
Article 1 
The State aid amounting, in principle, to RON 3 656 675 for Electrocentrale Deva and RON 22 619 821 for Termoelectrica in the form of preferential electricity tariffs in favour of those undertakings, unlawfully granted by Romania in breach of Article 108(3) of the Treaty, is incompatible with the internal market.
Article 2 
Romania shall recover the incompatible aid referred to in Article 1 from the beneficiaries. The obligation to recover the aid is extended to CE Hunedoara.
The sums to be recovered shall bear interest from the date on which they were put at the disposal of the beneficiaries until their actual recovery.
The interest shall be calculated on a compound basis in accordance with Chapter V of Commission Regulation (EC) No 794/2004.
Article 3 
Recovery of the aid referred to in Article 1 shall be immediate and effective.
Romania shall ensure that this Decision is implemented within four months following the date of its notification.
Article 4 
Within two months following notification of this Decision, Romania shall submit the following information:

— the total amount (principal and recovery interests) to be recovered from each beneficiary,
— a detailed description of the measures already taken and planned to comply with this Decision, including the proof that it registered the recovery order at an appropriate ranking in the liquidation process of Termoelectrica,
— if it is impossible for by Termoelectrica to fulfil the recovery order, the order made against Termoelectrica to dissolve the company and proof that Termoelectrica definitively exits the market,
— documents demonstrating that the beneficiaries have been ordered to repay the aid.
Romania shall keep the Commission informed of the progress of the national measures taken to implement this Decision until recovery of the aid referred to in Article 1 has been completed. It shall immediately submit, on simple request by the Commission, information on the measures already taken and planned to comply with this Decision. It shall also provide detailed information concerning the amounts of aid and recovery interest already recovered from the beneficiary.
Article 5 
This Decision is addressed to Romania.
Done at Brussels, 20 April 2015.
For the Commission
Margrethe VESTAGER
Member of the Commission
ANNEX
The econometric analysis undertaken by the Commission aims at creating benchmark prices for the contracts under investigation, which would result from a regression analysis carried out on contracts in the dataset, which are not under investigation, by using features of these contracts. In a first step, the regression analysis allows constructing a benchmark price as a function of the contract characteristics of the dataset (‘in-sample predictions’). In a second step, the results of the regression analysis are used to predict a benchmark price for the contracts investigated taking into account their contract characteristics (‘out-of-sample predictions’). In the regression analysis, the variation in prices among the contracts in the dataset is explained using the following characteristics: quantity purchased and year dummies.

The econometric analysis relies on the principle that there are a number of drivers of prices, such as quantities. It would be misleading to compare the prices across different contracts without considering these drivers. The rationale of this quantitative exercise is, therefore that, once some external factors are taken into account, the prices across different contracts become more comparable. In the absence of normalisation, only perfectly identical contracts could be meaningfully compared.

This empirical exercise does not aim at estimating a causal relationship between prices and some external factors. For example, estimating a causal relationship between some factors and the prices would require dealing with the risk of endogeneity, that is, the risk that a causal variable (e.g. the quantities) is itself influenced by the explained variable (e.g. the price), due to omitted variables or simultaneity bias. The purpose of the quantitative exercise is to ‘normalise’ the prices across different contracts to make them more comparable to each other. This normalisation is necessary in the absence of perfectly identical contracts and supply characteristics.

The regression analysis captures the main features of the bilateral contracts at stake:


— including the quantity variable in the regression captures that prices are in general lower when quantities purchased are higher,
— including year dummies captures the time dimension and the possible change in market conditions between different years.

As regards the first step of the empirical analysis, the results of the regression analysis on the dataset contracts are reported in Table 1 below.

As regards the second step of the empirical analysis, the Commission has identified a benchmark for every year and then tested the position of the contracts relative to this benchmark in order to conclude whether the prices charged by Hidroelectrica were lower or higher than the modelled benchmark price. The following steps describe in detail the methodology used to determine the benchmark:


 Firstly, for each contract under investigation, it is calculated if and how far the actual price every year departs from its corresponding benchmark price computed using the regression and the contract characteristics;
 Secondly, the most-upward-diverging contract (‘MUD’) is identified; this is the dataset contract with the observed price which departs the most above its own corresponding benchmark price (in absolute terms). The choice of MUD which provides a range of variation above the central estimate of benchmark price, whilst being conservative, is justified; firstly, the econometric model does not explain 100 % of the observed price in the dataset and the price benchmark single estimate is provided within an interval of confidence and a margin of error above or below the estimate; secondly, price deviations from a single possible price exist on the real market; the MUD, which stems from market-based contracts (see recitals 42 to 45) brings quantified information about the possible extent of such deviations and provides a market-based range around the calculated benchmark price;
 Thirdly, the price difference from the MUD contract is used to separate observed prices above benchmark price from contracts below benchmark price:
— if a contract has an observed price above its corresponding benchmark price and if the price difference of this contract is higher than the MUD price difference, then this contract is considered prima facie not market conform,
— otherwise the contract should be deemed to be market conform;

The table below presents detailed results from the regression analysis on the dataset. The regression explains 36 % of the variations in the data. The coefficient estimates presented in the table below are used in a second stage to predict the ‘benchmark’ price for the contracts under investigation (out-of-sample predictions), assuming they would also be retail contracts, like contracts in the dataset.

Source SS df MS  Number of obs137F(5,131)14,73Prob > F0,0000R-squared0,3598Adj R-squared0,3354Root MSE23,937
Model 4218,7868 5 8436,95736
Residual 75057,7748 131 572,960113
Total 117242,562 136 862,077659Average price RON ~ h Coef. Std. Err. t P > |t| [95 % Conf. Interval]
Annual quantity GWh – ,0114518 ,0078662 – 1,46 0,148 – ,027013 ,0041094
year      
2008 26,39286 6,212094 4,25 0,000 14,10385 38,68186
2009 44,00499 6,668892 6,60 0,000 30,81234 57,19765
2010 32,16928 6,525077 4,93 0,000 19,26112 45,07744
2011 49,21547 6,458884 7,62 0,000 36,43826 61,99268
_cons 153,9978 5,159037 29,85 0,000 143,792 164,2036
The following tables present the results of the empirical analysis which uses the regression analysis detailed in Table 1 when, for each year, the MUD is selected on the basis of the difference in price levels (in RON/MWh) between each contract’s estimated price and its corresponding observed price. Tables 2 and 3 below present the differences between Hidroelectrica’s contractual purchase prices per each of the years (i.e.: 2009-2011) vis-à-vis the simulated price benchmark for the two companies under investigation.

In 2009, the MUD contract, that is the contract in the dataset with the highest difference between the observed price and its corresponding estimated price, has a price difference estimated at 69,73 RON/MWh. None of the two contracts between Hidroelectrica and Termoelectrica and Electrocentrale Deva has an observed price above their estimated price with a price difference larger than 69,73 RON/MWh (see Table 2).

In 2010, the MUD contract has a price difference estimated at 45,36 RON/MWh. Both contracts between Hidroelectrica and Termoelectrica and Electrocentrale Deva have an observed price above their estimated price with a price difference larger than 45,36 RON/MWh, that is a difference of 53,05 RON/MWh for the contract with Termoelectrica and 51,37 RON/MWh for the contract with Electrocentrale Deva (see Table 2).

In 2011, the MUD contract has a price difference estimated at 30,12 RON/MWh. The two contracts between Hidroelectrica and Termoelectrica and respectively between Hidroelectrica and Electrocentrale Deva have an observed price above their estimated price with a price difference larger than 30,12 RON/MWh, that is a difference of 38,62 RON/MWh for the contract with Termoelectrica and 32,64 RON/MWh for the contract with Electrocentrale Deva (see Table 2).


(RON/MWh)
TERMOELECTRICA 2009 2010 2011
Observed price (OP) 227,40 230,00 234,40
Predicted price (PP) 187,69 176,95 195,78
Difference (OP-PP) 39,71 53,05 38,62
MUD 69,73 45,36 30,12
Difference Observed price – Predicted price + MUD < MUD 7,69 8,50
ELECTROCENTRALE DEVA 2009 2010 2011
Observed price (OP) 230,20 234,00 234,00
Predicted price (PP) 192,28 182,63 201,54
Difference (OP-PP) 37,92 51,37 32,46
MUD 69,73 45,36 30,12
Difference Observed price – Predicted price + MUD < MUD 6,01 2,34

The results above show that the prices paid by Hidroelectrica to both Termoelectrica and Electrocentrale Deva in 2010 and 2011 are above a reasonable benchmark determined by the dataset contracts. However, this comparison is made between retail contracts (all contracts in the dataset) and wholesale contracts between Hidroelectrica and Electrocentrale Deva and Termoelectrica. In other words, the simulated benchmark prices include retailing costs which the two contracts did not incur and, therefore, the simulated benchmark prices are higher than corresponding wholesale prices. In order to capture this difference, it is therefore indispensable to deduce a retail margin of 5 % from the absolute value of the MUD. The results are shown in the table below and further confirm prices above a market benchmark in 2010 and 2011 for the two suppliers:


(RON/ MWh)
TERMOELECTRICA 2009 2010 2011
Observed price (OP) 227,40 230,00 234,40
Predicted price (PP) 187,69 176,95 195,78
Difference (OP-PP) 39,71 53,05 38,62
MUD 69,73 45,36 30,12
Difference Observed price – ((Predicted price + MUD) – 5 %) < MUD 18,81 19,80
ELECTROCENTRALE DEVA 2009 2010 2011
Observed price (OP) 230,20 234,00 234,00
Predicted price (PP) 192,28 182,63 201,54
Difference (OP-PP) 37,92 51,37 32,46
MUD 69,73 45,36 30,12
Difference Observed price – ((Predicted price + MUD) – 5 %) < MUD 17,41 13,92

In conclusion, the econometric analysis indicates contract prices for Termoelectrica and Electrocentrale Deva above market prices. However, given the wide interval of uncertainty which is not captured by the model, the conclusion of the econometric analysis needs to be complemented with additional economic information on market-conformity of Hidroelectrica's behaviour and/or other contract data.
