The second is R-Square, which reflects the explanatory power of the independent variable X to the dependent Special Database variable Y. For example, if we find R-Square = 0.96, it means that 96% of the change in Y can be explained by the change in X. The linear relationship between the two is perfect and convincing. The third is P-Value, which reflects the statistical significance of the linear relationship. The smaller the P-Value, the more likely there is a Special Database linear relationship between the independent variable and the dependent variable. Academically, P-Value generally needs to be less than 0.05 to be meaningful.
It can be appropriately relaxed in practice. The movie box office data in the United States is very complete.
We used all the Special Database annual data since 1980 to carry out regression analysis and came to the conclusion that: looking at the annual unit, the U.S. movie industry is a strong cyclical industry, and macroeconomic data and movies The correlation coefficient of box office receipts is large, explanatory, and statistically significant. Similar conclusions Special Database can be drawn whether using GDP, household disposable income or total personal expenditure as independent variables. Sorry, there is really no "lipstick effect" in the media and entertainment industry!
What's more, the conclusions of the regression analysis are the same regardless of whether the macro data of the Special Database current period or the previous period are used. This shows that macro data such as GDP not only affects the box office of the current year, but also has a forward-looking perspective on the box office of the next year. In fact, even with the naked eye, you can see that the data points jointly defined by U.S. movie box office Special Database receipts and GDP, or residents’ disposable income, fall on an almost perfect line, a linear relationship that statisticians can only dream of. Sorry, there is really no "lipstick effect" in the media and entertainment industry!