for advertising activities modeled by an Adstock variable, the Advertising Elasticities are computed through a simulated procedure based on estimated SEM with Fixed Effects Model. More specifically, long-term Advertising Elasticities are computed by increasing each marketing activity by 1% on the first day (change of total sales/traffic), whereas short-term Advertising Elasticities by increasing the corresponding advertising variable by 1% per day (change in average daily sales/traffic). The effectiveness of this model can be summarized to the rationale of capturing the effect of each marketing activity on the disaggregate restaurant level. That is, a focused budget allocation can be implemented according to the client’s intentions to improve individual performance of specific stores, due to the model’s possibility of capturing the effect of a change in a marketing activity (country level) on net sales or foot traffic of specific restaurants (restaurant-by-restaurant level). For instance, restaurant “Brescia Freccia Rossa” located in “Brescia” has corresponding Advertising Elasticities shown in Table 3. By increasing 1% the marketing activity of GRP TV it is expected to increase the daily net sales of “Brescia Freccia Rossa” restaurant by 0.59 € in the short run and by 0.701 €, whereas the daily foot traffic is expected to increase by 0.074 and 0.083 respectively. Response Advertising Advertising Elasticity (€ / people) Variable Activity Short 0.592 TV GRP Long 0.701 Net Sales Short 0.604 Offline Campaigns Long 0.825 Short 0.074 TV GRP Long 0.083 Receipts Count Short 0.078 Offline Campaigns Long 0.115

Table 3. Advertising Elasticities for restaurants located in “Brescia” The computed Advertising Elasticities for each restaurant at a specific Province (Appendix B), provide also information about average Advertising Elasticities on an aggregate level. From the average Advertising Elasticities for each restaurant (Table 4), someone can compute the average Advertising Elasticity of a marketing activity at the country

13 4. Model Estimation Advertising Elasticities level. For instance, a 1% increase on TV GRP, is expected to increase total net sales in the short run at country level by 241€ on average (the average GRP TV Elasticity on the short run for each restaurant is 0.479 and the number of stores operating in the entire time horizon in 2015-2016 are 505). Those results match the ones presented at the aggregate country-level analysis (Georgopoulos A., 2017) in magnitude, but they are statistically more accurate since they are estimated by controlling for differences in different restaurants. Response Advertising Advertising Elasticity (€ / people) Variable Activity Short 0.479 TV GRP Long 0.569 Net Sales Short 0.401 Offline Campaigns Long 0.648 Short 0.057 TV GRP Long 0.065 Receipts Count Short 0.062 Offline Campaigns Long 0.096

Table 4. Average Advertising Elasticities for each restaurant

14 5. Recommendations

5 Recommendations

For the stores that operate in the entire time period, the marketing activities of TV and other Offline campaigns are proven to be the most statistically and economically significant and effective. Therefore, for improving the performance of such restaurants, the marketing budget is highly recommended to be allocated on those two communication campaigns. More specifically, TV is appeared to be the most effective advertising activity in increasing net sales in the short run. Therefore, a continued investment should be secured. Since the carryover effect of TV activity is on average smaller than the one of other Offline Campaigns, advertisements should air frequently, and multiple slots should be purchased. On the other hand, other Offline campaigns are proven to be more effecient that TV in attracting foot traffic in the short and long run. That is, spending on offline campaigns could be kept on the same level if budget is not a primary concern. As far as Radio and Online campaigns is conserned, they appear to have a limited effect on both sales and traffic in general. It is thus advised to lower spending on Radio and shift the investment towards more effective campaigns such as TV and other Offline campaigns. Online campaigns should either occur more frequently or have a higher allocated budget in order to depict their effect on the restaurants performance statistically and economically. Moreover, a focused budget allocation can also be implemented in order to improve individual performance of specific restaurants, due to the model’s possibility of capturing the effect of a change in a marketing activity on net sales or foot traffic of the “target” restaurant. With the adstock parameters known for each Italian Province, the client has the opportunity to take advantage of local memory characteristics and generate marketing strategies that will minimise the marketing budget and simultaneously maximise their impact on consumers’ decisions. Furthermore, the lowest average performance of individual restaurants is examined in months February, May and June. For those months, it is highly recommended to increase advertising spending with a high short elasticity in increasing sales, e.g. TV. In April although a high customer foot traffic is observed, a relative low number of net sales take place. That is, it is suggested to focus advertising in increasing sales rather than foot traffic in April. In addition, significantly more sales are achieved on weekends rather than weekdays, and thus more advertisements should be aired on weekdays combined with retaurant promotional events for weekdays. Last but not least, when a major sport event takes place in Italy, both foot traffic and net sales are significantly decreased. For such days, additional delivery services with corresponding focused advertising activities in TV and other Offline campaigns might balance out the loss sales due to sport events.

15 References

References

BALTAGI, B. H., SONG, S. H. & KOH, W. 2003. Testing panel data regression models with spatial error correlation. Journal of econometrics, 117, 123-150. BIVAND, R. 2016. Creating neighbours. BREUSCH, T. S. & PAGAN, A. R. 1980. The Lagrange multiplier test and its applications to model specification in econometrics. The Review of Economic Studies, 47, 239-253. DEMEULEMEESTER, E. & HERROELEN, W. 2002. Project scheduling-A research handbook. Vol. 49 of International Series in Operations Research & Management Science. Kluwer Academic Publishers, Boston. ELHORST, J. P. 2014. Spatial panel data models. Spatial Econometrics. Springer. GEORGOPOULOS A., L. Q., PEK ZHI XUAN, KULIAN J., TSO TSZ HO, HO WING YUNG 2017. Group Assignment 2. Imperial College Business School. GOLDRATT, E. M. 1997. Critical chain. North River Press: Great Barrington, MA. LESAGE, J. P. 2008. An introduction to spatial econometrics. Revue d'économie industrielle, 19-44. LEWIS, J. P. 1995. Project planning. Scheduling & Control: A hands-On guide to bringing projects in on time and on budget, McGrawHill. MILLO, G. & PIRAS, G. 2012. splm: Spatial panel data models in R. Journal of Statistical Software, 47, 1-38. VITON, P. A. 2010. Notes on spatial econometric models. City and regional planning, 870, 9-10.

16 Appendices

Appendices

A. Fixed Effects

Table 5. Fixed Effects for each cross-sectional unit (restaurant)

Restaurant FE on Net FE on Restaurant FE on Net FE on Restaurant FE on Net FE on Code Sales Traffic Code Sales Traffic Code Sales Traffic ABBIATEGRASSO-1,185.14 *** -144.1 *** CASERTA TOY'S - SAN MARCO EVANGELISTA-1,947.54 *** -360.53 FIRENZE INTERNO STAZIONE5,800.99 1,436.21 *** ACIREALE DRIVE-602.67 *** -48.12 *** CASORIA -987.5 *** -280.99 *** FIRENZE NENNI-1,402.02 *** -307.96 *** AFFI DRIVE 1,255.39 *** 57.48 *** CASSANO -644.64 *** 2.36 *** FIRENZE OSMANNORO-77.83 *** -102.87 *** AFRAGOLA 299.34 *** -41.51 *** CASSINO 1,376.36 *** 75.07 *** FIRENZE SENESE-2,695.01 *** -441.34 AGRIGENTO -1,292.67 *** -166.4 *** CASTEGNATO -673.4 *** -105.61 *** FIRENZE TALENTI-3,651.71 *** -494.27 *** ALBIGNASEGO PD-1,768.08 *** -339.6 *** CASTEL MAGGIORE-1,053.85 *** -173.49 *** FIUME VENETO1,607.18 *** -1.77 *** ALESSANDRIA 1,121.45 *** 156.2 *** CASTELFRANCO VENETO-1,891.08 *** -371.35 *** FIUMICINO RETAIL PARK2,360.44 *** 36.81 *** ALGHERO -3,798.27 *** -455.3 *** CASTELLANZA -1,972.54 *** -328.47 *** FIUMICINO TERMINAL A2,665.96 *** 227.22 . ALPIGNANO -3,149.06 *** -431.3 *** CASTELLETTO TICINO3,467.06 *** 284.4 *** FIUMICINO TORRIMPIETRA-1,345.02 *** -320.18 *** ANCONA BARACCOLA841.69 *** -33.67 *** CASTELNUOVO SCRIVIA-1,414.94 *** -390.79 *** FIUMICINO VIA DEL FARO500.57 *** -12.32 *** ANTEGNATE -683.78 *** -23.97 *** CASTELVETRANO-2,667.16 *** -403.4 *** FOGGIA MONGOLFIERA1,213.61 *** 198.15 *** ANZIO -618.16 *** -272.1 *** CASTENASO -1,501.37 *** -236.97 *** FOIANO -643.94 *** -272.32 *** AOSTA 837.32 *** -90.41 *** CASTIONE ANDEVENNO-484.41 *** -171.02 *** FORLÌÎ -492.02 *** -126.96 *** APRILIA PONTINA Q8-1,579.67 *** -342.1 *** CATANIA -588.27 *** 568.36 *** FORLÌÎ MALL -2,436.59 *** -232.63 *** APRILIA VALLELATA-955.39 ** -114.9 *** CATANIA ALCALÌÛ-2,854.87 *** -224.48 *** FORMIA -875.31 *** -67.48 * AREZZO -958.37 *** -227.6 *** CATANIA GRAVINA-2,358.18 *** -307.8 *** FOSSANO DRIVE-2,017.78 *** -367.44 *** ARNO OVEST -176.44 *** -290.6 *** CATANIA MALL-1,530.56 *** -137.45 *** FROSINONE 212.94 *** 17.08 *** ASSAGO 3,160.48 *** 404.26 *** CATANIA S. GIOVANNI-315.41 *** 23.49 *** FROSINONE LEPINI3,178.58 *** 235.33 *** ASSISI -398.3 *** -56.36 *** CATANIA TENUTELLA498.37 *** -47.45 *** GALLARATE VIA MILANO2,826.46 *** 305.99 *** ASTI CONSORZIO245.95 *** 79.63 *** CATANIA ULISSE -378.26 *** 27.32 *** GARBAGNATE 2,199.70 *** 333.98 *** BAGNOLO CREMASCO1,930.76 *** 164.93 *** CATANZARO LE AQUILE-3,811.38 *** -529.26 *** GARLATE 2,241.67 *** 270.76 *** BARI CASAMASSIMA3,106.97 *** 249.46 CATANZARO LE FONTANE2,827.26 *** 237.11 *** GELA -2,063.11 *** -182.05 *** BARI MUNGIVACCA380.78 *** -47.43 *** CATTOLICA -3,539.41 *** -423.15 *** GENOVA BRIGNOLE-660.52 *** 67.36 *** BARI SANTA CATERINA0.25 -5.59 *** CECINA -787.03 *** -159.61 *** GENOVA FIUMARA385.36 *** 49.35 *** BARI SPARANO 781.33 *** 727.25 *** CENTO 693.11 128.21 *** GENOVA PORTO ANTICO ACQUARIO-502.8 *** 250.35 *** BARI TANGENZIALE389.52 *** 68.54 *** CESANO BOSCONE-2,311.77 *** -212.77 *** GENOVA TRAGHETTI-2,797.50 *** -382.23 *** BARLETTA -3,276.14 *** -441.3 *** CESENA CERVESE 22.91 *** -105.41 *** GENOVA XX SETTEMBRE2,513.02 *** 626.88 BASSANO 1,975.40 *** 167.23 *** CHIENTI EST -3,063.16 *** -511.65 *** GIOIA TAURO 1,328.30 *** 56.97 *** BEINASCO 1,477.50 *** 51.9 *** CHIERI -1,821.84 *** -328.45 *** GIUGLIANO -761.45 *** -4.33 *** BELLINZAGO -802.29 *** -38.16 *** CHIOGGIA -767.23 *** -192.39 *** GRAVELLONA TOCE-1,953.22 *** -275.22 *** BELLUNO STAZIONE-4,141.61 *** -543.3 *** CIAMPINO 1,712.30 *** 34.51 *** GROSSETO -1,223.11 *** -276.82 *** BELPASSO CT 585.05 *** 127.86 *** CINISELLO MALL-3,181.10 *** -336.33 *** GRUGLIASCO 4,232.32 *** 395.06 *** BERGAMO P.ZA MARCONI488.63 *** 506.1 *** CINISELLO TESTI17,605.67 *** 1,186.80 *** GRUGLIASCO SPIZZICO-3,867.42 *** -488.49 *** BIELLA 1,164.47 *** -31.49 *** CITTÌÛ DI CASTELLO-213.23 -127.09 GUIDONIA -493.57 *** -232.74 *** BINASCO 3,165.68 *** 365.62 *** CIVITANOVA MARCHE-1,929.87 *** -299.3 *** IMOLA DRIVE -402.44 *** -223.89 *** BISCEGLIE -4,005.85 *** -508.6 *** CIVITAVECCHIA 54.99 *** -1.07 *** JESI -491.82 *** -61.46 *** CAAB334.85 *** -130.6 *** COLLESALVETTI-1,665.11 *** -347.86 *** JESOLO 229.66 *** 29.22 *** BOLOGNA ESTERNO STAZIONE 22,550.13 *** 678.37 *** COLOGNO MONZESE447.28 *** -57.01 *** L' AQUILA 1,467.90 *** 77.71 *** BOLOGNA INDIPENDENZA 13,482.28 *** 978.79 *** COLONNELLA -2,249.53 *** -361.59 ** LA PIOPPA EST -596.19 *** -321.17 *** BOLOGNA S. LAZZARO1,497.46 *** 157.75 *** COMO 333.3 233.42 ** LA PIOPPA OVEST-2,265.03 *** -429.25 *** BOLOGNA STALINGRADO1,220.93 *** 178.97 *** CONCESIO TRIUMPLINA571.59 *** -19.79 *** LA SPEZIA -2,398.39 *** -350.37 *** BOLOGNA TOGLIATTI DRIVE2,261.92 *** 167 *** CORRIDONIA 22.33 *** -20.02 *** LA SPEZIA STAZIONE-3,748.65 *** -445.2 *** BOLOGNA VIII AGOSTO1,738.37 *** 763.44 *** CORSICO -253.92 ** -209.64 LA SPEZIA TERRAZZE-2,302.07 *** -229.57 *** BOLZANO BUOZZI5,052.16 *** 255.24 *** CREMONA DRIVE-614.17 *** -217.72 *** LADISPOLI 734.34 *** -128.2 *** BREMBATE DRIVE-444.03 -98.86 . CREMONA MALL-176.87 *** -3.68 *** LAINATE 1,971.10 *** 258.66 *** BRESCIA CAMPOGRANDE5,208.21 *** 694.48 *** CROTONE PASSOVECCHIO-546.99 *** -214.08 *** LAMEZIA I 2 MARI-635.75 *** -189.17 *** BRESCIA CONTINENTE67.64 *** -12.62 *** CUNEO AUCHAN-628.91 *** -190.5 *** LAMEZIA TERME DRIVE-1,719.68 *** -285.52 BRESCIA FRECCIA ROSSA618.85 *** 368.47 *** CURNO 3,904.07 *** 650.11 *** LATINA FIORI -318.14 *** 262.08 *** BUSNAGO 2,369.92 *** 454.1 *** CURTATONE 2,310.46 *** 164.84 *** LATINA ISONZO 517.07 *** -6.06 *** BUSTO ARSIZIO-1,906.62 * -163.5 *** DALMINE 2,854.34 *** 285.42 *** LATINA ROMAGNOLI1,801.63 *** 275.25 CAGLIARI ARST-1,654.19 *** 261.16 *** DARFO BOARIO TERME-580.23 *** -50.5 *** LECCE SURBO 1,266.84 *** 106.09 *** CAGLIARI BACAREDDA132.67 *** -87.17 *** DESENZANO SUL GARDA2,258.98 *** 166.28 *** LECCE TEMPLARI-1,783.60 *** 10.83 *** CAGLIARI PERETTI921.9 *** 43.28 *** DESIO 3,520.30 *** 412.1 *** LECCO -1,596.05 *** -50.26 *** CAGLIARI S. SIMONE-1,018.73 *** -146.6 *** DOMODOSSOLA -825.33 *** -47.21 *** LEGNAGO 1,890.34 *** 217.87 *** CALCINAIA FORNACETTE860.52 *** -90.91 *** EBOLI -1,066.00 *** -295.22 *** LEGNANO 1,518.88 *** 193.46 *** CALTANISSETTA-2,266.48 *** -311.4 *** ERBA -503.7917 *** -114.63 *** LEINÌÎ -960.2 *** -293.56 *** CAMAIORE LIDO1,926.87 *** 53.13 *** ERBUSCO 1,796.52 333.05 *** LENTATE SUL SEVESO1,681.97 *** 171.49 * CAMPI BISENZIO2,158.88 *** 217.58 *** FAENZA -2,228.85 *** -388.03 *** LIDI COMACCHIESI809.32 *** -43.57 *** CAMPOBASSO DRIVE-1,033.93 -185.4 *** FERRARA DRIVE -63.11 *** -92.89 *** LIMBIATE -439.84 *** -17.94 *** CANT̪ -1,420.41 *** -218.5 *** FERRARA SUD 1,297.13 *** 67.19 *** LIPOMO -958.2 -167.82 * CARESANABLOT -32.32 *** -148 *** FERRARA TRENTO E TRIESTE-929.65 *** 257.75 *** LIVORNO -2,635.08 *** -257.41 *** CARINI -2,185.99 *** -351.8 *** FIDENZA -1,247.55 *** -285.89 *** TANGENZIALE EST62.29 *** -15.73 *** CARMAGNOLA-2,229.06 *** -372.4 *** FIDENZA VIA EMILIA-3,805.33 *** -564.03 *** LONATO -623.88 *** -136.02 *** CARPI 782.44 *** -34.52 *** FIRENZE AGNELLI-2,135.51 *** -360.13 *** LORETO -933.36 *** -163.51 *** CARUGATE 2,767.58 *** 313.99 *** FIRENZE BARACCA AGIP DRIVE-2,820.86 *** -396.79 *** LUCCA CAPANNORI-780.89 *** -219.84 *** CASALECCHIO DI RENO 1-1,153.31 -242 *** FIRENZE CAMPI-3,091.96 *** -524.4 *** LUCCA EUROPA1,533.25 *** 37.72 *** CASALECCHIO DI RENO 2-765.01 *** -193.6 *** FIRENZE -1,472.56 *** -188.43 *** LUGAGNANO DI SONA1,942.84 *** 134.92 *** CASALPUSTERLENGO30.58 *** 60.69 *** FIRENZE ESTERNO STAZIONE9,025.23 *** 1,860.65 *** LUGO -2,022.63 *** -350.81 *** Appendices

MADDALONI DRIVE-1,437.84 *** -315.7 *** NAPOLI MUNICIPIO-506.52 *** 45.09 *** REGGIO EMILIA STAZIONE-4,329.81 *** -435.48 *** MAGENTA 1,648.75 *** 91.11 *** NAPOLI P.ZZA GARIBALDI-2,840.11 *** -223.99 *** REGGIO EMILIA TIEN AN MEN3,340.47 *** 321.34 *** MALNATE 911.73 *** -64.21 *** NAPOLI STADIO FUORIGROTTA1,813.63 *** 202.7 *** RENDE 2,513.99 *** 544.16 MANTOVA -2,825.69 *** -242.2 *** NERVIANO -2,531.31 *** -354.29 *** RENDE MARCONI2,902.02 *** 632.2 *** MARCIANISE 4,945.01 *** 511.71 *** NETTUNO -1,037.57 *** -250.17 *** RESCALDINA -258.08 *** 0.9 *** MARCON DRIVE-2,238.14 -381.2 *** NOCERA SUPERIORE-2,285.57 *** -364.21 *** RICCIONE -2,189.35 *** -358.02 *** MARCON GALLERIA-2,131.75 *** -59.65 *** NOLA 1,539.59 *** 148.64 *** RICCIONE AQUAFAN-4,511.19 *** -643.25 *** MARGHERA MALL78.88 *** 141.22 *** NOVARA SAN MARTINO-911.65 *** -136.28 *** RIETI -820.57 *** -103.6 *** MASSA 206.78 *** -169 *** NOVARA SPORTING754.43 *** 41.3 *** RIMINI FLAMINIA-2,167.89 *** -340.56 *** MERCOGLIANO -539.15 *** -193.9 *** NOVATE MILANESE-912.07 *** 57.71 *** RIMINI LE BEFANE484.82 *** 195.76 *** MESAGNE -165.54 *** -60.92 *** OLBIA 3,394.34 *** 297.05 *** RIMINI POPILIA-1,632.63 *** -285.78 *** MESSINA CAIROLI-826.15 *** 248.64 *** OLGIATE OLONA1,715.87 *** 173.63 *** RIMINI TINTORI-3,719.61 * -429.24 * MESSINA DRIVE-2,673.12 *** -412.6 *** ORIO AL SERIO 3,764.37 *** 405.61 *** RIVOLI -1,928.85 *** -349.49 *** MESTRE CORSO DEL POPOLO-405.49 120.78 *** ORIO AL SERIO AEROPORTO2,805.90 *** 547.5 *** RODENGO SAIANO138.88 *** -16.06 *** MESTRE STAZIONE-880.87 *** -24.2 *** ORISTANO 553.8 *** -66.28 *** ROMA -391.05 *** -123.29 *** MESTRE TERRAGLIO-69.24 *** -139.7 *** ORZINUOVI -1,127.58 -126.99 *** ROMA ANNIBALIANO-669.57 *** -73.84 *** MESTRE TOSATTO MALL-2,384.03 *** -185.4 *** OSTIA PORTO TURISTICO-4,501.86 *** -628.94 *** ROMA ARDEATINA3,477.67 *** 448.93 *** MILANO ANTONINI1,325.09 . 182.15 *** OSTIA TOSCANELLI82.69 *** 36.66 *** ROMA AURELIA2,625.26 *** 207.41 *** MILANO BONOLA-1,620.27 *** 129.42 *** PADERNO DUGNANO-1,913.96 *** -225.06 *** ROMA C.SO FRANCIA3,761.33 *** 431.16 *** MILANO BUONARROTI1,491.29 *** 310.94 *** PADOVA -796.8 *** 305.97 *** ROMA CAPENA2,078.16 *** 69.64 *** MILANO CENTRALE 2109.79 *** 368.67 *** PADOVA GUIDO RENI811.9 *** 135.32 *** ROMA CASAL DEL MARMO-1,365.85 *** -342.23 *** MILANO CERTOSA-1,090.87 *** -158.4 *** PADOVA OVEST-1,051.70 *** -308.56 *** ROMA CASALOTTI856.03 *** -68.6 *** MILANO CORSO LODI-2,038.72 *** -72.27 *** PADOVA VIA VENEZIA-761.02 *** -239.25 *** ROMA CINECITTA'-1,024.42 *** -80.05 *** MILANO DE GASPERI-1,005.32 *** -192.2 *** PALERMO BORGONUOVO-3,813.29 -355.07 *** ROMA COLLI ALBANI-1,506.15 -210.04 *** MILANO DUOMO18,248.72 *** ###### *** PALERMO CASTELNUOVO-313.18 *** 248.6 *** ROMA DE LA SALLE-507.54 *** 143.04 *** MILANO FARINI-353.93 *** 289.78 *** PALERMO DRIVE -7.5 *** 49.29 *** ROMA DRAGONA-86.59 *** -232.37 *** MILANO GALLERIA FONTANA7,665.84 *** ###### *** PALERMO LA MALFA-712.33 *** -41.03 *** ROMA EUR 999.46 *** 130.65 *** MILANO LINATE-2,077.31 *** -305.5 *** PALERMO NOTARBARTOLO-3,750.34 *** -416.17 *** ROMA EUR 2 -1,960.68 *** -47.17 *** MILANO LORENTEGGIO DRIVE3,239.17 *** 450.94 *** PALERMO PECORAINO-750.17 *** -95.75 *** ROMA FONTANA DI TREVI3,624.71 *** 406.93 *** MILANO LOTTO-1,024.18 *** 112.08 *** PALERMO STAZIONE-3,506.86 *** -276.24 ROMA GIOLITTI4,595.29 *** 1,267.72 *** MILANO MALPENSA2,054.18 *** 78.79 *** PANTIGLIATE 1,621.64 *** 153.21 *** ROMA GIULIO CESARE5,486.31 *** 1,000.05 *** MILANO OBERDAN283.35 *** 438.35 *** PARCO LEONARDO-625.18 *** -4.45 *** ROMA GRANAI DI NERVA-2,784.43 -366.37 *** MILANO P.LE LORETO756.61 . 462.32 *** PARMA 303.84 *** -59.91 *** ROMA LUNGHEZZA6,251.34 *** 887.38 *** MILANO P.ZA ARGENTINA-254.39 *** 259.99 *** PARMA EST 573.73 *** 42.3 *** ROMA MAGLIANA-32.68 *** -70.9 MILANO PAULLESE-106.73 *** -42.53 *** PARMA SAN LEONARDO-173.48 *** -105.82 *** ROMA MIRTI 2,063.38 *** 372.95 *** MILANO ROGOREDO-1,985.01 *** -327.5 *** PARONA -2,823.92 *** -437.29 ROMA NAZIONALE-371.66 *** 4.98 *** MILANO RUBICONE1,145.96 167.56 *** PAVIA BRAMBILLA1,924.02 *** 128.69 *** ROMA NOMENTANA3,488.95 *** 119.7 *** MILANO RUBICONE 21,157.20 *** 75.02 *** PAVONE CANAVESE-249.76 -3.37 *** ROMA OLGIATA-1,258.97 *** -334.22 *** MILANO SABOTINO-52.86 *** 496.12 *** PERUGIA 1 -3,463.50 *** -361.52 *** ROMA P.ZZA DI SPAGNA9,249.68 *** 1,345.76 *** MILANO SAN BABILA-1,206.22 *** 32.45 *** PERUGIA COLLESTRADA37.02 *** 108.32 ROMA PALAIA -350.42 *** -287.67 *** MILANO SARPI-2,179.85 *** -180.2 *** PERUGIA SAN SISTO433.89 *** -35.92 *** ROMA PARCHI COLOMBO-418.13 *** -242.08 *** MILANO STAZIONE CENTRALE INTERNO7,828.41 *** ###### *** PESCARA -1,051.66 *** 3.31 *** ROMA PIO XI -913.66 *** -139.67 *** MILANO VIA NOVARA-879.91 *** -183.1 *** PESCHIERA 1,591.40 *** 65.06 *** ROMA PORTA DI ROMA10,755.94 *** 1,059.03 *** MILANO XXII MARZO-1,424.59 *** -97.34 *** PIACENZA EMILIA2,421.75 *** 135.8 *** ROMA PRATI FISCALI1,779.66 *** 240.05 *** MILANO XXIV MAGGIO-303.82 *** 288.35 *** PIACENZA STAZIONE-3,170.08 *** -116.81 *** ROMA RE DI ROMA1,082.80 140.43 *** MILAZZO -703.08 *** -225.9 *** PIEVE FISSIRAGA1,803.42 *** 107.11 *** ROMA REGINA MARGHERITA-1,646.41 *** -58.57 *** MIRANDOLA -661.44 *** -155 *** PINEROLO DRIVE-349.66 ** -139.76 *** ROMA SAN PAOLO-29.29 *** 139 *** MODENA BRUCIATA478.58 *** 78.71 *** PIOMBINO -1,736.65 *** -367.57 *** ROMA STRADIVARI-1,819.50 *** -298.41 *** MODENA EMILIA EST-903.61 *** -152.2 *** PISA MIRACOLI -178.49 *** 174.87 *** ROMA STURZO1,121.54 *** 288.16 *** MODENA OVEST1,644.63 *** 194.98 *** PISA STAZIONE-1,821.39 *** -146.43 *** ROMA TERMINI12,265.29 *** 2,741.09 *** MODENA PORTALI-1,997.86 *** -115.1 *** PISTOIA ACI 985.52 *** -48.31 ** ROMA FORUM2,019.92 *** 1,008.26 *** MODENA STAZIONE-3,209.66 *** -317.4 *** POMEZIA -1,126.48 *** -246.29 *** ROMA CAVALLARI406.63 *** -80.04 MOLFETTA -330.83 *** -132.9 *** POMEZIA CASTELLI ROMANI785.22 *** -19.59 ROMA TIBURTINA DE PAOLIS-585.48 *** 4.33 *** MONCALIERI 437.24 *** -40.81 *** POMPEI -3,005.50 *** -392.15 *** ROMA TOR BELLA MONACA-766.56 *** -304.9 *** MONDOVÌÎ -808.94 *** -197.2 *** POMPEI MALL -979.29 *** 8.03 *** ROMA TOR VERGATA MALL-2,581.68 *** -302.11 *** MONFALCONE-1,688.93 *** -124.8 PONTECAGNANO MALL-1,813.72 *** -164.82 *** ROMA -321.57 *** -214.6 *** MONTANO LUCINO2,699.42 *** 200.66 *** PORDENONE -648.99 *** -172.26 *** ROMA TRIONFALE-352.03 *** -188.38 *** MONTEBELLO 649.85 *** 6.96 * PORTO SAN GIORGIO DRIVE-2,022.52 *** -329.7 *** ROMA TUSCOLANA-958.38 *** -102.42 *** MONTECATINI CAMPORCIONI627.41 *** -52.62 *** PORTOGRUARO RETAIL PARK-497.08 *** -204.91 *** ROMA V.LE AMERICA-1,290.49 *** 64.42 *** MONTECCHIO DRIVE1,120.37 *** 13.8 *** POTENZA -1,665.73 *** -244.81 *** ROMAGNANO SESIA1,922.42 *** 166.76 *** MONTEMURLO-1,943.40 *** -379.2 *** PRATO 3,286.91 *** 347.75 *** ROMANINA 4,267.89 *** 309.73 *** MONTEPAONE-2,076.66 ** -241.7 PUEGNAGO -1,898.48 *** -267.08 *** RONCADELLE -1,706.38 *** -207.42 *** MONTEROTONDO1,090.06 *** 152 *** QUARTUCCIU 4,945.99 *** 754.38 *** ROVERETO 2,031.26 *** 264.2 *** MONTESILVANO-196.95 *** 3.86 *** RAGUSA DRIVE-2,015.33 *** -230.69 ** ROVIGO 3,818.15 *** 374.43 *** MONZA V.LE LOMBARDIA4,206.60 *** 663.8 *** RAVENNA DRIVE-3,527.56 *** -520.58 *** ROZZANO 3,936.76 *** 395.46 *** MONZA VIA MILANO-2,470.97 *** -141.3 *** RAVENNA IPERCOOP-900.59 ** -23.04 *** RUBANO -1,424.43 *** -348.64 *** MUGELLO -2,435.19 *** -492.1 *** RAVENNA MIRABILANDIA-957.81 . -352.53 *** S.GIOVANNI TEATINO-1,545.31 *** -279.22 *** NAPOLI AEROPORTO-3,964.98 ** -492.3 *** RAVENNA VIA TRIESTE-157.24 *** -56.95 *** S.GIULIANO TERME-1,542.34 -303.15 *** NAPOLI ARGINE-2,532.30 *** -256.1 *** REGGIO CALABRIA-102.52 *** 146.51 *** SALERNO MERCATELLO751.18 *** 96.78 *** NAPOLI DOGANELLA-187.96 *** -212.8 *** REGGIO CALABRIA TANGENZIALE-1,598.59 *** -329.75 *** SAN BENEDETTO DEL TRONTO-49.02 *** -41.8 *** NAPOLI INTERNO STAZIONE458.23 *** 216.69 *** REGGIO EMILIA-1,047.23 *** -151.19 *** SAN DONÌÛ DI PIAVE-3,195.80 *** -427.15 ***

18 Appendices

SAN DONÌÛ DI PIAVE DRIVE-832.3 *** -304.8 *** SIENA DRIVE 580.79 *** -118.99 TREVISO REPUBBLICA640.85 *** 64 *** SAN GIOVANNI LUPATOTO-1,046.26 *** -70.44 *** SIRACUSA DRIVE -210.91 *** -33.52 *** TRIESTE MALL-2,343.08 *** -295.81 *** SAN GIOVANNI LUPATOTO DRIVE1,754.63 *** 164.29 *** SIRACUSA MELILLI C.C. BELVEDERE AUCHAN-1,004.86 -0.84 *** TRUCCAZZANO-1,867.40 *** -215.85 *** SAN GIULIANO MILANESE-2,796.39 *** -371.7 *** SOLBIATE ARNO1,568.71 *** 107.92 *** UDINE -966.87 *** 348.42 . SAN GIULIANO MILANESE CC LE CUPOLE-1,893.13 *** -237.9 *** SOMMA LOMBARDO51.84 *** -35.7 *** UDINE CITTÌÛ FIERA-1,673.91 *** -293.96 *** SAN MARINO -2,710.16 *** -512 *** SORA -606.7 *** -77.66 *** VAREDO 1,318.08 *** 11.67 *** SAN MARTINO SICCOMARIO1,439.04 *** 365.28 *** STEZZANO -1,260.67 *** -155.01 *** VARESE 1 -686.73 *** 145.65 *** SAN MAURO TORINESE-2,405.74 *** -369.2 *** STRADELLA -511.44 *** -49.63 *** VARESE STADIO2,693.69 *** 203.24 *** SAN PRISCO -1,463.07 *** -267.6 *** TARANTO -313.17 *** 208.63 *** VASTO -1,245.98 *** -167.08 *** SAN REMO -1,475.04 *** -180.3 *** TAVAGNACCO -358.1 *** -260.7 *** VELLETRI 1,678.65 *** 129.81 *** SAN VENDEMIANO - CONEGLIANO-1,188.96 *** -293.9 *** TAVERNOLA 340.86 *** -68.56 *** VENARIA -533.57 *** -126.06 *** SANTA VITTORIA D'ALBA-2,095.22 *** -375.1 *** TERNI DRIVE 2,191.64 *** 56.08 *** VENEZIA STRADA NUOVA1,107.52 *** 58.5 *** SARONNO -1,061.49 *** -100.1 *** TERRACINA DRIVE1,130.15 *** 24.7 *** VENTIMIGLIA -1,261.62 *** -258.43 *** SARZANA -811.02 *** -201.1 *** TEVEROLA -2,932.85 *** -441.75 *** VERANO BRIANZA5,593.22 *** 609.51 *** SASSARI 379.05 *** 204.49 *** TIVOLI TERME -1,325.66 *** -286.26 *** VERBANIA -1,298.48 *** -195.02 *** SASSUOLO 342.92 *** -101.9 *** TORINO CASTELLO1,619.87 *** 414.45 *** VEROLANUOVA-2,418.60 -389.09 *** SAVIGNANO SUL RUBICONE1,705.83 133.36 *** TORINO COSSA-2,242.01 *** -354.6 *** VERONA FIERA 789.48 *** 156.81 *** SAVONA 2,592.40 *** 410.85 *** TORINO GIULIO CESARE-455.38 *** -116.21 *** VERONA MILANO-41.84 *** -42.07 *** SCHIO DRIVE 59.32 *** -179.3 *** TORINO MONGINEVRO (NORAUTO)-1,153.77 *** -232.9 *** VERONA PORTA NUOVA2,293.32 *** 603.11 *** SEDRIANO 1,866.16 *** 114.84 *** TORINO P.ZZA STATUTO-1,800.25 *** -40.74 *** VICENZA MALL-1,249.42 *** -93.71 *** SEGRATE 624.53 *** 127.16 *** TORINO PORTA NUOVA STAZIONE1,258.69 *** 370.62 *** VICENZA SAN LAZZARO1,116.53 *** 78.29 *** SEGRATE CASSANESE3,496.39 *** 425.27 *** TORINO VIA LIVORNO-2,232.59 *** -266.06 *** VIGEVANO 1,545.33 *** 174.48 *** SENIGALLIA 227.53 *** 109.66 ** TORRI DI QUARTESOLO1,171.48 *** 391.48 *** VIGNATE -1,755.18 *** -117.67 *** SERIATE ALLE VALLI2,215.44 *** 212.98 TORTONA -1,302.99 *** -125.04 *** VIGNOLA -898.66 *** -205.81 *** SERRAVALLE SCRIVIA OUTLET659.36 *** -18.38 *** TRADATE 1,581.88 *** 224.24 *** VILLANOVA MONFERRATO-2,789.67 *** -448.51 *** SESTO SAN GIOVANNI - SARCA-1,078.23 *** 2.92 *** TRENTO 6,545.15 *** 530.37 *** VILLARICCA 2,565.59 *** 168.81 *** SESTO SAN GIOVANNI V.LE ITALIA-1,081.48 *** -41.29 *** TRENTOLA DUCENTA - AVERSA-612.85 *** -38.22 *** VILLESSE MALL-1,314.05 *** -218.8 *** SESTU 2,914.74 *** 165.17 *** TREVIGLIO 1,631.03 *** 273.18 *** VIMERCATE 2,370.66 *** 347.05 *** SIDERNO -1,153.93 *** -199.2 *** TREVISO -3,338.85 *** -307.06 *** VITERBO SAN PAOLO2,779.79 *** 294.88 *** CAGLIARI PERETTI921.9 *** 43.28 *** DESIO 3,520.30 *** 412.1 *** LECCO -1,596.05 *** -50.26 *** CAGLIARI S. SIMONE-1,018.73 *** -146.6 *** DOMODOSSOLA -825.33 *** -47.21 *** LEGNAGO 1,890.34 *** 217.87 *** CALCINAIA FORNACETTE860.52 *** -90.91 *** EBOLI -1,066.00 *** -295.22 *** LEGNANO 1,518.88 *** 193.46 *** CALTANISSETTA-2,266.48 *** -311.4 *** ERBA -503.79 *** -114.63 *** LEINÌÎ -960.2 *** -293.56 *** CAMAIORE LIDO1,926.87 *** 53.13 *** ERBUSCO 1,796.52 333.05 *** LENTATE SUL SEVESO1,681.97 *** 171.49 * CAMPI BISENZIO2,158.88 *** 217.58 *** FAENZA -2,228.85 *** -388.03 *** LIDI COMACCHIESI809.32 *** -43.57 *** CAMPOBASSO DRIVE-1,033.93 -185.4 *** FERRARA DRIVE -63.11 *** -92.89 *** LIMBIATE -439.84 *** -17.94 *** CANT̪ -1,420.41 *** -218.5 *** FERRARA SUD 1,297.13 *** 67.19 *** LIPOMO -958.2 -167.82 * CARESANABLOT -32.32 *** -148 *** FERRARA TRENTO E TRIESTE-929.65 *** 257.75 *** LIVORNO -2,635.08 *** -257.41 *** CARINI -2,185.99 *** -351.8 *** FIDENZA -1,247.55 *** -285.89 *** LODI TANGENZIALE EST62.29 *** -15.73 *** CARMAGNOLA-2,229.06 *** -372.4 *** FIDENZA VIA EMILIA-3,805.33 *** -564.03 *** LONATO -623.88 *** -136.02 *** CARPI 782.44 *** -34.52 *** FIRENZE AGNELLI-2,135.51 *** -360.13 *** LORETO -933.36 *** -163.51 *** CARUGATE 2,767.58 *** 313.99 *** FIRENZE BARACCA AGIP DRIVE-2,820.86 *** -396.79 *** LUCCA CAPANNORI-780.89 *** -219.84 *** CASALECCHIO DI RENO 1-1,153.31 -242 *** FIRENZE CAMPI-3,091.96 *** -524.4 *** LUCCA EUROPA1,533.25 *** 37.72 *** CASALECCHIO DI RENO 2-765.01 *** -193.6 *** FIRENZE CAVOUR-1,472.56 *** -188.43 *** LUGAGNANO DI SONA1,942.84 *** 134.92 *** CASALPUSTERLENGO30.58 *** 60.69 *** FIRENZE ESTERNO STAZIONE9,025.23 *** 1,860.65 *** LUGO -2,022.63 *** -350.81 *** ZUMPANO CS -767.02 *** -197.1 ***

B. Advertising Elasticities per Province

Elasticity GRP TV (Sales) Elasticity Offline (Sales) Elasticity GRP TV (Traffic) Elasticity Offline (Traffic) Provincia Short Long Short Long Short Long Short Long Agrigento 0.29239 0.41889 0.01699 0.01817 0.03328 0.04447 0.00279 0.00279 Alessandria 0.54194 0.60399 0.55746 0.81820 0.07589 0.08007 0.08435 0.11512 Ancona 0.60353 0.67324 0.37476 0.57820 0.09233 0.09233 0.03456 0.05766 Aosta 0.68924 0.72744 0.00003 0.00030 0.01437 0.01437 0.07725 0.10354 Aquila 0.53482 0.53482 0.41500 0.51955 0.06238 0.06238 0.12536 0.12536 Arezzo 0.01059 0.12978 0.01699 0.01817 0.06899 0.08165 0.07402 0.10138 Ascoli Piceno 0.54194 0.60399 0.10510 1.03536 0.08209 0.08209 0.01467 0.14450 Asti 0.86644 0.86644 0.48531 0.75162 0.09233 0.09233 0.12029 0.12029 Avellino 0.00883 0.09323 0.28240 0.63001 0.00103 0.01087 0.03614 0.09071 Bari 0.59096 0.85891 0.45051 0.82803 0.06868 0.09268 0.07229 0.12212 Barletta-Andria-Trani0.01395 0.20022 0.00376 0.00796 0.00163 0.02335 0.00052 0.00111 Belluno 0.00677 0.05406 0.88285 0.88285 0.01437 0.01437 0.01932 0.12854 Bergamo 0.70956 0.79340 0.53783 0.77358 0.08685 0.09724 0.07506 0.10797 Biella 0.80505 0.85137 0.58424 0.84272 0.01437 0.01437 0.09285 0.11688

19 Appendices

Bologna 0.80505 0.85137 0.57010 0.88917 0.06238 0.06238 0.08198 0.12834 Bolzano 0.74360 0.89605 0.10510 1.03536 0.05699 0.06229 0.01467 0.14450 Brescia 0.59145 0.70001 0.60438 0.82482 0.07436 0.08300 0.07780 0.11419 Brindisi 0.27806 0.46523 0.78385 0.78385 0.03243 0.05426 0.12029 0.12029 Cagliari 0.10579 0.14389 0.58867 0.79005 0.01234 0.01678 0.11602 0.11602 Caltanissetta 0.68803 0.81726 0.25465 0.36404 0.08025 0.09532 0.00279 0.00279 Campobasso 0.00883 0.09323 0.56885 0.81964 0.05130 0.06053 0.09687 0.12215 Caserta 0.51296 0.68944 0.41077 0.93316 0.05589 0.08055 0.06354 0.13037 Catania 0.63612 0.80394 0.45322 0.70092 0.08025 0.09532 0.07969 0.10687 Catanzaro 0.28334 0.40585 0.01997 0.01997 0.03328 0.04447 0.00279 0.00279 Chieti 0.44762 0.60024 0.81553 0.81553 0.05822 0.07318 0.06488 0.11945 Como 0.70956 0.79340 0.58038 0.90676 0.01437 0.01437 0.08718 0.12704 Cosenza 0.71343 0.91398 0.34167 0.68703 0.06238 0.06238 0.07082 0.10173 Cremona 0.74462 0.83369 0.42897 0.66283 0.08970 0.09478 0.06325 0.09782 Crotone 0.54583 0.78979 0.52108 0.52108 0.06366 0.09212 0.07560 0.07560 Cuneo 0.52384 0.65891 0.58885 0.92289 0.06110 0.07686 0.08257 0.12083 Fermo 0.02726 0.11105 0.10510 1.03536 0.00318 0.01295 0.01467 0.14450 Ferrara 0.60353 0.67324 0.57658 0.83120 0.07589 0.08007 0.09173 0.12365 Firenze 0.00677 0.05406 0.61230 0.89388 0.01437 0.01437 0.07874 0.12421 Foggia 0.56882 0.82468 0.44079 0.80936 0.06099 0.08811 0.06678 0.12321 Forl-Cesena 0.67321 0.75202 0.01486 0.01688 0.08506 0.08982 0.07722 0.11117 Frosinone 0.63612 0.80394 0.31411 0.70202 0.08685 0.09724 0.05644 0.11407 Genova 0.40618 0.45203 0.39162 0.88347 0.06409 0.06757 0.05655 0.12809 Gorizia 0.49912 0.62738 0.01699 0.01817 0.06222 0.07354 0.00237 0.00254 Grosseto 0.00677 0.05406 0.00224 0.00599 0.00123 0.01514 0.00031 0.00084 Imperia 0.29086 0.30628 0.10656 1.05106 0.03404 0.03404 0.00031 0.00084 La Spezia 0.28851 0.33984 0.01699 0.01817 0.04951 0.05511 0.00237 0.00254 Latina 0.39871 0.50005 0.64131 0.86330 0.06222 0.07354 0.09879 0.11688 Lecce 0.00677 0.05406 0.01699 0.01817 0.00153 0.00939 0.00237 0.00254 Lecco 0.68803 0.81726 0.49664 0.92047 0.06899 0.08165 0.07502 0.12811 Livorno 0.28977 0.32222 0.01997 0.01997 0.07279 0.07279 0.00279 0.00279 Lodi 0.83528 0.88608 0.53874 0.83737 0.10253 0.10253 0.08644 0.12513 Lucca 0.53344 0.63048 0.00008 0.00079 0.07589 0.08007 0.00000 0.00004 Macerata 0.53344 0.63048 0.51495 0.73992 0.06667 0.07434 0.12226 0.12226 Mantova 0.12318 0.12318 0.39226 0.79173 0.01437 0.01437 0.05757 0.11647 Massa Carrara 0.76901 0.81255 0.36985 0.57057 0.09917 0.09917 0.05272 0.07041 Messina 0.63884 0.86605 0.72197 0.72197 0.08661 0.10336 0.10288 0.10288 Milano 0.48856 0.53408 0.58444 0.91399 0.06238 0.06238 0.08209 0.12882 Modena 0.80505 0.85137 0.45322 0.70092 0.09692 0.10263 0.10940 0.10940 Monza e Brianza0.80505 0.85137 0.61937 0.89654 0.09720 0.09720 0.08209 0.12882 Napoli 0.44762 0.60024 0.43930 0.89276 0.05459 0.07325 0.06920 0.12909 Novara 0.77481 0.86902 0.55181 0.85876 0.09390 0.09930 0.08644 0.12513 Oristano 0.39871 0.50005 0.32975 0.73782 0.06899 0.08165 0.04226 0.10644 Padova 0.75449 0.90385 0.57097 0.76574 0.05699 0.06229 0.09268 0.09268 Palermo 0.10579 0.14389 0.71336 0.75192 0.01234 0.01678 0.10720 0.10720 Parma 0.79367 0.89240 0.01699 0.01817 0.06238 0.06238 0.08038 0.10280 Pavia 0.83528 0.88608 0.53208 0.82656 0.10253 0.10253 0.08722 0.12636 Perugia 0.74462 0.83369 0.55181 0.85876 0.09390 0.09930 0.09808 0.12376 Pescara 0.00124 0.00583 0.00003 0.00030 0.08710 0.08710 0.06239 0.09647 Piacenza 0.53482 0.53482 0.24306 0.44250 0.06238 0.06238 0.03554 0.05081 Pisa 0.28851 0.33984 0.74713 0.84024 0.07166 0.07558 0.10277 0.12259 Pistoia 0.79367 0.89240 0.49592 0.83552 0.09743 0.10335 0.07301 0.12343 Pordenone 0.68803 0.81726 0.43341 0.72689 0.09390 0.09930 0.05194 0.08689 Potenza 0.12318 0.12318 0.51195 0.79411 0.01437 0.01437 0.08362 0.12077 Prato 0.67321 0.75202 0.52316 0.88438 0.09233 0.09233 0.07957 0.12410 Ragusa 0.10579 0.14389 0.34536 0.69460 0.01234 0.01678 0.04559 0.11516 Ravenna 0.02726 0.11105 0.10510 1.03536 0.00318 0.01295 0.01467 0.14450 Reggio Calabri 0.43965 0.63251 0.50524 0.78337 0.06268 0.08433 0.06921 0.11661 Reggio Emilia 0.53482 0.53482 0.25367 0.50835 0.06238 0.06238 0.03392 0.06176 Rep.San Marino0.60353 0.67324 0.49021 0.82545 0.08506 0.08982 0.08785 0.12739 Rieti 0.85019 0.85019 0.70706 0.70706 0.06238 0.06238 0.09464 0.09464 Rimini 0.02726 0.11105 0.10510 1.03536 0.00255 0.01175 0.01467 0.14450

20 Appendices

Roma 0.70956 0.79340 0.58741 0.91959 0.01437 0.01437 0.08209 0.12882 Rovigo 0.68803 0.81726 0.46012 0.84665 0.08685 0.09724 0.06288 0.11556 Salerno 0.35989 0.51642 0.45140 0.92063 0.03768 0.05401 0.07203 0.12351 Sassari 0.02726 0.11105 0.01699 0.01817 0.00318 0.01295 0.00000 0.00004 Savona 0.56151 0.66407 0.89962 0.89962 0.09037 0.10136 0.10940 0.10940 Siena 0.53482 0.53482 0.58667 0.58667 0.06238 0.06238 0.06279 0.06279 Siracusa 0.46803 0.62802 0.81553 0.81553 0.05983 0.08042 0.12029 0.12029 Sondrio 0.00677 0.05406 0.00003 0.00030 0.00079 0.00631 0.00000 0.00004 Taranto 0.28334 0.40585 0.76811 0.76811 0.03305 0.04734 0.11161 0.11161 Teramo 0.00883 0.09323 0.51082 0.81054 0.00123 0.01514 0.03271 0.09384 Terni 0.53482 0.53482 0.40068 0.61860 0.01437 0.01437 0.06979 0.10022 Torino 0.12318 0.12318 0.53673 0.90969 0.01437 0.01437 0.07598 0.12935 Trapani 0.61077 0.89056 0.01699 0.01817 0.07821 0.10761 0.00237 0.00254 Trento 0.83528 0.88608 0.45322 0.70092 0.09917 0.09917 0.07847 0.10520 Treviso 0.79367 0.89240 0.51265 0.86535 0.09692 0.10263 0.06488 0.11945 Trieste 0.01228 0.16528 0.21239 0.60847 0.00182 0.02738 0.03106 0.07784 Udine 0.77481 0.86902 0.43798 0.62782 0.06238 0.06238 0.03652 0.04298 Varese 0.80505 0.85137 0.64131 0.86330 0.10106 0.10106 0.12536 0.12536 Venezia 0.28706 0.35941 0.01699 0.01817 0.03365 0.03964 0.00237 0.00254 Verbano Cusio 0.72927 0.77006 0.01699 0.01817 0.09233 0.09233 0.01092 0.11207 Vercelli 0.83528 0.88608 0.47872 0.80529 0.10106 0.10106 0.08157 0.12756 Verona 0.46057 0.54363 0.63969 0.87059 0.07436 0.08300 0.08546 0.12476 Vicenza 0.68803 0.81726 0.61937 0.89654 0.07647 0.09069 0.08928 0.12150 Viterbo 0.70956 0.79340 0.52806 0.89340 0.08970 0.09478 0.07875 0.12273

21