Data are collected through a survey.

Multiannual

Sine is an ongoing system to observe and monitor a generation (or set) of new enterprises every four years.

In this case, a generation is a group of enterprises created over the same period (the first half) of a given year. Each generation of enterprises is therefore only represented by the companies created in the first half of the year.

For each generation, the information is collected using three surveys:

• the first, a few months after the creation of the enterprise;

• the second, at the end of the third year of existence of the enterprise;

• the third, five years after its creation.

November 2026 to April 2027 (wave 1)

November 2029 to April 2030 (wave 2)

November 2031 to April 2032 (wave 3)

Legal unit

Not all new businesses are surveyed.

The Sine 2026 cohort samples are drawn from business start-ups registered in the SIRUS statistical register during the first half of 2026, divided into strata according to region, sector of activity and business type (sole proprietorships excluding micro-entrepreneurs, micro-entrepreneurs and companies).

The region corresponds to the new regions resulting from the territorial reform.

The sampling method used ensures that the results are both nationally and regionally representative.

Businesses that have ceased trading between two surveys are surveyed in the round following their closure, but not in subsequent rounds.

The total Sine 2026 sample (first survey of the 2026 generation) comprises 75,000 entrepreneurs.

The second survey of this cohort will take place in 2029 and the third in 2031.

Since the 2022 generation, the sample has covered Mayotte for all types of creator.

75,000

None

Non-responding companies are contacted.

The raw data are cleaned and adjusted according to the methods described below.

Partial non-response is subject to imputation: correction of the data by cold-deck (on employment from the HERACLES source, on turnover from the ESANE source or Acoss) or hot-deck (imputation of the other responses to the questionnaire by donor/receiver).

Total non-response is adjusted by imputation, in two steps: imputation of activity status (active or ceased) using an activity status model, then imputation using a non-response model. Successive reweightings would lead to having three sets of weights in the final file, one for each survey, at the end of the three surveys of the cohort. This would pose difficult problems for crossing several variables from different waves.

not applicable

not applicable